# DecimalAI

- [Catch agent regressions before they ship](https://docs.decimal.ai/introduction.md): The manifest-aware platform for agent change management — catch regressions before deploy, share proven skills, and keep your training data valid as your agent evolves.
- [Build an agent](https://docs.decimal.ai/build-an-agent.md): Create an agent and get it answering — from scratch, from a skill pack, or from skills you pick yourself. About five minutes.
- [Tutorials](https://docs.decimal.ai/tutorials.md): Five tutorials, what each one actually costs you, and what you are holding at the end — starting with the one that needs no account at all.
- [Install a Skill in 5 Minutes](https://docs.decimal.ai/tutorials/install-a-skill.md): Tutorial: pick a skill with a verified benchmark from the public registry, install it into Claude Code or Cursor, and watch it fire — no signup, no SDK, no API key.
- [Quickstart](https://docs.decimal.ai/quickstart.md): See both demos in 2 minutes on seeded data, then wire DecimalAI to your own agent.
- [The 2-Minute Demo](https://docs.decimal.ai/tutorials/two-minute-demo.md): See the impact report and the ranked skills registry on realistic seeded data — one command each, no agent code, no LLM keys.
- [DecimalAI for Engineers](https://docs.decimal.ai/for-engineers.md): Shipping agents to production safely. The deploy-safety reading path: traces, manifests, regression checks, and CI integration.
- [DecimalAI for Platform Teams](https://docs.decimal.ai/for-platform-teams.md): Operating DecimalAI in production: multi-agent debug, teams, RBAC, and security.
- [Agents](https://docs.decimal.ai/guides/agents.md): Naming, splitting, renaming, and configuring per-agent evaluation. The Agent is the unit of identity that ties every other DecimalAI concept together.
- [Tracing](https://docs.decimal.ai/guides/tracing.md): Capture and inspect agent execution traces across any framework.
- [Manifests & Versioning](https://docs.decimal.ai/guides/manifests.md): Automatic agent version tracking with compatibility scoring — detect what changed and what broke.
- [Regression Check (GitHub Action)](https://docs.decimal.ai/guides/regression-check.md): Catch agent regressions before they ship — manifest-aware impact analysis on every PR, no eval cases required.
- [Post-deploy Bisect](https://docs.decimal.ai/guides/post-deploy-bisect.md): A regression slipped past the pre-deploy check. Find the manifest version that broke a metric — without re-running anything.
- [Compatibility Policies](https://docs.decimal.ai/guides/compatibility-policies.md): How DecimalAI classifies traces when your agent changes — keep, repair, replay, or drop — and how to customize the rules.
- [Replay](https://docs.decimal.ai/guides/replay.md): Re-run stale traces through your updated agent and compare results.
- [Skills](https://docs.decimal.ai/guides/skills.md): Reusable agent instructions with observability — from SKILL.md to production analytics.
- [Prompt & skills, versions and roll back](https://docs.decimal.ai/guides/agent-setup-versions.md): See exactly what an agent receives, change its skills and prompt as one reviewed change, and roll any change back.
- [Authoring Skills](https://docs.decimal.ai/guides/authoring-skills.md): How to write a skill that triggers at the right times, changes behavior, and proves it honestly — classification, description craft, body craft, and the eval suite.
- [Assemble an Agent from Skills](https://docs.decimal.ai/guides/agents-from-skills.md): The mental model for building agents as a lean main prompt plus a skill bundle — router mechanics, progressive disclosure, fork vs. install vs. use, and how to choose skills from the registry.
- [Community Registry](https://docs.decimal.ai/guides/registry.md): Browse, install, fork, and publish skills — with real production effectiveness data, not just star counts.
- [Vocabulary](https://docs.decimal.ai/guides/vocabulary.md): One meaning each: install, fork, export, users, uses, instrument, and the three things called an agent.
- [Skills on Disk](https://docs.decimal.ai/guides/skills-on-disk.md): Install registry skills as plain folders your framework loads natively, locked to exact bytes for CI and Docker: decimalai skills add, install --frozen, update, verify.
- [Native Skill Loaders](https://docs.decimal.ai/guides/native-skill-loaders.md): The eight agent frameworks that read installed skill folders themselves: the one line that points each at your skills, what DecimalAI records when one loads a skill, and the gaps each has upstream.
- [Claude Code Plugin](https://docs.decimal.ai/guides/claude-code.md): Search and install agent skills ranked by measured effectiveness, from inside Claude Code. Three slash commands, no account, no API key — plus the other two ways to get a registry skill into Claude Code.
- [Use Skills Without the SDK](https://docs.decimal.ai/guides/use-skills-without-the-sdk.md): Every route from the public registry to your agent that doesn't need the Python SDK in your agent: web Copy, raw URLs and curl, `decimalai skills pull`, the MCP server, and the Claude Code plugin. Each one writes the registry's exact bytes.
- [SkillScore](https://docs.decimal.ai/guides/skillscore.md): The evaluated quality behind a skill's score, and how it differs from lifetime usage.
- [skillevaluation (eval.yaml)](https://docs.decimal.ai/guides/skillevaluation.md): The open A/B benchmark format + runner for agent skills. Run it locally for free on your own API key; push results to DecimalAI; verified runs power the registry.
- [Playground](https://docs.decimal.ai/guides/playground.md): Re-run production traces with modified prompts. Edit skills, compare outputs, and iterate on agent behavior — all with your own API keys.
- [Skills Observability](https://docs.decimal.ai/tutorials/skills-observability.md): Tutorial: Track skill effectiveness from discovery to production analytics.
- [Build a Support Agent from Skills](https://docs.decimal.ai/tutorials/support-agent-from-skills.md): Preview a recorded example, build a local agent without an account, or save a starter and try a bounded hosted run.
- [How skills are vetted](https://docs.decimal.ai/guides/trust-safety/how-skills-are-vetted.md): Skills are code your agent loads and acts on. SkillSafety is the vetting pipeline — static scan, AI review, content review — that decides what reaches the registry, and what it's labeled.
- [Fixing a blocked publish](https://docs.decimal.ai/guides/trust-safety/fixing-a-blocked-publish.md): Every reason the registry can refuse a publish — what each one means, the exact fix, and how to clear it before your launch moment.
- [Content policy](https://docs.decimal.ai/guides/trust-safety/content-policy.md): What a published skill's text may not contain — the eight prohibited-content categories DecimalAI's content-safety review enforces, and how to fix a flag.
- [What scanning can't catch](https://docs.decimal.ai/guides/trust-safety/what-scanning-cant-catch.md): The honest limits of skill scanning — why prompt-level approval is not a security boundary, and how to run defense in depth as a consumer.
- [Scanning locally and in CI](https://docs.decimal.ai/guides/trust-safety/scanning-locally-and-in-ci.md): Run the exact same SkillSafety scanner the publish gate runs — on your laptop and in CI, free, with no API key and nothing leaving your machine.
- [Evaluations](https://docs.decimal.ai/guides/evaluations.md): Automated quality checks on agent traces — pre-built evaluators, LLM-as-judge, and the evaluation dashboard.
- [Datasets & Training](https://docs.decimal.ai/guides/datasets.md): Build training datasets from production traces and fine-tune models.
- [End-to-End Training Pipeline](https://docs.decimal.ai/tutorials/training-pipeline.md): Tutorial: From production traces to a fine-tuned model in one workflow.
- [Multi-Agent Systems](https://docs.decimal.ai/guides/multi-agent.md): Instrument multi-agent systems — per-sub-agent datasets, orchestration-aware training data, and independent version tracking.
- [Teams & Workspaces](https://docs.decimal.ai/guides/teams.md): Organize agents, traces, and skills by team with role-based access.
- [Troubleshooting](https://docs.decimal.ai/guides/troubleshooting.md): Common issues and how to fix them.
- [Skill lift does not survive a model change](https://docs.decimal.ai/research/skill-lift-across-models.md): We re-measured 45 agent skills on two models. Every one of them moved. A lift number without a pinned baseline is not a measurement.
- [Concepts](https://docs.decimal.ai/concepts.md): Every key concept in DecimalAI — how traces, manifests, evaluations, and multi-agent systems work together.
- [Execution Model](https://docs.decimal.ai/concepts/execution-model.md): How DecimalAI captures and organizes agent activity — traces, spans, LLM calls, sessions.
- [Versioning & Compatibility](https://docs.decimal.ai/concepts/versioning.md): Manifests, components, compatibility verdicts, and the engine that classifies traces against agent changes.
- [Evaluation](https://docs.decimal.ai/concepts/evaluation.md): Evaluators, eval scores, eval verdicts, and the unified decision engine that combines quality + compatibility.
- [Multi-Agent Systems](https://docs.decimal.ai/concepts/multi-agent.md): Orchestrators, sub-agents, delegation vs handoff, and drift detection.
- [Skills & Data Pipeline](https://docs.decimal.ai/concepts/skills-and-data.md): Skills (SKILL.md), datasets, export formats (SFT/DPO), replay, and repair.
- [Glossary](https://docs.decimal.ai/glossary.md): Quick-reference definitions for every term used in DecimalAI.
- [Why DecimalAI?](https://docs.decimal.ai/guides/why-decimalai.md): What manifest-aware agent change management is, why it's a different category from observability, and when DecimalAI is the right tool for it.
- [Trust & Exit](https://docs.decimal.ai/guides/trust-and-exit.md): What you're actually depending on when you adopt DecimalAI — open formats, no code in your LLM critical path, everything exportable — and what leaving looks like.
- [Pricing](https://docs.decimal.ai/pricing.md): DecimalAI plan tiers — Free, Core, Pro, Enterprise — with quotas, rate limits, and Skills Registry features.
- [Security & Data Handling](https://docs.decimal.ai/security.md): What DecimalAI stores, how it's encrypted, retention policies, and deletion.
- [FAQ](https://docs.decimal.ai/faq.md): Quick answers to common questions about DecimalAI.
- [Migrations](https://docs.decimal.ai/migrations.md): Move code to SDK 0.25, 0.23, 0.21, 0.20, 0.19 and 0.18, move a project to SDK 0.15's skills on disk, and map LangSmith, Braintrust, Langfuse and Phoenix concepts to DecimalAI.
- [Changelog](https://docs.decimal.ai/changelog.md): Recent changes to the DecimalAI platform, SDK, and GitHub Action.
- [Roadmap](https://docs.decimal.ai/roadmap.md): What's in flight and planned on the DecimalAI platform & SDK.
- [Python SDK](https://docs.decimal.ai/sdk/python.md): The `decimalai` Python package — installation, tracing, manifests, evaluations, replay, datasets, framework adapters, and skills.
- [Init & Setup](https://docs.decimal.ai/sdk/python/init.md): Install the package, initialize the SDK, and configure environment variables. The starting point for every Python SDK user.
- [Tracing](https://docs.decimal.ai/sdk/python/tracing.md): Decorators and helpers to record LLM calls, tool calls, and trace boundaries from Python.
- [Manifests](https://docs.decimal.ai/sdk/python/manifests.md): Explicitly register agent configuration for version tracking when auto-detection isn't enough.
- [Evaluations](https://docs.decimal.ai/sdk/python/evaluations.md): Push scores onto traces, define custom evaluators with @eval, and import results from DeepEval / LangSmith.
- [Replay & Experiments](https://docs.decimal.ai/sdk/python/replay.md): Re-run historical traces against a new manifest, and run controlled A/B comparisons between variants.
- [Datasets & Training](https://docs.decimal.ai/sdk/python/datasets.md): Pull versioned datasets to JSONL or Parquet, push to HuggingFace Hub, or load directly as a HuggingFace Dataset object.
- [Framework Instrumentation](https://docs.decimal.ai/sdk/python/frameworks.md): Auto-capture traces from LangChain, OpenAI Agents, your own OpenAI SDK loop, Claude Agent SDK, Pydantic AI, Google ADK, the Anthropic Messages API, LlamaIndex, or any OpenTelemetry-emitting framework — usually with one line of code.
- [LangChain & LangGraph](https://docs.decimal.ai/sdk/python/frameworks/langchain.md): Give a LangChain agent its DecimalAI prompt and skills as one create_agent middleware with agent_config(), and trace every chain, graph and agent run.
- [OpenAI Agents SDK](https://docs.decimal.ai/sdk/python/frameworks/openai-agents.md): Give an OpenAI Agents SDK agent its prompt and skills with agent_config(): it runs before you have a DecimalAI account, and adding a key connects it, traces every run and lets you edit its prompt in the dashboard.
- [OpenAI SDK](https://docs.decimal.ai/sdk/python/frameworks/openai.md): Give an agent you build on the openai SDK, with your own Chat Completions or Responses API tool loop, its DecimalAI prompt and skills with agent_config(), one run per user message, and trace each run.
- [Gemini API](https://docs.decimal.ai/sdk/python/frameworks/google-genai.md): Give an agent you build on the google-genai SDK its DecimalAI prompt and skills with agent_config(), one run per user message, with automatic function calling or a loop of your own, and trace each run.
- [Claude Agent SDK / Claude Code](https://docs.decimal.ai/sdk/python/frameworks/claude-agent-sdk.md): Trace Claude Agent SDK query() runs, and load registry skills installed in your project as a Claude Code plugin.
- [Pydantic AI](https://docs.decimal.ai/sdk/python/frameworks/pydantic-ai.md): Give a Pydantic AI agent its DecimalAI prompt and skills as one capability with agent_config(), which also traces each of its runs.
- [Google ADK](https://docs.decimal.ai/sdk/python/frameworks/adk.md): Give a Google ADK agent its DecimalAI prompt and skills with agent_config(), and trace every invocation with DecimalAIPlugin in the App.
- [Anthropic Messages API](https://docs.decimal.ai/sdk/python/frameworks/anthropic.md): Give a Claude agent built on the anthropic SDK its DecimalAI prompt and skills with agent_config(), one run per user message, and trace each run.
- [LlamaIndex](https://docs.decimal.ai/sdk/python/frameworks/llamaindex.md): Auto-instrument LlamaIndex query engines, retrievers, and synthesizers.
- [CrewAI](https://docs.decimal.ai/sdk/python/frameworks/crewai.md): Trace CrewAI crews through the OpenInference instrumentors and DecimalAI's OTel exporter, and deliver your agent's skills into every agent turn.
- [Generic OpenTelemetry](https://docs.decimal.ai/sdk/python/frameworks/otel.md): Capture traces from any framework that emits OTel spans following the gen_ai.* semantic conventions.
- [Skills](https://docs.decimal.ai/sdk/python/skills.md): Install registry skills into a project, point your framework's own skill loader at them, sync the skills you write, and route skills at runtime.
- [CLI](https://docs.decimal.ai/sdk/cli.md): Command-line interface for traces, evaluations, skills, datasets, replay, and more.
- [Authentication](https://docs.decimal.ai/api-reference/authentication.md): API key authentication, scopes, permissions, rotation, and revocation.
- [Errors](https://docs.decimal.ai/api-reference/errors.md): HTTP error codes returned by the DecimalAI API and how to handle them.
- [Common endpoints](https://docs.decimal.ai/api-reference/common-endpoints.md): Quick reference for the endpoints most users hit, with SDK wrapper mappings.
- [Traces API](https://docs.decimal.ai/api-reference/traces/overview.md): Ingest, search, and inspect agent execution traces — the atomic unit of the platform.
- [Search Traces](https://docs.decimal.ai/api-reference/traces/search.md): Search traces using query parameters on the List Traces endpoint.
- [Evaluations API](https://docs.decimal.ai/api-reference/evaluations/overview.md): Push, query, and aggregate quality scores on traces. Drives the keep / repair / replay / drop verdict that decides what becomes training data.
- [Replay API](https://docs.decimal.ai/api-reference/replay/overview.md): Re-run historical traces against a new manifest. Confirms behavioral impact of an agent change empirically.
- [Skills API](https://docs.decimal.ai/api-reference/skills/overview.md): Create, version, fork, and publish reusable instruction blocks (SKILL.md). First-class manifest components.
- [Skill Router](https://docs.decimal.ai/api-reference/skills/router.md): Load the right skills into your agent's prompt on every turn — and get per-skill effectiveness scoring for free.
- [Manifests API](https://docs.decimal.ai/api-reference/manifests/overview.md): Register and inspect agent manifest versions — the structural identity DecimalAI uses for change detection.
- [Datasets API](https://docs.decimal.ai/api-reference/datasets/overview.md): Build versioned SFT/DPO training datasets from manifest-classified, eval-scored traces.
- [Registry API](https://docs.decimal.ai/api-reference/registry/overview.md): Browse, fork, and rate public skills. The shared catalog of reusable SKILL.md blocks, ranked by SkillScore.
- [List agents](https://docs.decimal.ai/api-reference/agents/list-agents.md): List distinct agents with summary stats.
- [Create an agent](https://docs.decimal.ai/api-reference/agents/create-an-agent.md): Create an agent by registering its baseline manifest.
- [What each agent runs, for Home](https://docs.decimal.ai/api-reference/agents/what-each-agent-runs-for-home.md): For each named agent: the prompt version it is served, its runs in the last 30 days, how many loaded a skill and which skills, its graded runs, and the newest change to its prompt or skills. Across the workspace: skill links pinned behind a newer version, the newest config versions (one edit that ch…
- [Get Agent Setup](https://docs.decimal.ai/api-reference/agents/get-agent-setup.md)
- [Start Setup Check](https://docs.decimal.ai/api-reference/agents/start-setup-check.md)
- [Finish Setup Check](https://docs.decimal.ai/api-reference/agents/finish-setup-check.md)
- [Get Setup Check](https://docs.decimal.ai/api-reference/agents/get-setup-check.md)
- [View Setup Check Trace](https://docs.decimal.ai/api-reference/agents/view-setup-check-trace.md)
- [Retry Initial Skills](https://docs.decimal.ai/api-reference/agents/retry-initial-skills.md): Retry only unfinished original assignments; this cannot add new skills.
- [Get the multi-agent topology for an agent](https://docs.decimal.ai/api-reference/agents/get-the-multi-agent-topology-for-an-agent.md): Get the multi-agent topology for an agent.
- [Generate synthetic prompts for an agent](https://docs.decimal.ai/api-reference/agents/generate-synthetic-prompts-for-an-agent.md): Generate synthetic prompts for an agent.
- [Get agent eval policy (deprecated)](https://docs.decimal.ai/api-reference/agents/get-agent-eval-policy-deprecated.md): DEPRECATED — Use GET /api/v1/evaluators?agent_name=... instead.
- [Upsert agent eval policy (deprecated)](https://docs.decimal.ai/api-reference/agents/upsert-agent-eval-policy-deprecated.md): DEPRECATED — Use POST /api/v1/evaluators instead.
- [Get per-agent eval budget (deprecated)](https://docs.decimal.ai/api-reference/agents/get-per-agent-eval-budget-deprecated.md): **Deprecated.** Per-agent budgets are no longer enforced — LLM-judge usage is tracked at the org level via billing. This endpoint returns a stub for backward compatibility and will be removed in a future release. Use `GET /api/v1/billing/usage` instead.
- [Ranked skill suggestions for this agent](https://docs.decimal.ai/api-reference/agents/ranked-skill-suggestions-for-this-agent.md): Return a ranked list of skills to install on, or remove from, this agent.
- [Get health metrics for each sub-agent of an orchestrator](https://docs.decimal.ai/api-reference/agents/get-health-metrics-for-each-sub-agent-of-an-orchestrator.md): Get health metrics for each sub-agent of an orchestrator.
- [Get delegation analytics for an orchestrator agent](https://docs.decimal.ai/api-reference/agents/get-delegation-analytics-for-an-orchestrator-agent.md): Get delegation analytics for an orchestrator agent.
- [Daily token+cost trend for an agent over a lookback window](https://docs.decimal.ai/api-reference/agents/daily-token+cost-trend-for-an-agent-over-a-lookback-window.md): Return per-day {trace_count, total_tokens, total_cost_usd} for an agent.
- [Get compatibility summary for an agent's latest manifest transition](https://docs.decimal.ai/api-reference/agents/get-compatibility-summary-for-an-agents-latest-manifest-transition.md): Get compatibility summary for an agent's latest manifest transition.
- [Aggregate Impact Report for an agent — composes compat-summary](https://docs.decimal.ai/api-reference/agents/aggregate-impact-report-for-an-agent-—-composes-compat-summary.md): Aggregate Impact Report for an agent.
- [Cascade-delete an agent and all dependent data](https://docs.decimal.ai/api-reference/agents/cascade-delete-an-agent-and-all-dependent-data.md): Cascade-delete an agent and all of its dependent data.
- [Get contextual cross-pillar suggestions for an agent](https://docs.decimal.ai/api-reference/agents/get-contextual-cross-pillar-suggestions-for-an-agent.md): Get contextual cross-pillar suggestions for an agent.
- [Get org-wide cross-pillar suggestions (not scoped to any agent)](https://docs.decimal.ai/api-reference/agents/get-org-wide-cross-pillar-suggestions-not-scoped-to-any-agent.md): Get org-wide cross-pillar suggestions (not scoped to any agent).
- [Rename an agent. The old name continues to resolve via the alias table.](https://docs.decimal.ai/api-reference/agents/rename-an-agent-the-old-name-continues-to-resolve-via-the-alias-table.md): Rename ``agent_name`` to ``payload["new_name"]`` for the caller's org.
- [List skills assigned to this agent](https://docs.decimal.ai/api-reference/agents/list-skills-assigned-to-this-agent.md): Return all skill subscriptions for the given agent.
- [How often this agent's routing offered each skill, and how often a run loaded it](https://docs.decimal.ai/api-reference/agents/how-often-this-agents-routing-offered-each-skill-and-how-often-a-run-loaded-it.md): `GET /skills/{name}/router-stats?agent_name=` for every skill at once, keyed by skill name.
- [Assign a skill to this agent (optionally pinned to a specific version)](https://docs.decimal.ai/api-reference/agents/assign-a-skill-to-this-agent-optionally-pinned-to-a-specific-version.md): Subscribe the agent to the skill, idempotent.
- [Unassign a skill from this agent](https://docs.decimal.ai/api-reference/agents/unassign-a-skill-from-this-agent.md): Remove the (agent_name, skill_id) subscription.
- [Always include a skill's full text in this agent's runs, or stop](https://docs.decimal.ai/api-reference/agents/always-include-a-skills-full-text-in-this-agents-runs-or-stop.md): Set whether every run of the agent gets this skill's full text.
- [Assign many skills to many agents in a single request](https://docs.decimal.ai/api-reference/agents/assign-many-skills-to-many-agents-in-a-single-request.md): Batch equivalent of ``POST /{agent_name}/skills/{skill_id}``.
- [Get this agent's configured system prompt](https://docs.decimal.ai/api-reference/agents/get-this-agents-configured-system-prompt.md): Return the agent's configured system prompt, or `null` if none is set.
- [Set this agent's system prompt](https://docs.decimal.ai/api-reference/agents/set-this-agents-system-prompt.md): Set or edit the agent's system prompt. A new version only if it changed.
- [Clear this agent's system prompt (history is retained)](https://docs.decimal.ai/api-reference/agents/clear-this-agents-system-prompt-history-is-retained.md): Return the agent to "no prompt set" without destroying its history.
- [List this agent's system-prompt version history](https://docs.decimal.ai/api-reference/agents/list-this-agents-system-prompt-version-history.md): Newest first. An agent with no prompt is `{"versions": [], "total": 0}`.
- [Get one historical version of this agent's system prompt](https://docs.decimal.ai/api-reference/agents/get-one-historical-version-of-this-agents-system-prompt.md): One version's full content — a single probe on the (prompt, number) unique.
- [Pin this agent's prompt to a version, or track latest](https://docs.decimal.ai/api-reference/agents/pin-this-agents-prompt-to-a-version-or-track-latest.md): Set `version_mode` and the pin together, in one UPDATE.
- [Trial Availability](https://docs.decimal.ai/api-reference/agents/trial-availability.md)
- [Create Trial](https://docs.decimal.ai/api-reference/agents/create-trial.md)
- [Get Trial](https://docs.decimal.ai/api-reference/agents/get-trial.md)
- [What applying staged changes (or a roll back) would do — writes nothing](https://docs.decimal.ai/api-reference/agent-config/what-applying-staged-changes-or-a-roll-back-would-do-—-writes-nothing.md)
- [Apply staged changes (or a roll back) in one transaction, as one config version](https://docs.decimal.ai/api-reference/agent-config/apply-staged-changes-or-a-roll-back-in-one-transaction-as-one-config-version.md)
- [The agent's running experiment, its ended ones, and each skill's measured lift](https://docs.decimal.ai/api-reference/agent-config/the-agents-running-experiment-its-ended-ones-and-each-skills-measured-lift.md): While an experiment runs, it shows counts and checks only, never a rate or a difference.
- [One experiment: its progress while it runs, its result once it ends](https://docs.decimal.ai/api-reference/agent-config/one-experiment:-its-progress-while-it-runs-its-result-once-it-ends.md)
- [The agent's current config version and its last three](https://docs.decimal.ai/api-reference/agent-config/the-agents-current-config-version-and-its-last-three.md)
- [Two config versions side by side: prompt, skills, the list text, results](https://docs.decimal.ai/api-reference/agent-config/two-config-versions-side-by-side:-prompt-skills-the-list-text-results.md)
- [One config version: its setup, what changed and its results](https://docs.decimal.ai/api-reference/agent-config/one-config-version:-its-setup-what-changed-and-its-results.md)
- [The agent's config versions, newest first, with code-change markers](https://docs.decimal.ai/api-reference/agent-config/the-agents-config-versions-newest-first-with-code-change-markers.md)
- [Save a reviewed public starter into your workspace](https://docs.decimal.ai/api-reference/registry/save-a-reviewed-public-starter-into-your-workspace.md)
- [Read a recorded public skill example, without model inference](https://docs.decimal.ai/api-reference/registry/read-a-recorded-public-skill-example-without-model-inference.md)
- [Browse the public skills registry](https://docs.decimal.ai/api-reference/registry/browse-the-public-skills-registry.md): Browse the public skills registry.
- [Search the public skills registry, with the query in the request body](https://docs.decimal.ai/api-reference/registry/search-the-public-skills-registry-with-the-query-in-the-request-body.md): `GET /skills?q=` with the query in the request body instead of the URL.
- [Get a registry skill](https://docs.decimal.ai/api-reference/registry/get-a-registry-skill.md): Returns the full record for a public registry skill, including body markdown, attachments, SkillScore (evidence-tiered quality composite), and review summary.
- [Fork lineage tree for a public registry skill](https://docs.decimal.ai/api-reference/registry/fork-lineage-tree-for-a-public-registry-skill.md): Returns the fork tree rooted at this public registry skill.
- [Stage R trigger dry-run: would this description surface for these prompts](https://docs.decimal.ai/api-reference/registry/stage-r-trigger-dry-run:-would-this-description-surface-for-these-prompts.md): Score prompts through the SAME hybrid retrieval `smart_route` uses (RRF over dense pgvector + sparse tsvector — shared code, not a re-implementation) against your org's live index PLUS the candidate. Per prompt: `{score, rank, would_surface}` where `would_surface` means the candidate lands in top_k.
- [Ingest an anonymous registry event ping](https://docs.decimal.ai/api-reference/registry/ingest-an-anonymous-registry-event-ping.md): Ingest an anonymous install/copy/fetch ping from a distribution channel.
- [Advisory novelty check: published skills most similar to this one (never blocks publish)](https://docs.decimal.ai/api-reference/registry/advisory-novelty-check:-published-skills-most-similar-to-this-one-never-blocks-publish.md): Nearest PUBLISHED skills to `{name}` by description-embedding cosine.
- [Advisory publish-time novelty dry-run for an unpublished/ad-hoc skill (never blocks)](https://docs.decimal.ai/api-reference/registry/advisory-publish-time-novelty-dry-run-for-an-unpublishedad-hoc-skill-never-blocks.md): Mirror of `/trigger-dryrun` for the novelty rail: dry-run an unpublished (or draft) skill's description against the published index BEFORE publishing, to see what it most resembles. Advisory-only — recall/dedup is a hint, not a gate.
- [Dry-run a hypothetical user message against a public registry skill (no auth, no LLM call)](https://docs.decimal.ai/api-reference/registry/dry-run-a-hypothetical-user-message-against-a-public-registry-skill-no-auth-no-llm-call.md): Public dry-run for a registry skill. Mirrors the auth'd /api/v1/skills/{name}/playground-run but takes a public registry skill ID and skips the org-ownership check, so a visitor can sanity-check the trigger match + rendered body BEFORE installing.
- [Fetch a specific version's body markdown for a public registry skill](https://docs.decimal.ai/api-reference/registry/fetch-a-specific-versions-body-markdown-for-a-public-registry-skill.md): Returns the body_markdown for a specific version of a public registry skill. No authentication required. Fetch two versions to diff a skill's body from one release to the next.
- [Get a public registry skill's eval.yaml (latest version, or ?version=N)](https://docs.decimal.ai/api-reference/registry/get-a-public-registry-skills-evalyaml-latest-version-or-?version=n.md): Return a public registry skill's `eval.yaml` text.
- [Latest benchmark run + per-case results for a public registry skill](https://docs.decimal.ai/api-reference/registry/latest-benchmark-run-+-per-case-results-for-a-public-registry-skill.md): Anonymous-readable view of the publisher's latest benchmark run.
- [Precomputed indexable catalogue](https://docs.decimal.ai/api-reference/registry/precomputed-indexable-catalogue.md)
- [Bulk name+lastmod feed of search-indexable skills (sitemap source)](https://docs.decimal.ai/api-reference/registry/bulk-name+lastmod-feed-of-search-indexable-skills-sitemap-source.md): Bulk name + lastmod feed of search-indexable registry skills.
- [Index-eligible sibling skills, for the scorecard's internal-link block](https://docs.decimal.ai/api-reference/registry/index-eligible-sibling-skills-for-the-scorecards-internal-link-block.md): Skills adjacent to this one in the registry's `(source_repo, url_slug)` order.
- [Published skills that do the same job, for the scorecard's alternatives block](https://docs.decimal.ai/api-reference/registry/published-skills-that-do-the-same-job-for-the-scorecards-alternatives-block.md): Nearest published skills by description vector, at or above the same-job threshold.
- [Cross-org production trace aggregations for a public registry skill](https://docs.decimal.ai/api-reference/registry/cross-org-production-trace-aggregations-for-a-public-registry-skill.md): Anonymous-readable, privacy-safe Live Traces summary.
- [Public Skills Leaderboard — ranked by performance dimension within a window](https://docs.decimal.ai/api-reference/registry/public-skills-leaderboard-—-ranked-by-performance-dimension-within-a-window.md): Anonymous-readable, time-windowed ranked leaderboard.
- [Your organization's durable skill activation receipts](https://docs.decimal.ai/api-reference/registry/your-organizations-durable-skill-activation-receipts.md)
- [Usage time-series for a public registry skill (npm-style chart data)](https://docs.decimal.ai/api-reference/registry/usage-time-series-for-a-public-registry-skill-npm-style-chart-data.md): Returns a multi-series usage time-series for a public registry skill, summed across all consuming orgs' forks. The npm-style chart on the public detail page reads from this.
- [Fork a registry skill into your workspace](https://docs.decimal.ai/api-reference/registry/fork-a-registry-skill-into-your-workspace.md): Forks a public registry skill into your organization. The forked skill is fully owned by your org — edits do not affect the public version.
- [Read complete linked-skill configuration](https://docs.decimal.ai/api-reference/registry/read-complete-linked-skill-configuration.md): Return every saved workspace/agent pointer, including exact pin IDs and version labels. ``current_version`` is the newest injectable source version, even before installation. ``source_available`` and ``source_unavailable_reason`` describe the source; ``precedence`` reports availability and reason pe…
- [Replace all linked-skill scopes and version choices atomically](https://docs.decimal.ai/api-reference/registry/replace-all-linked-skill-scopes-and-version-choices-atomically.md): Replace this organization's entire pointer set in one transaction.
- [Use a registry skill — a linked pointer, not a copy](https://docs.decimal.ai/api-reference/registry/use-a-registry-skill-—-a-linked-pointer-not-a-copy.md): Link a public registry skill into your workspace *live* (no fork).
- [Stop using a registry skill — remove the linked pointer](https://docs.decimal.ai/api-reference/registry/stop-using-a-registry-skill-—-remove-the-linked-pointer.md): Remove this org's Use pointer(s) for a registry skill.
- [Rate a registry skill](https://docs.decimal.ai/api-reference/registry/rate-a-registry-skill.md): Rate a registry skill. The caller must have added it to their workspace first — either path counts, a Use (linked) or a fork (owned copy).
- [List attachments for a public registry skill](https://docs.decimal.ai/api-reference/registry/list-attachments-for-a-public-registry-skill.md): List attachments for a public registry skill.
- [Get a single attachment with content for a public registry skill](https://docs.decimal.ai/api-reference/registry/get-a-single-attachment-with-content-for-a-public-registry-skill.md): Get a single attachment with content for a public registry skill.
- [Set the registry badge on a public skill (admin only)](https://docs.decimal.ai/api-reference/registry/set-the-registry-badge-on-a-public-skill-admin-only.md): Set the registry badge on a public skill (admin only).
- [Set the author display name on a registry skill (admin only)](https://docs.decimal.ai/api-reference/registry/set-the-author-display-name-on-a-registry-skill-admin-only.md): Set the author display name on a registry skill (admin only).
- [Download a runnable public Support starter without an account](https://docs.decimal.ai/api-reference/registry/download-a-runnable-public-support-starter-without-an-account.md)
- [List the role packs an agent can be created from](https://docs.decimal.ai/api-reference/registry/list-the-role-packs-an-agent-can-be-created-from.md): Every pack's metadata and starter-prompt hash — no prompt bodies.
- [Get one role pack — starter prompt and starter skills](https://docs.decimal.ai/api-reference/registry/get-one-role-pack-—-starter-prompt-and-starter-skills.md): One pack: metadata, the starter system prompt, and the starter skills.
- [Get the calling org's claim state for an imported skill](https://docs.decimal.ai/api-reference/registry/get-the-calling-orgs-claim-state-for-an-imported-skill.md): Get your organization's claim status for an imported registry skill.
- [Start claiming an imported skill (returns the proof token + instructions)](https://docs.decimal.ai/api-reference/registry/start-claiming-an-imported-skill-returns-the-proof-token-+-instructions.md): Start claiming an imported registry skill that you maintain.
- [Verify a pending claim (fetches the well-known file from the source repo)](https://docs.decimal.ai/api-reference/registry/verify-a-pending-claim-fetches-the-well-known-file-from-the-source-repo.md): Verify a pending claim by reading the proof file from the source repository.
- [Public verified-lift SVG badge for a registry skill (README embed)](https://docs.decimal.ai/api-reference/registry/public-verified-lift-svg-badge-for-a-registry-skill-readme-embed.md): Anonymous SVG badge of a skill's verified lift + the model it was measured on, e.g. ``decimalai | +62% · gemini-3.5-flash``.
- [Get all annotations for a specific trace](https://docs.decimal.ai/api-reference/annotations/get-all-annotations-for-a-specific-trace.md): Get all annotations for a specific trace.
- [Add a human annotation/label to a trace](https://docs.decimal.ai/api-reference/annotations/add-a-human-annotationlabel-to-a-trace.md): Add a human annotation/label to a trace.
- [Update an existing annotation](https://docs.decimal.ai/api-reference/annotations/update-an-existing-annotation.md): Update an existing annotation.
- [Delete an annotation](https://docs.decimal.ai/api-reference/annotations/delete-an-annotation.md): Delete an annotation.
- [Get annotation label distribution and summary stats](https://docs.decimal.ai/api-reference/annotations/get-annotation-label-distribution-and-summary-stats.md): Get annotation label distribution and summary stats.
- [Promote annotated traces into an eval dataset](https://docs.decimal.ai/api-reference/annotations/promote-annotated-traces-into-an-eval-dataset.md): Promote annotated traces into an eval dataset.
- [List recent admin actions — oncall 'what changed' surface](https://docs.decimal.ai/api-reference/audit-log/list-recent-admin-actions-—-oncall-what-changed-surface.md): Return audit log rows for the calling org, newest first.
- [List supported LLM models for the playground](https://docs.decimal.ai/api-reference/auth/list-supported-llm-models-for-the-playground.md): Public catalog of known models the playground can route to, not an exhaustive allowlist. Versioned Gemini, GPT/ChatGPT, OpenAI o-series and Claude text families are accepted for self-run benchmark results; hosted runners retain platform-paid restrictions. Optional `?provider=openai|gemini|anthropic`…
- [API root — HATEOAS-lite index](https://docs.decimal.ai/api-reference/auth/api-root-—-hateoas-lite-index.md): Returns a directory of top-level API resources with deep-link URLs, so you can discover endpoint categories without reading the whole spec. No authentication required.
- [Whoami — confirm key, see scope/permissions/org](https://docs.decimal.ai/api-reference/auth/whoami-—-confirm-key-see-scopepermissionsorg.md): Single-call confirmation that the caller's auth works + what it gives.
- [Compatibility-score badge (keep rate) for an agent](https://docs.decimal.ai/api-reference/badges/compatibility-score-badge-keep-rate-for-an-agent.md): Return an SVG badge of `keep%` from the agent's latest compat report.
- [Get all available plans with limits and pricing](https://docs.decimal.ai/api-reference/billing/get-all-available-plans-with-limits-and-pricing.md): Get all available plans with limits and pricing.
- [Get current plan details and limits](https://docs.decimal.ai/api-reference/billing/get-current-plan-details-and-limits.md): Get current plan details and limits.
- [Get usage for the current billing period](https://docs.decimal.ai/api-reference/billing/get-usage-for-the-current-billing-period.md): Get usage for the current billing period.
- [Read current organization resource counts and their plan limits](https://docs.decimal.ai/api-reference/billing/read-current-organization-resource-counts-and-their-plan-limits.md)
- [Get the latest N recorded organization usage months (default 6)](https://docs.decimal.ai/api-reference/billing/get-the-latest-n-recorded-organization-usage-months-default-6.md): Get the latest N recorded organization usage months (default 6).
- [Project current-period usage to end-of-month](https://docs.decimal.ai/api-reference/billing/project-current-period-usage-to-end-of-month.md): Estimate organization usage to month end from elapsed UTC calendar days.
- [Download usage history as CSV (one row per period × dimension)](https://docs.decimal.ai/api-reference/billing/download-usage-history-as-csv-one-row-per-period-×-dimension.md): Organization-wide recorded usage history as CSV, with explicit provenance.
- [List recent Stripe invoices with PDF download links (admin)](https://docs.decimal.ai/api-reference/billing/list-recent-stripe-invoices-with-pdf-download-links-admin.md): List recent Stripe invoices for the current organization.
- [Download a ZIP archive of invoice PDFs + manifest for one year (year-end audit, admin)](https://docs.decimal.ai/api-reference/billing/download-a-zip-archive-of-invoice-pdfs-+-manifest-for-one-year-year-end-audit-admin.md): Bundle one calendar year of Stripe invoice PDFs + a CSV manifest into a single ZIP — one download for a year-end audit.
- [Review an authoritative existing-subscription upgrade before confirming it](https://docs.decimal.ai/api-reference/billing/review-an-authoritative-existing-subscription-upgrade-before-confirming-it.md)
- [Read a saved organization-scoped upgrade review or confirmation receipt](https://docs.decimal.ai/api-reference/billing/read-a-saved-organization-scoped-upgrade-review-or-confirmation-receipt.md)
- [Start a Stripe Checkout session for a plan upgrade](https://docs.decimal.ai/api-reference/billing/start-a-stripe-checkout-session-for-a-plan-upgrade.md): Start a plan change and return the URL to send the browser to.
- [Update the org billing contact email (admin)](https://docs.decimal.ai/api-reference/billing/update-the-org-billing-contact-email-admin.md): Update the billing contact email for the organization.
- [Confirm a completed Stripe Checkout session and sync the plan](https://docs.decimal.ai/api-reference/billing/confirm-a-completed-stripe-checkout-session-and-sync-the-plan.md): Authoritative answer to "did my upgrade land?" for the page the browser returns to after Stripe Checkout.
- [Get a Stripe Customer Portal URL for subscription management](https://docs.decimal.ai/api-reference/billing/get-a-stripe-customer-portal-url-for-subscription-management.md): Get a Stripe Customer Portal URL for subscription management.
- [Handle incoming Stripe webhook events](https://docs.decimal.ai/api-reference/billing/handle-incoming-stripe-webhook-events.md): Handle incoming Stripe webhook events.
- [Resolve skills to install into a project](https://docs.decimal.ai/api-reference/install/resolve-skills-to-install-into-a-project.md): Resolve each reference to a skill version, a rendering and an install name.
- [Resolve public skills to install, without an API key](https://docs.decimal.ai/api-reference/install/resolve-public-skills-to-install-without-an-api-key.md): The anonymous twin of `POST /install/resolve`: public skills only, always the `foreign` variant, at most 20 items per request. A skill that is not public resolves as `not_found`, exactly as a reference that matches nothing.
- [Get the files of one skill rendering](https://docs.decimal.ai/api-reference/install/get-the-files-of-one-skill-rendering.md): The exact files of one rendering of one version: SKILL.md first, then the attachments, each with its sha256, size and mode, as UTF-8 text.
- [Get the files of one public skill rendering, without an API key](https://docs.decimal.ai/api-reference/install/get-the-files-of-one-public-skill-rendering-without-an-api-key.md): The anonymous twin of `GET /install/bundles/{version_id}`: public skills only, the `foreign` variant only. Cached publicly for five minutes.
- [Get a public skill's folder, without an API key](https://docs.decimal.ai/api-reference/install/get-a-public-skills-folder-without-an-api-key.md): A public skill's current rendering under its project-free install name, for a loose copy (`decimalai skills pull`, the Claude plugin). Always the `foreign` variant. When the head version failed its safety scan, the newest version that passed is served and `policy_notes` says so.
- [Get a public skill's SKILL.md as text, without an API key](https://docs.decimal.ai/api-reference/install/get-a-public-skills-skillmd-as-text-without-an-api-key.md): The SKILL.md of `GET /registry/skills/{id_or_slug}/bundle`, byte for byte, as `text/markdown`. `ETag` is `"<body_sha256>-v<N>-r<render_hash[:12]>"`; `X-Decimalai-Install-Name`, `X-Decimalai-Version-Id` and `X-Decimalai-Render-Hash` name what was rendered. Attachments are not included: fetch the bund…
- [Public top verified skills + registry counts (marketing site hero)](https://docs.decimal.ai/api-reference/public/public-top-verified-skills-+-registry-counts-marketing-site-hero.md): Anonymous top-N verified skills by SkillScore, plus registry counts.
- [Workspace-wide activity feed (manifests, regressions, audit, training)](https://docs.decimal.ai/api-reference/changelog/workspace-wide-activity-feed-manifests-regressions-audit-training.md): Return up to `limit` recent events newest-first for the caller's org.
- [List contract violations detected for a trace](https://docs.decimal.ai/api-reference/contract-violations/list-contract-violations-detected-for-a-trace.md): Return all contract violations persisted for this trace.
- [Paginated list of contract violations for an agent](https://docs.decimal.ai/api-reference/contract-violations/paginated-list-of-contract-violations-for-an-agent.md): List violations for an agent within a time window (default last 24h).
- [Aggregate violation counts for an agent dashboard](https://docs.decimal.ai/api-reference/contract-violations/aggregate-violation-counts-for-an-agent-dashboard.md): Total + per-kind breakdown for last 24h and last 7d.
- [Preview what would fire if this agent were in closed-world mode](https://docs.decimal.ai/api-reference/contract-violations/preview-what-would-fire-if-this-agent-were-in-closed-world-mode.md): Run the contract checker in simulation against the last 7d of traces.
- [Workspace-wide LLM cost analytics](https://docs.decimal.ai/api-reference/costs/workspace-wide-llm-cost-analytics.md): Returns totals + by_agent + by_model + by_day rollups.
- [List datasets](https://docs.decimal.ai/api-reference/datasets/list-datasets.md): List datasets, optionally filtered by target agent.
- [Create a dataset](https://docs.decimal.ai/api-reference/datasets/create-a-dataset.md): Create a new dataset.
- [Manifest compatibility buckets for the dataset-create modal](https://docs.decimal.ai/api-reference/datasets/manifest-compatibility-buckets-for-the-dataset-create-modal.md): Keep/repair/replay/drop counts for traces relative to a target manifest.
- [Get a dataset](https://docs.decimal.ai/api-reference/datasets/get-a-dataset.md): Get dataset detail with versions.
- [Build a new dataset version from traces](https://docs.decimal.ai/api-reference/datasets/build-a-new-dataset-version-from-traces.md): Build a new dataset version from traces.
- [Export a dataset version](https://docs.decimal.ai/api-reference/datasets/export-a-dataset-version.md): Export a dataset version as JSONL or Parquet.
- [Get quality statistics for a dataset version](https://docs.decimal.ai/api-reference/datasets/get-quality-statistics-for-a-dataset-version.md): Get quality statistics for a dataset version.
- [Validate a dataset version quality for CI gates](https://docs.decimal.ai/api-reference/datasets/validate-a-dataset-version-quality-for-ci-gates.md): Validate a dataset version quality for CI gates.
- [Compare two dataset versions side-by-side](https://docs.decimal.ai/api-reference/datasets/compare-two-dataset-versions-side-by-side.md): Compare two dataset versions side-by-side.
- [Update the quality review status of a dataset version](https://docs.decimal.ai/api-reference/datasets/update-the-quality-review-status-of-a-dataset-version.md): Update the quality review status of a dataset version.
- [Get all evaluation scores for a trace](https://docs.decimal.ai/api-reference/eval-scores/get-all-evaluation-scores-for-a-trace.md): Get all evaluation scores (quality + compatibility) for a trace.
- [Push external evaluation scores](https://docs.decimal.ai/api-reference/eval-scores/push-external-evaluation-scores.md): Push evaluation scores from an external system (DeepEval, LangSmith, etc.).
- [Get full eval breakdown with provenance](https://docs.decimal.ai/api-reference/eval-scores/get-full-eval-breakdown-with-provenance.md): Get the full eval breakdown for a trace, grouped by source.
- [Compute unified verdict for a trace](https://docs.decimal.ai/api-reference/eval-scores/compute-unified-verdict-for-a-trace.md): Compute and persist the unified verdict for a trace.
- [Batch compute unified verdicts](https://docs.decimal.ai/api-reference/eval-scores/batch-compute-unified-verdicts.md): Batch compute unified verdicts for multiple traces.
- [Download all eval scores for the org as CSV (audit, offline review).](https://docs.decimal.ai/api-reference/eval-scores/download-all-eval-scores-for-the-org-as-csv-audit-offline-review.md): Stream EvalScore rows for the caller's org as CSV.
- [List available evaluator templates with category metadata](https://docs.decimal.ai/api-reference/evaluators/list-available-evaluator-templates-with-category-metadata.md): List available evaluator templates with category metadata.
- [List evaluators configured for an agent (or org-wide defaults)](https://docs.decimal.ai/api-reference/evaluators/list-evaluators-configured-for-an-agent-or-org-wide-defaults.md): List evaluators configured for an agent (or org-wide defaults).
- [Create a new evaluator from a template or custom config](https://docs.decimal.ai/api-reference/evaluators/create-a-new-evaluator-from-a-template-or-custom-config.md): Create a new evaluator from a template or custom config.
- [Register SDK-defined evaluators discovered via @eval decorator](https://docs.decimal.ai/api-reference/evaluators/register-sdk-defined-evaluators-discovered-via-@eval-decorator.md): Register SDK-defined evaluators discovered via @eval decorator.
- [Auto-suggested evaluators based on recent trace patterns](https://docs.decimal.ai/api-reference/evaluators/auto-suggested-evaluators-based-on-recent-trace-patterns.md): Returns prebuilt evaluators the workspace would benefit from, based on heuristic analysis of recent trace patterns.
- [Cross-agent coverage matrix](https://docs.decimal.ai/api-reference/evaluators/cross-agent-coverage-matrix.md): Cross-agent coverage matrix.
- [Delete an evaluator](https://docs.decimal.ai/api-reference/evaluators/delete-an-evaluator.md): Delete an evaluator.
- [Update an evaluator's configuration.](https://docs.decimal.ai/api-reference/evaluators/update-an-evaluators-configuration.md): Update an evaluator's configuration.
- [List prompt-template versions for an evaluator](https://docs.decimal.ai/api-reference/evaluators/list-prompt-template-versions-for-an-evaluator.md): Return the version history of an evaluator's prompt_template.
- [Per-day pass rate + mean score for an evaluator over a lookback window](https://docs.decimal.ai/api-reference/evaluators/per-day-pass-rate-+-mean-score-for-an-evaluator-over-a-lookback-window.md): Time-series of `(date, pass_rate, mean_score, sample_count)` for an evaluator.
- [Get staleness status for all evaluators of an agent](https://docs.decimal.ai/api-reference/evaluators/get-staleness-status-for-all-evaluators-of-an-agent.md): Get staleness status for all evaluators of an agent.
- [Trigger a staleness scan for one agent or all agents in the org](https://docs.decimal.ai/api-reference/evaluators/trigger-a-staleness-scan-for-one-agent-or-all-agents-in-the-org.md): Trigger a staleness scan for one agent or all agents in the org.
- [Mark an evaluator as valid against the current manifest](https://docs.decimal.ai/api-reference/evaluators/mark-an-evaluator-as-valid-against-the-current-manifest.md): Mark an evaluator as valid against the current manifest.
- [List the caller's org's evergreen policies](https://docs.decimal.ai/api-reference/evergreen/list-the-callers-orgs-evergreen-policies.md): List the caller's org's evergreen policies.
- [Create an evergreen policy in one of the caller's projects](https://docs.decimal.ai/api-reference/evergreen/create-an-evergreen-policy-in-one-of-the-callers-projects.md): Create an evergreen policy (bound to a project the caller owns).
- [List evergreen tasks, optionally filtered by policy](https://docs.decimal.ai/api-reference/evergreen/list-evergreen-tasks-optionally-filtered-by-policy.md): List the caller's org's evergreen tasks, optionally filtered by policy.
- [Mark a trace as an evergreen task for continuous regression testing](https://docs.decimal.ai/api-reference/evergreen/mark-a-trace-as-an-evergreen-task-for-continuous-regression-testing.md): Mark a trace as an evergreen task for continuous regression testing.
- [Get regression reports showing score trends across manifest versions](https://docs.decimal.ai/api-reference/evergreen/get-regression-reports-showing-score-trends-across-manifest-versions.md): Get regression reports showing score trends across manifest versions.
- [Import traces from a JSONL upload (deprecated path — use /traces/import)](https://docs.decimal.ai/api-reference/import/import-traces-from-a-jsonl-upload-deprecated-path-—-use-tracesimport.md): Upload and parse a JSONL file.
- [Bulk-import historical traces (deprecated path — use /traces/import-bulk)](https://docs.decimal.ai/api-reference/import/bulk-import-historical-traces-deprecated-path-—-use-tracesimport-bulk.md): Bulk-import historical traces — useful for migrating from another observability tool or seeding the dashboard from a backup.
- [Import a list of LangSmith Run objects (verbatim export format)](https://docs.decimal.ai/api-reference/import/import-a-list-of-langsmith-run-objects-verbatim-export-format.md): Accept a bare list of LangSmith `Run` exports — no wrapping required.
- [Import traces from a JSONL upload](https://docs.decimal.ai/api-reference/import/import-traces-from-a-jsonl-upload.md): Upload and parse a JSONL file.
- [Bulk-import historical traces](https://docs.decimal.ai/api-reference/import/bulk-import-historical-traces.md): Bulk-import historical traces — useful for migrating from another observability tool or seeding the dashboard from a backup.
- [List manifests](https://docs.decimal.ai/api-reference/manifests/list-manifests.md): List manifests in timeline order.
- [Register a manifest](https://docs.decimal.ai/api-reference/manifests/register-a-manifest.md): Register a new manifest version.
- [Get a manifest](https://docs.decimal.ai/api-reference/manifests/get-a-manifest.md): Get a manifest by ID with full component list.
- [Compute a diff between this manifest and another (or its parent)](https://docs.decimal.ai/api-reference/manifests/compute-a-diff-between-this-manifest-and-another-or-its-parent.md): Compute a diff between this manifest and another (or its parent).
- [Suggest evaluators based on what this manifest declares](https://docs.decimal.ai/api-reference/manifests/suggest-evaluators-based-on-what-this-manifest-declares.md): B.1 — derive evaluator suggestions from the manifest's declared contract.
- [Get compatibility reports for a manifest](https://docs.decimal.ai/api-reference/manifests/get-compatibility-reports-for-a-manifest.md): Get compatibility reports for a manifest.
- [Drill down into per-episode compatibility verdicts](https://docs.decimal.ai/api-reference/manifests/drill-down-into-per-episode-compatibility-verdicts.md): Drill down into per-episode compatibility verdicts.
- [Run a fresh per-episode compatibility analysis](https://docs.decimal.ai/api-reference/manifests/run-a-fresh-per-episode-compatibility-analysis.md): Run a fresh per-episode compatibility analysis.
- [Export an agent's manifest timeline as CSV](https://docs.decimal.ai/api-reference/manifests/export-an-agents-manifest-timeline-as-csv.md): Export an agent's manifest version timeline as a CSV file.
- [Manifest timeline for an agent](https://docs.decimal.ai/api-reference/manifests/manifest-timeline-for-an-agent.md): Get the manifest timeline for an agent.
- [Datasets linked to a manifest](https://docs.decimal.ai/api-reference/manifests/datasets-linked-to-a-manifest.md): Get datasets and their versions linked to a specific manifest.
- [Get policy presets](https://docs.decimal.ai/api-reference/manifests/get-policy-presets.md): Get available policy presets (strict / default / permissive).
- [Create a new compatibility policy](https://docs.decimal.ai/api-reference/manifests/create-a-new-compatibility-policy.md): Create a new compatibility policy.
- [Get the active policy for an agent or project](https://docs.decimal.ai/api-reference/manifests/get-the-active-policy-for-an-agent-or-project.md): Get the active policy for an agent or project.
- [Update a policy's rules or preset.](https://docs.decimal.ai/api-reference/manifests/update-a-policys-rules-or-preset.md): Update a policy's rules or preset.
- [Apply a compatibility policy to a manifest diff](https://docs.decimal.ai/api-reference/manifests/apply-a-compatibility-policy-to-a-manifest-diff.md): Apply a compatibility policy to a manifest diff.
- [Preview the impact of a policy on traces](https://docs.decimal.ai/api-reference/manifests/preview-the-impact-of-a-policy-on-traces.md): Preview how many traces would be affected by each action bucket.
- [Roll back to a prior manifest — one-click oncall mitigation](https://docs.decimal.ai/api-reference/manifests/roll-back-to-a-prior-manifest-—-one-click-oncall-mitigation.md): One-click rollback to a prior manifest version.
- [Get current organization details](https://docs.decimal.ai/api-reference/organization/get-current-organization-details.md): Get current organization details.
- [List all org members](https://docs.decimal.ai/api-reference/organization/list-all-org-members.md): List all org members.
- [List pending invitations for the org](https://docs.decimal.ai/api-reference/organization/list-pending-invitations-for-the-org.md): List invitations for the caller's org.
- [Invite a new member to the org (canonical REST plural)](https://docs.decimal.ai/api-reference/organization/invite-a-new-member-to-the-org-canonical-rest-plural.md): Invite a new member to the org.
- [Invite a new member to the org](https://docs.decimal.ai/api-reference/organization/invite-a-new-member-to-the-org.md): Invite a new member to the org.
- [Bulk-invite up to 100 members in one call](https://docs.decimal.ai/api-reference/organization/bulk-invite-up-to-100-members-in-one-call.md): Bulk-invite multiple members in one call.
- [Revoke a pending invitation and release its reserved seat](https://docs.decimal.ai/api-reference/organization/revoke-a-pending-invitation-and-release-its-reserved-seat.md): Revoke a pending invitation, freeing the seat it reserved.
- [Accept an invitation](https://docs.decimal.ai/api-reference/organization/accept-an-invitation.md): Accept an invitation.
- [Remove a member from the org](https://docs.decimal.ai/api-reference/organization/remove-a-member-from-the-org.md): Remove a member from the org.
- [Record signup attribution (referral source + landing referrer)](https://docs.decimal.ai/api-reference/organization/record-signup-attribution-referral-source-+-landing-referrer.md): Record signup attribution for the org — how it first heard of the product.
- [Get the caller's email preferences](https://docs.decimal.ai/api-reference/email/get-the-callers-email-preferences.md)
- [Update the caller's email preferences](https://docs.decimal.ai/api-reference/email/update-the-callers-email-preferences.md): Returns the SAVED state, re-read from the database.
- [Get recent traces with LLM call messages for playground testing](https://docs.decimal.ai/api-reference/playground/get-recent-traces-with-llm-call-messages-for-playground-testing.md): Get recent traces with LLM call messages for playground testing.
- [Execute a modified LLM call using the user's stored credentials](https://docs.decimal.ai/api-reference/playground/execute-a-modified-llm-call-using-the-users-stored-credentials.md): Execute a modified LLM call using the user's stored credentials.
- [Opt-in pairwise preference verdict (runs on the user's BYOK key)](https://docs.decimal.ai/api-reference/playground/opt-in-pairwise-preference-verdict-runs-on-the-users-byok-key.md): Relative pairwise preference of ``candidate`` vs ``baseline`` for the same input.
- [List the caller's org's projects](https://docs.decimal.ai/api-reference/projects/list-the-callers-orgs-projects.md): List the caller's org's projects.
- [Create a new project in the caller's org](https://docs.decimal.ai/api-reference/projects/create-a-new-project-in-the-callers-org.md): Create a new project in the caller's org.
- [Get a project by ID](https://docs.decimal.ai/api-reference/projects/get-a-project-by-id.md): Get a project by ID (caller's org only).
- [Update a project](https://docs.decimal.ai/api-reference/projects/update-a-project.md): Update a project (caller's org only).
- [List regression checks for an agent, most recent first](https://docs.decimal.ai/api-reference/regression/list-regression-checks-for-an-agent-most-recent-first.md): List regression checks for an agent, most recent first.
- [Run a regression check for a candidate manifest against the baseline](https://docs.decimal.ai/api-reference/regression/run-a-regression-check-for-a-candidate-manifest-against-the-baseline.md): Run a regression check for a candidate manifest against the baseline.
- [Fetch a regression check by ID. Used by the frontend detail page](https://docs.decimal.ai/api-reference/regression/fetch-a-regression-check-by-id-used-by-the-frontend-detail-page.md): Fetch a regression check by ID. Used by the frontend detail page.
- [Set the engineer's human_decision on a regression check](https://docs.decimal.ai/api-reference/regression/set-the-engineers-human_decision-on-a-regression-check.md): Annotate a regression check with the engineer's decision.
- [Behavioral call-replay for a check's model change (defaults to mock — no token spend)](https://docs.decimal.ai/api-reference/regression/behavioral-call-replay-for-a-checks-model-change-defaults-to-mock-—-no-token-spend.md): Re-issue a representative recorded model call per affected trace against the candidate model and diff vs the recorded answer.
- [Get Regression Timeline](https://docs.decimal.ai/api-reference/regression/get-regression-timeline.md): Return the per-manifest metric time series + regression detection.
- [Get Ci Setup Status](https://docs.decimal.ai/api-reference/regression/get-ci-setup-status.md): Return whether CI for regression checks is wired up for this agent.
- [List Regression Alerts](https://docs.decimal.ai/api-reference/regression/list-regression-alerts.md): List alerts for an agent, optionally filtered by status.
- [Create Regression Alert](https://docs.decimal.ai/api-reference/regression/create-regression-alert.md): Manually flag a manifest as regressed.
- [Aggregate regression-alert stats: counts, MTTR, by-agent / by-severity](https://docs.decimal.ai/api-reference/regression/aggregate-regression-alert-stats:-counts-mttr-by-agent-by-severity.md): Audit your regression alerts in one call instead of paginating `/regression-alerts` and aggregating client-side. Returns total and open counts, mean time to resolution, and breakdowns by agent and by severity, over an optional `since` window.
- [Active alerts grouped by agent — for the on-call landing surface](https://docs.decimal.ai/api-reference/regression/active-alerts-grouped-by-agent-—-for-the-on-call-landing-surface.md): One call that answers 'which agents need attention right now?', without paginating through `/regression-alerts` per-agent. Returns agents with at least one open (active OR acknowledged) alert, sorted by most-recent alert first. Suited to an on-call or incident landing page.
- [Get Regression Alert](https://docs.decimal.ai/api-reference/regression/get-regression-alert.md): Fetch a single alert by ID.
- [Acknowledge Regression Alert](https://docs.decimal.ai/api-reference/regression/acknowledge-regression-alert.md): Mark an alert as acknowledged (engineer saw it but hasn't fixed yet).
- [Resolve Regression Alert](https://docs.decimal.ai/api-reference/regression/resolve-regression-alert.md): Mark an alert as resolved (regression no longer applies).
- [Get Rollback Preview](https://docs.decimal.ai/api-reference/regression/get-rollback-preview.md): Generate a rollback preview for an alert.
- [Preview repairs for a manifest transition](https://docs.decimal.ai/api-reference/repair/preview-repairs-for-a-manifest-transition.md): Preview deterministic transformations for two versions of the same agent.
- [Apply repairs to all eligible episodes](https://docs.decimal.ai/api-reference/repair/apply-repairs-to-all-eligible-episodes.md): Apply deterministic transformations and retain a durable batch receipt.
- [List durable repair receipts for an exact version pair](https://docs.decimal.ai/api-reference/repair/list-durable-repair-receipts-for-an-exact-version-pair.md)
- [Get repair batch status and results](https://docs.decimal.ai/api-reference/repair/get-repair-batch-status-and-results.md): Get repair batch status and results.
- [Apply only user-approved repair rules](https://docs.decimal.ai/api-reference/repair/apply-only-user-approved-repair-rules.md): Apply only user-approved repair rules.
- [List replay batches](https://docs.decimal.ai/api-reference/replay/list-replay-batches.md): List replay batches in the workspace, newest first.
- [Create a replay batch](https://docs.decimal.ai/api-reference/replay/create-a-replay-batch.md): Create a replay batch.
- [Get a replay batch](https://docs.decimal.ai/api-reference/replay/get-a-replay-batch.md): Get a replay batch with full task breakdown.
- [Get a single replay task with its input for execution](https://docs.decimal.ai/api-reference/replay/get-a-single-replay-task-with-its-input-for-execution.md): Get a single replay task with its input for execution.
- [Submit a replay task result](https://docs.decimal.ai/api-reference/replay/submit-a-replay-task-result.md): Submit the result of a replay task.
- [Export replay prompts](https://docs.decimal.ai/api-reference/replay/export-replay-prompts.md): Export traces needing replay as a downloadable file.
- [Export multi-turn sessions that need replay](https://docs.decimal.ai/api-reference/replay/export-multi-turn-sessions-that-need-replay.md): Export multi-turn sessions that need replay.
- [Link a replayed trace to its original](https://docs.decimal.ai/api-reference/replay/link-a-replayed-trace-to-its-original.md): Link a replayed trace to its original.
- [Export DPO preference pairs from a completed replay batch](https://docs.decimal.ai/api-reference/replay/export-dpo-preference-pairs-from-a-completed-replay-batch.md): Export DPO preference pairs from a completed replay batch.
- [Get platform configuration and statistics](https://docs.decimal.ai/api-reference/settings/get-platform-configuration-and-statistics.md): Get platform configuration and statistics.
- [List all API keys (prefix and label only — no raw keys)](https://docs.decimal.ai/api-reference/settings/list-all-api-keys-prefix-and-label-only-—-no-raw-keys.md): List this org's API keys (prefix and label only — no raw keys).
- [Create a new API key](https://docs.decimal.ai/api-reference/settings/create-a-new-api-key.md): Create a new API key.
- [Revoke an API key. Only global-scoped keys can revoke keys](https://docs.decimal.ai/api-reference/settings/revoke-an-api-key-only-global-scoped-keys-can-revoke-keys.md): Revoke an API key. Only global-scoped keys can revoke keys.
- [List all API keys (canonical REST path)](https://docs.decimal.ai/api-reference/api-keys/list-all-api-keys-canonical-rest-path.md): List this org's API keys (prefix and label only — no raw keys).
- [Create a new API key (canonical REST path)](https://docs.decimal.ai/api-reference/api-keys/create-a-new-api-key-canonical-rest-path.md): Create a new API key.
- [Revoke an API key (canonical REST path)](https://docs.decimal.ai/api-reference/api-keys/revoke-an-api-key-canonical-rest-path.md): Revoke an API key. Only global-scoped keys can revoke keys.
- [Generate an AI-powered improvement suggestion for a skill](https://docs.decimal.ai/api-reference/skills/generate-an-ai-powered-improvement-suggestion-for-a-skill.md): Generate an AI-powered improvement suggestion for a skill.
- [Apply a suggested improvement by creating a new skill version](https://docs.decimal.ai/api-reference/skills/apply-a-suggested-improvement-by-creating-a-new-skill-version.md): Apply a suggested improvement by creating a new skill version.
- [List past AI-generated suggestion versions for a skill](https://docs.decimal.ai/api-reference/skills/list-past-ai-generated-suggestion-versions-for-a-skill.md): List past AI-generated suggestion versions for a skill.
- [List skills](https://docs.decimal.ai/api-reference/skills/list-skills.md): List all skills for the organization.
- [Create a skill](https://docs.decimal.ai/api-reference/skills/create-a-skill.md): Create a new skill with its first version.
- [Reconcile a batch of local skills with the platform](https://docs.decimal.ai/api-reference/skills/reconcile-a-batch-of-local-skills-with-the-platform.md): One endpoint, two consumers:
- [Per-install skill sync-divergence state](https://docs.decimal.ai/api-reference/skills/per-install-skill-sync-divergence-state.md): Per-install divergence pills for the org's skills.
- [Report an install's local skill hashes (no push)](https://docs.decimal.ai/api-reference/skills/report-an-installs-local-skill-hashes-no-push.md): Refresh an install's locally-observed hashes without pushing anything.
- [Get the skill menu (Free tier)](https://docs.decimal.ai/api-reference/skills/get-the-skill-menu-free-tier.md): Get the full skill menu for prompt injection (Free tier).
- [Smart-route a query to the best skill](https://docs.decimal.ai/api-reference/skills/smart-route-a-query-to-the-best-skill.md): Smart routing: semantic search + performance re-ranking.
- [Export org skills with full content](https://docs.decimal.ai/api-reference/skills/export-org-skills-with-full-content.md): Export org skills with full content + attachments for disk write.
- [Getting-started signals: acquired a skill, made it available, seen it fire](https://docs.decimal.ai/api-reference/skills/getting-started-signals:-acquired-a-skill-made-it-available-seen-it-fire.md): Has this org taken a skill, got it into an agent, and seen it fire?
- [List skills this org has linked with Use (not forked)](https://docs.decimal.ai/api-reference/skills/list-skills-this-org-has-linked-with-use-not-forked.md): The org's ``Use`` pointers — skills linked live from the registry.
- [Get content hashes for all org skills](https://docs.decimal.ai/api-reference/skills/get-content-hashes-for-all-org-skills.md): Get content hashes for all org skills.
- [Get a skill by name](https://docs.decimal.ai/api-reference/skills/get-a-skill-by-name.md): Get skill metadata, ownership, and analytics.
- [Existence probe with get_skill's exact access rules](https://docs.decimal.ai/api-reference/skills/existence-probe-with-get_skills-exact-access-rules.md): 200 + {"exists": bool} — never 404.
- [Get the body markdown of a skill for prompt injection / load_skill](https://docs.decimal.ai/api-reference/skills/get-the-body-markdown-of-a-skill-for-prompt-injection-load_skill.md): Get the body markdown of a skill — the serve path behind ``load_skill``.
- [Opt-in: generate platform-authored starter test cases for this skill](https://docs.decimal.ai/api-reference/skills/opt-in:-generate-platform-authored-starter-test-cases-for-this-skill.md): Explicit-opt-in entry point for platform test generation.
- [List the benchmark test cases on this skill's latest version](https://docs.decimal.ai/api-reference/skills/list-the-benchmark-test-cases-on-this-skills-latest-version.md): List the benchmark test cases on a skill's latest version.
- [Author a single benchmark test case in the browser](https://docs.decimal.ai/api-reference/skills/author-a-single-benchmark-test-case-in-the-browser.md): Add a benchmark test case to a skill's latest version.
- [Edit a single benchmark test case](https://docs.decimal.ai/api-reference/skills/edit-a-single-benchmark-test-case.md): Replace a benchmark test case on a skill's latest version.
- [Delete a single benchmark test case](https://docs.decimal.ai/api-reference/skills/delete-a-single-benchmark-test-case.md): Delete a benchmark test case from a skill's latest version.
- [Run the A/B benchmark suite for this skill's latest version](https://docs.decimal.ai/api-reference/skills/run-the-ab-benchmark-suite-for-this-skills-latest-version.md): Run this skill's benchmark suite now.
- [Import a locally produced skillevaluation results.json (unverified)](https://docs.decimal.ai/api-reference/skills/import-a-locally-produced-skillevaluation-resultsjson-unverified.md): Open-runner funnel: persist a local `skillevaluation run` result.
- [List recent benchmark runs for this skill](https://docs.decimal.ai/api-reference/skills/list-recent-benchmark-runs-for-this-skill.md): Returns the N most-recent SkillTestRun rows + their per-case results.
- [One benchmark run, fully serialized (older-run lazy-load)](https://docs.decimal.ai/api-reference/skills/one-benchmark-run-fully-serialized-older-run-lazy-load.md): Full per-case detail for ONE benchmark run.
- [Unified Skill Health card payload](https://docs.decimal.ai/api-reference/skills/unified-skill-health-card-payload.md): One payload that drives the SkillHealthHeader card.
- [List drafted suggested edits for this skill](https://docs.decimal.ai/api-reference/skills/list-drafted-suggested-edits-for-this-skill.md): List the suggested edits proposed for a skill.
- [Accept a suggested edit → new SkillVersion + regression tests + benchmark](https://docs.decimal.ai/api-reference/skills/accept-a-suggested-edit-→-new-skillversion-+-regression-tests-+-benchmark.md): Close the loop: apply the patch, create v(N+1), generate regression tests from supporting traces, kick off a benchmark run.
- [Reject a suggested edit](https://docs.decimal.ai/api-reference/skills/reject-a-suggested-edit.md): Reject a draft suggested edit so it is no longer proposed.
- [Per-skill Live Traces summary — effectiveness distribution + discoverability gap](https://docs.decimal.ai/api-reference/skills/per-skill-live-traces-summary-—-effectiveness-distribution-+-discoverability-gap.md): Drives the Live Traces tab on /skills/<name>.
- [List all open struggle Patterns for this skill](https://docs.decimal.ai/api-reference/skills/list-all-open-struggle-patterns-for-this-skill.md): Drives the "View all N patterns" drilldown.
- [Test whether a hypothetical user input would activate this skill, and preview the rendered body](https://docs.decimal.ai/api-reference/skills/test-whether-a-hypothetical-user-input-would-activate-this-skill-and-preview-the-rendered-body.md): Standalone test surface for a skill.
- [List versions of a skill](https://docs.decimal.ai/api-reference/skills/list-versions-of-a-skill.md): List all versions of a skill, newest first.
- [Per-version usage breakdown](https://docs.decimal.ai/api-reference/skills/per-version-usage-breakdown.md): Per-version usage stats: subscription_count + activation_count + agent_count per version. Lets the registry Versions UI render a "which version is production-active" column without sending the full subscription list to the client.
- [Get a specific version's full content.](https://docs.decimal.ai/api-reference/skills/get-a-specific-versions-full-content.md): Get a specific version's full content.
- [Compute a unified diff between two skill versions](https://docs.decimal.ai/api-reference/skills/compute-a-unified-diff-between-two-skill-versions.md): Compute a unified diff between two skill versions.
- [Update a skill](https://docs.decimal.ai/api-reference/skills/update-a-skill.md): Update a skill. Creates a new version if body content changes.
- [Delete a skill (soft-delete)](https://docs.decimal.ai/api-reference/skills/delete-a-skill-soft-delete.md): Soft-delete a skill (sets `is_active=False`).
- [Re-ablate this public skill's latest version now (bounded, on-demand)](https://docs.decimal.ai/api-reference/skills/re-ablate-this-public-skills-latest-version-now-bounded-on-demand.md): Manual on-demand re-ablation.
- [Rename a skill](https://docs.decimal.ai/api-reference/skills/rename-a-skill.md): Rename a skill. The new name must be unique within the requester's org.
- [Offer a skill only to the agents that use it](https://docs.decimal.ai/api-reference/skills/offer-a-skill-only-to-the-agents-that-use-it.md): Stop offering a skill to every agent; keep it on the agents that use it.
- [Per-skill performance metrics with baseline comparison](https://docs.decimal.ai/api-reference/skills/per-skill-performance-metrics-with-baseline-comparison.md): Per-skill performance metrics with baseline comparison.
- [Use and benchmark lift for a set of skills](https://docs.decimal.ai/api-reference/skills/use-and-benchmark-lift-for-a-set-of-skills.md): Runs that loaded each skill in this workspace, the agents they came from, and the skill's benchmark lift — one call for a whole list of skills.
- [Compare two versions of a skill](https://docs.decimal.ai/api-reference/skills/compare-two-versions-of-a-skill.md): Compare two versions of a skill.
- [Rank skills by effectiveness](https://docs.decimal.ai/api-reference/skills/rank-skills-by-effectiveness.md): Rank skills by effectiveness.
- [Daily skill activation timeline for an agent](https://docs.decimal.ai/api-reference/skills/daily-skill-activation-timeline-for-an-agent.md): Daily skill activation timeline for an agent.
- [Per-skill offered-vs-activated rollup](https://docs.decimal.ai/api-reference/skills/per-skill-offered-vs-activated-rollup.md): Rollup the org's routing decisions that offered `skill_name` and measure how often a downstream trace actually activated it.
- [Get current routing configuration and readiness status](https://docs.decimal.ai/api-reference/skills/get-current-routing-configuration-and-readiness-status.md): Get current routing configuration and readiness status.
- [Offered-vs-activated join for a single routing decision](https://docs.decimal.ai/api-reference/skills/offered-vs-activated-join-for-a-single-routing-decision.md): Resolve the offered-vs-activated answer for a single router call.
- [Deprecated alias of /assign (subscribe → assign, Use/Fork consolidation)](https://docs.decimal.ai/api-reference/skills/deprecated-alias-of-assign-subscribe-→-assign-usefork-consolidation.md): Subscribe an agent to a skill.
- [Deprecated alias of DELETE /assign (subscribe → assign, Use/Fork consolidation)](https://docs.decimal.ai/api-reference/skills/deprecated-alias-of-delete-assign-subscribe-→-assign-usefork-consolidation.md): Unsubscribe an agent from a skill.
- [Assign a skill to an agent (an agent-scope Use)](https://docs.decimal.ai/api-reference/skills/assign-a-skill-to-an-agent-an-agent-scope-use.md): Subscribe an agent to a skill.
- [Unassign a skill from an agent (removes the agent-scope Use)](https://docs.decimal.ai/api-reference/skills/unassign-a-skill-from-an-agent-removes-the-agent-scope-use.md): Unsubscribe an agent from a skill.
- [List all agents subscribed to a skill (canonical REST plural)](https://docs.decimal.ai/api-reference/skills/list-all-agents-subscribed-to-a-skill-canonical-rest-plural.md): List all agents subscribed to a skill.
- [List all agents subscribed to a skill](https://docs.decimal.ai/api-reference/skills/list-all-agents-subscribed-to-a-skill.md): List all agents subscribed to a skill.
- [Impact analysis: show how many agents would be affected by a skill change](https://docs.decimal.ai/api-reference/skills/impact-analysis:-show-how-many-agents-would-be-affected-by-a-skill-change.md): Impact analysis: show how many agents would be affected by a skill change.
- [Export skill analytics as CSV for stakeholder reports](https://docs.decimal.ai/api-reference/skills/export-skill-analytics-as-csv-for-stakeholder-reports.md): Export a skill's headline analytics as CSV.
- [Transfer skill ownership to a different workspace](https://docs.decimal.ai/api-reference/skills/transfer-skill-ownership-to-a-different-workspace.md): Transfer skill ownership to a different workspace.
- [Fork a skill — create an independent copy in the caller's workspace](https://docs.decimal.ai/api-reference/skills/fork-a-skill-—-create-an-independent-copy-in-the-callers-workspace.md): Fork a skill — create an independent copy in the caller's workspace.
- [List all sharing grants for a skill](https://docs.decimal.ai/api-reference/skills/list-all-sharing-grants-for-a-skill.md): List all sharing grants for a skill.
- [Add a sharing grant to a skill](https://docs.decimal.ai/api-reference/skills/add-a-sharing-grant-to-a-skill.md): Add a sharing grant to a skill.
- [Remove a sharing grant from a skill](https://docs.decimal.ai/api-reference/skills/remove-a-sharing-grant-from-a-skill.md): Remove a sharing grant from a skill.
- [Publish a skill to the public registry](https://docs.decimal.ai/api-reference/skills/publish-a-skill-to-the-public-registry.md): Publish a skill to the public registry.
- [Remove a skill from the public registry](https://docs.decimal.ai/api-reference/skills/remove-a-skill-from-the-public-registry.md): Remove a skill from the public registry.
- [Failure-first harvest: run a skill's eval cases on the BASE model to see if the base already passes](https://docs.decimal.ai/api-reference/skills/failure-first-harvest:-run-a-skills-eval-cases-on-the-base-model-to-see-if-the-base-already-passes.md): Answer "should this skill exist?" before benchmarking/publishing it.
- [Check if the forked skill has upstream updates available](https://docs.decimal.ai/api-reference/skills/check-if-the-forked-skill-has-upstream-updates-available.md): Check if the forked skill has upstream updates available.
- [Merge upstream changes into a forked skill](https://docs.decimal.ai/api-reference/skills/merge-upstream-changes-into-a-forked-skill.md): Merge upstream changes into a forked skill.
- [Re-run SkillSafety checks on a skill (free Tier-1; optional metered deep review)](https://docs.decimal.ai/api-reference/skills/re-run-skillsafety-checks-on-a-skill-free-tier-1;-optional-metered-deep-review.md): Owner-triggered SkillSafety re-check.
- [Import a skill from a SKILL.md file content](https://docs.decimal.ai/api-reference/skills/import-a-skill-from-a-skillmd-file-content.md): Import a skill from a SKILL.md file content.
- [Export a skill as a standard SKILL.md file](https://docs.decimal.ai/api-reference/skills/export-a-skill-as-a-standard-skillmd-file.md): Export a skill as a standard SKILL.md file.
- [List all attachments for a skill](https://docs.decimal.ai/api-reference/skill-attachments/list-all-attachments-for-a-skill.md): List all attachments for a skill.
- [Upload a single attachment to a skill](https://docs.decimal.ai/api-reference/skill-attachments/upload-a-single-attachment-to-a-skill.md): Upload a single attachment to a skill.
- [Get a single attachment with its full content](https://docs.decimal.ai/api-reference/skill-attachments/get-a-single-attachment-with-its-full-content.md): Get a single attachment with its full content.
- [Delete a single attachment](https://docs.decimal.ai/api-reference/skill-attachments/delete-a-single-attachment.md): Delete a single attachment.
- [Get an attachment by its relative file path](https://docs.decimal.ai/api-reference/skill-attachments/get-an-attachment-by-its-relative-file-path.md): Get an attachment by its relative file path.
- [Overwrite an existing attachment by path (stable attachment_id)](https://docs.decimal.ai/api-reference/skill-attachments/overwrite-an-existing-attachment-by-path-stable-attachment_id.md): Overwrite an attachment's content in place — keeps `attachment_id` stable.
- [Upload multiple attachments at once](https://docs.decimal.ai/api-reference/skill-attachments/upload-multiple-attachments-at-once.md): Upload multiple attachments at once.
- [Ingest a telemetry event](https://docs.decimal.ai/api-reference/telemetry/ingest-a-telemetry-event.md): Ingest a client-side telemetry event from the dashboard.
- [Capabilities](https://docs.decimal.ai/api-reference/evidence/capabilities.md)
- [Collect](https://docs.decimal.ai/api-reference/evidence/collect.md)
- [Stream](https://docs.decimal.ai/api-reference/evidence/stream.md)
- [Health](https://docs.decimal.ai/api-reference/evidence/health.md)
- [Entry](https://docs.decimal.ai/api-reference/evidence/entry.md)
- [Run](https://docs.decimal.ai/api-reference/evidence/run.md)
- [Persist Proof](https://docs.decimal.ai/api-reference/evidence/persist-proof.md)
- [Proof](https://docs.decimal.ai/api-reference/evidence/proof.md)
- [Batch Usage](https://docs.decimal.ai/api-reference/traces/batch-usage.md): Read owned immutable usage identities and receipt publication; no transcript or model work.
- [Batch Quality](https://docs.decimal.ai/api-reference/traces/batch-quality.md): Read up to 100 owned results without grading, publishing, or model calls.
- [Pending Quality](https://docs.decimal.ai/api-reference/traces/pending-quality.md)
- [Get Quality](https://docs.decimal.ai/api-reference/traces/get-quality.md)
- [List traces](https://docs.decimal.ai/api-reference/traces/list-traces.md): List traces for the project (paginated).
- [Ingest a trace](https://docs.decimal.ai/api-reference/traces/ingest-a-trace.md): Ingest a single trace from the SDK.
- [Ingest a batch of traces](https://docs.decimal.ai/api-reference/traces/ingest-a-batch-of-traces.md): Ingest a batch of traces in a single request.
- [Group traces by agent or session with per-group rollups](https://docs.decimal.ai/api-reference/traces/group-traces-by-agent-or-session-with-per-group-rollups.md): Collapse the trace list into groups (by agent or session) with summary metrics per group — volume, error rate, eval pass/fail + avg score, avg duration, last activity. Honours the same filters as the list endpoint so a group's numbers match what `GET /traces?agent_name=<key>` would drill into.
- [Aggregate stats across traces](https://docs.decimal.ai/api-reference/traces/aggregate-stats-across-traces.md): Aggregate statistics for traces matching the given filters.
- [Eval rollup stats](https://docs.decimal.ai/api-reference/traces/eval-rollup-stats.md): Aggregate evaluation statistics for the eval dashboard.
- [Get a trace](https://docs.decimal.ai/api-reference/traces/get-a-trace.md): Get a single trace with its full span tree and LLM calls.
- [Export a trace as a flat JSON document](https://docs.decimal.ai/api-reference/traces/export-a-trace-as-a-flat-json-document.md): Return a self-contained JSON snapshot of the trace plus all spans + llm_calls.
- [List all child traces of a parent trace (multi-agent orchestration)](https://docs.decimal.ai/api-reference/traces/list-all-child-traces-of-a-parent-trace-multi-agent-orchestration.md): List all child traces of a parent trace (multi-agent orchestration).
- [Get the Skill Rater report for a trace](https://docs.decimal.ai/api-reference/traces/get-the-skill-rater-report-for-a-trace.md): Return the Skill Rater report for a trace, or 404 if not yet rated.
- [Manually override a trace's status](https://docs.decimal.ai/api-reference/traces/manually-override-a-traces-status.md): Manually override a trace's status.
- [Run evaluators on a trace](https://docs.decimal.ai/api-reference/traces/run-evaluators-on-a-trace.md): Run evaluation on a trace.
- [Set a manual compatibility override for a trace](https://docs.decimal.ai/api-reference/traces/set-a-manual-compatibility-override-for-a-trace.md): Set a manual compatibility override for a trace.
- [Get the public skill AI rating prompt and provenance format](https://docs.decimal.ai/api-reference/traces/get-the-public-skill-ai-rating-prompt-and-provenance-format.md)
- [Get this trace's witnessed skill snapshots and AI rating prompt](https://docs.decimal.ai/api-reference/traces/get-this-traces-witnessed-skill-snapshots-and-ai-rating-prompt.md)
- [Submit AI feedback for public skills witnessed in your trace](https://docs.decimal.ai/api-reference/traces/submit-ai-feedback-for-public-skills-witnessed-in-your-trace.md): Store externally reported AI feedback; no provider call or charge.
- [Force-run the Skill Rater on a single trace (on-demand)](https://docs.decimal.ai/api-reference/traces/force-run-the-skill-rater-on-a-single-trace-on-demand.md): Run the Skill Rater on one trace, synchronously.
- [List available fine-tuning providers with configuration status](https://docs.decimal.ai/api-reference/training/list-available-fine-tuning-providers-with-configuration-status.md): List available fine-tuning providers with configuration status.
- [Get configured provider credentials (keys masked)](https://docs.decimal.ai/api-reference/training/get-configured-provider-credentials-keys-masked.md): Get configured provider credentials (keys masked).
- [Store or update provider credentials](https://docs.decimal.ai/api-reference/training/store-or-update-provider-credentials.md): Store or update provider credentials.
- [Remove stored credentials for a provider](https://docs.decimal.ai/api-reference/training/remove-stored-credentials-for-a-provider.md): Remove stored credentials for a provider.
- [List training jobs for the org](https://docs.decimal.ai/api-reference/training/list-training-jobs-for-the-org.md): List training jobs for the org.
- [Launch a fine-tuning job](https://docs.decimal.ai/api-reference/training/launch-a-fine-tuning-job.md): Launch a fine-tuning job.
- [Get training job detail with metrics](https://docs.decimal.ai/api-reference/training/get-training-job-detail-with-metrics.md): Get training job detail with metrics.
- [Manually poll a training job's status from the provider.](https://docs.decimal.ai/api-reference/training/manually-poll-a-training-jobs-status-from-the-provider.md): Manually poll a training job's status from the provider.
- [Cancel a running training job](https://docs.decimal.ai/api-reference/training/cancel-a-running-training-job.md): Cancel a running training job.
- [Attribute orchestrator failures to sub-agents](https://docs.decimal.ai/api-reference/multi-agent-training/attribute-orchestrator-failures-to-sub-agents.md): Attribute observed orchestrator failures back to specific sub-agents.
- [Preview the training dataset that would be built for one sub-agent](https://docs.decimal.ai/api-reference/multi-agent-training/preview-the-training-dataset-that-would-be-built-for-one-sub-agent.md): Preview the training dataset that would be built for one sub-agent.
- [Fan out training jobs for N sub-agents under a single coordinator](https://docs.decimal.ai/api-reference/multi-agent-training/fan-out-training-jobs-for-n-sub-agents-under-a-single-coordinator.md): Launch a coordinated multi-agent training run.
- [List all training jobs in a multi-agent coordinator](https://docs.decimal.ai/api-reference/multi-agent-training/list-all-training-jobs-in-a-multi-agent-coordinator.md): List the per-sub-agent training jobs fanned out by a coordinator.
- [Receive and process Stripe webhook events](https://docs.decimal.ai/api-reference/webhooks/receive-and-process-stripe-webhook-events.md): Receive and process Stripe webhook events.
- [Sync Clerk user events to the local User table](https://docs.decimal.ai/api-reference/webhooks/sync-clerk-user-events-to-the-local-user-table.md): Sync Clerk user events to the local User table.
- [List workspaces visible to the current user](https://docs.decimal.ai/api-reference/workspaces/list-workspaces-visible-to-the-current-user.md): List workspaces visible to the current user.
- [Create a new workspace](https://docs.decimal.ai/api-reference/workspaces/create-a-new-workspace.md): Create a new workspace.
- [Get workspace details](https://docs.decimal.ai/api-reference/workspaces/get-workspace-details.md): Get workspace details.
- [Delete a workspace (cannot delete default)](https://docs.decimal.ai/api-reference/workspaces/delete-a-workspace-cannot-delete-default.md): Delete a workspace (cannot delete default).
- [Update workspace name/description](https://docs.decimal.ai/api-reference/workspaces/update-workspace-namedescription.md): Update workspace name/description.
- [List members of a workspace](https://docs.decimal.ai/api-reference/workspaces/list-members-of-a-workspace.md): List members of a workspace.
- [Add a user to a workspace](https://docs.decimal.ai/api-reference/workspaces/add-a-user-to-a-workspace.md): Add a user to a workspace.
- [Remove a user from a workspace](https://docs.decimal.ai/api-reference/workspaces/remove-a-user-from-a-workspace.md): Remove a user from a workspace.
- [Update a workspace member's role](https://docs.decimal.ai/api-reference/workspaces/update-a-workspace-members-role.md): Update a workspace member's role.

## OpenAPI Specs

- [openapi](/openapi.json)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.