Check specific documentation pages against source code, one factual claim at a time. Receive verdicts showing supported, partly supported, contradicted, or unsupported statements, with code file and line references and suggested corrections.
中文简介正在准备中。当前显示英语简介。
Use this skill to verify CLAIM-LEVEL grounding of a documentation page (or set of pages) against the source code. Activate when you have specific pages to check for factual accuracy -- not when sweeping a whole corpus (use docs-corpus-audit for that) and not when triaging a PR diff (use docs-sync for that). Trigger nouns: "is this doc accurate", "verify the page against the code", "fact-check this section", "any claims that drifted from source", "fact-checking", "grounding audit", "drift hunt", "claim verification". Returns per-claim verdicts (GROUNDED | PARTIAL | CONTRADICTED | UNSUPPORTED) with file:line evidence citations. Catches paragraph-level inaccuracies that page-level audit averages over -- e.g. a paragraph with 5 claims where 4 are grounded and 1 is fabricated. Does NOT modify files (returns advisory only); does NOT re-architect the docs; does NOT triage PRs.
安装前可以查看交给 AI 代理的指令内容。
CLAIM-LEVEL grounding verification. Adapts the RAGAS faithfulness-eval pattern (proven in RAG literature) to docs/code instead of generated- answers/retrieved-context. Source code is the ground truth; docs paragraphs are the candidate text under audit.
python-architect persona doc-writer persona
This skill is a SIBLING of docs-corpus-audit and docs-sync. The
boundary is load-bearing:
| Skill | Trigger | Scope | Granularity |
|---|---|---|---|
| docs-sync | PR opened/synchronized | PR diff only | Page-level |
| docs-corpus-audit | Maintainer asks for whole-corpus pass | Entire corpus | Page-level |
| docs-grounding-verifier | Verify specific pages factually | 1..N pages | CLAIM-level |
docs-corpus-audit invokes this skill in its VERIFY phase on the
highest-risk pages of each wave. docs-sync can invoke it on the
specific pages in a PR diff. The skill is also runnable standalone.
docs-corpus-audit.docs-sync.editorial-owner persona directly.PARENT
-> [Stage 1: EXTRACT claims, fan-out PANEL]
per page -> LLM extracts atomic factual claims as JSON
script: scripts/extract-claims.py
-> [Stage 2: RETRIEVE evidence, deterministic S7]
per claim -> grep over src/ via keywords + hints
script: scripts/retrieve-evidence.sh (NO LLM)
-> [Stage 3: JUDGE grounding, adversarial A7]
per (claim, evidence) -> LLM rules GROUNDED|PARTIAL|CONTRADICTED|UNSUPPORTED
asset: assets/judge-prompt.md
-> [Stage 4: SYNTHESIZE]
aggregate ungrounded -> doc-writer for fix
re-verify after fix (A8 ALIGNMENT LOOP)
Stage 2 is the load-bearing design choice: evidence retrieval is DETERMINISTIC (grep + AST hints), not LLM. The judge in Stage 3 can only rule on evidence it actually receives -- it cannot hallucinate support that the retriever did not find. This is the structural guard against the failure mode "the LLM convinces itself the docs match the code."
Input: list of page paths to verify (1..N). If a risk_class is
attached (e.g. "high-stakes"), prefer it; otherwise treat all as equal.
Out-of-scope:
docs/src/content/docs/ or
packages/apm-guide/.apm/skills/apm-usage/.For each page, dispatch ONE claim-extractor agent:
scripts/extract-claims.py <page> produces the
prompt and embeds the page content.{"page", "claims":[{"id","text","section","keywords", "expected_source_areas"}]} capped at 15 claims per page.Parallel safe; no shared state between extractors.
For each claim, pipe to scripts/retrieve-evidence.sh:
{"claim_id","claim_text","evidence":[...], "evidence_count"}.Sequential is fine (grep is fast). No LLM. Diagnostics on stderr, data on stdout.
For each (claim, evidence) tuple, dispatch ONE grounding-judge agent:
assets/judge-prompt.md.judge-prompt.md.Batching across claims-of-one-page into a single judge call is fine (prompt with all tuples at once). Across pages, fan out.
Aggregate verdicts. Materialize the report:
{
"summary": {
"pages_verified": N,
"claims_total": N,
"grounded": N, "partial": N, "contradicted": N, "unsupported": N,
"grounding_rate": N/total
},
"actionable": [
{"page", "claim", "verdict", "evidence_cited", "fix_suggestion"}
]
}
CONTRADICTED and PARTIAL are doc-writer work items. UNSUPPORTED is
split: if retrieval_fix_suggestion is plausible, retry retrieval
with the suggested keywords; if still empty, treat as CONTRADICTED.
Hand actionable items to doc-writer (one subagent per page). After edits, RE-RUN the pipeline on the same pages. The grounding_rate must MONOTONICALLY INCREASE between iterations or the loop has diverged -- stop and escalate to the operator.
evals/) passes on the trigger evals and
the content evals before the skill is treated as production-ready.scripts/extract-claims.py -- Stage 1 prompt builder. --help, --schema.scripts/retrieve-evidence.sh -- Stage 2 retriever. Deterministic. --help.scripts/verify-page.sh -- end-to-end orchestrator. --help.assets/judge-prompt.md -- Stage 3 adversarial judge prompt.evals/trigger-evals.json -- 20 dispatch queries (10 should, 10 shouldn't).evals/content-evals.json -- seeded-drift recall scenarios.evals/run-evals.sh -- the eval-runner that turns JSON into metrics.references/.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Review OpenAPM specification changes through four specialist perspectives covering schemas, registries, dependency resolution, and web architecture. The skill combines findings and mechanical checks into one advisory comment, separating immediate fixes from work deferred to later versions.
中文简介正在准备中。当前显示英语简介。
Review APM positioning, public documentation, release communication, and breaking-change decisions using GitHub evidence. Check that incompatible changes include changelog entries and migration notes, and resolve disagreements among the project's specialist reviewers.
中文简介正在准备中。当前显示英语简介。
Get guidance on using APM, a package manager for AI agents, to install and share reusable instructions, skills, and server configurations. Covers dependencies, package creation, authentication, policy checks, CLI commands, and troubleshooting.
中文简介正在准备中。当前显示英语简介。
Guide authentication changes in APM CLI for GitHub and Azure DevOps. Centralizes credential lookup through AuthResolver and explains token precedence, Azure CLI fallback, Git credential helper retries, and error messages for failed authentication.
中文简介正在准备中。当前显示英语简介。
Post or update one GitHub comment for an APM autopilot run. The skill assembles public or debug content, adds an AI-generated disclaimer, and supports previewing the assembled comment before posting.
中文简介正在准备中。当前显示英语简介。
Build an implementation queue from accepted GitHub issues and distribute them to dedicated workers. Record selection reasons, check for existing pull requests, and process the full queue with a configurable concurrency limit, defaulting to two workers.
中文简介正在准备中。当前显示英语简介。