Docs Grounding Verifier

What it does

When your agent uses it

• Verify CLAIM-LEVEL grounding of a documentation page (or set of pages) against the source code
• Nouns: is this doc accurate
• Verify the page against the code
• Fact-check this section

Example prompts

• “is this doc accurate”
• “verify the page against the code”
• “fact-check this section”
• “/docs-grounding-verifier”

Requirements

• A Bash shell

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1SCOPE
2. 2EXTRACT (parallel)
3. 3RETRIEVE (deterministic, batched)
4. 4JUDGE (parallel)
5. 5SYNTHESIZE
6. 6ALIGNMENT LOOP (A8)

What it can do on your machine

Read from SKILL.md and the folder at commit 280b8a7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Shell, from the files we listed), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Docs Grounding Verifier loads about 1.9k tokens when it runs. Until then it costs about 227 tokens; SKILL.md has 662 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~227

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from microsoft/apm at commit 280b8a7, republished under its MIT licence (© microsoft). 662 words, ~1,881 tokens.

name

docs-grounding-verifier

description

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.

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)

{
  "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"}
  ]
}

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 112 other files (scripts, assets) in .apm/skills/docs-grounding-verifier of microsoft/apm.

• SKILL.md
• assets/judge-prompt.md
• evals/content-evals.json
• evals/run-evals.sh
• evals/runs/20260527-194228/seeded-corpus/drift-install-flag/page.md
• evals/runs/20260527-194228/seeded-corpus/drift-install-flag/scenario.json
• evals/runs/20260527-194228/seeded-corpus/drift-policy-reject/page.md
• evals/runs/20260527-194228/seeded-corpus/drift-policy-reject/scenario.json
• evals/runs/20260527-194228/seeded-corpus/drift-registry-resolver/page.md
• evals/runs/20260527-194228/seeded-corpus/drift-registry-resolver/scenario.json
• evals/runs/20260527-194228/trigger-prompts.txt
• evals/runs/proof/claims
• … and 101 more

Open the folder on GitHubat commit 280b8a7