Name: docs-corpus-audit
Rating: 74.4 (1 reviews)
Author: microsoft

docs-corpus-audit

Use this skill to run a holistic regrounding pass on the entire microsoft/apm documentation corpus against current source code, page-by-page, and emit surgical fixes for stale claims. Activate when the maintainer wants a WHOLE-CORPUS audit (not per-PR review) -- typical triggers include "audit the docs", "reground the corpus", "check every page against code", "pre-release docs sweep", "the docs have drifted everywhere", or "we just reshaped the TOC, find dead links". Wave-batched and S7-verified; scales to the full ~112-page corpus in ~10 minutes wall-time. This is a SIBLING to docs-sync, not a replacement: docs-sync is per-PR (triggered by a diff); this skill is per-corpus (triggered by a maintainer ask). They share agent personas, schemas, and the docs index, but their triggers MUST NOT collide. Does NOT auto-merge, does NOT push without maintainer review, and does NOT replace per-PR drift detection.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-structured body with concrete commands, an 8-step validated workflow, and a correctly wired bundle. The only weakness is verbosity from restating the sibling/trigger boundary in multiple sections and an ornamental provenance block.

Suggestions

State the docs-sync trigger boundary once (in the Sibling contract section) and reference it elsewhere instead of repeating the per-PR vs per-corpus distinction in the intro, table, and roster.

Trim or fold the Provenance section into a one-line note; session-design provenance does not aid runtime execution and reads as ornamental padding.

Merge the Roster table's persona column with the Sibling contract table since both enumerate the same shared personas, eliminating the overlap.

Dimension	Reasoning	Score
Conciseness	Substantively dense and free of generic concept-explanation padding, but the trigger/dispatch boundary is restated in the intro, the Sibling contract table, and the Roster, and the provenance block is ornamental -- earning 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Fully executable guidance throughout -- 'uv run apm <verb> --help', 'grep -n src/apm_cli/', 'python -c "import ..."', concrete script invocations, file paths, and numeric thresholds (>20 edits, max 2 redrafts, >=0.5 val) -- copy-paste ready.	3 / 3
Workflow Clarity	The 8-step process is explicitly sequenced with validation checkpoints (schema-validation of returns, cross-corpus post-pass) and a real feedback loop (alignment re-grep -> targeted re-dispatch, bounded max 2 redrafts) for this batch operation.	3 / 3
Progressive Disclosure	Clear overview body with well-signaled, verified one-level-deep references to real bundle files (assets/subagent-prompt-template.md, assets/panelist-return-schema.json, scripts/scan-cross-corpus-drift.sh), each listed in the Bundled assets section with its purpose.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exceptionally strong description: concrete actions, abundant natural triggers, explicit what/when guidance, and hard sibling-boundary language that prevents dispatch collision. No first/second-person voice issues; substance rather than fluff throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions -- 'run a holistic regrounding pass', 'page-by-page' audit, 'emit surgical fixes for stale claims', 'Wave-batched and S7-verified' -- matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (regrounding pass + surgical fixes) and when ('Activate when the maintainer wants a WHOLE-CORPUS audit' with enumerated triggers), satisfying the top anchor for both what AND when.	3 / 3
Trigger Term Quality	Dense coverage of natural maintainer phrasings -- 'audit the docs', 'reground the corpus', 'check every page against code', 'pre-release docs sweep', 'the docs have drifted everywhere', 'reshaped the TOC, find dead links' -- well beyond the 'some relevant keywords' anchor.	3 / 3
Distinctiveness Conflict Risk	Niche is sharply delimited -- 'SIBLING to docs-sync, not a replacement', per-PR vs per-corpus trigger split, and 'Does NOT auto-merge... does NOT replace per-PR drift detection' make collision unlikely, matching the clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 8 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: .agents/skills/docs-corpus-audit/SKILL.md
Commit: 634f7b6

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.