CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 well-architected, highly actionable skill body with a clear sequenced workflow, validation feedback loops, and properly split bundle references. Its main weakness is length — some framing is restated across sections and could be condensed.

Suggestions

Tighten conciseness: the sibling-contract and architecture-invariants material is partly restated across the description, the 'Sibling contract' table, and the 'Architecture invariants' list — consolidate to remove overlap.

The body references an evals/ directory ('See evals/') that does not exist in the bundle; either include it or drop the reference to avoid a dead pointer.

DimensionReasoningScore

Conciseness

The body is dense and mostly free of concept padding, but at ~200 lines it carries repeated framing (sibling-contract restated, invariants restated in prose and table) that could be tightened, so it sits at 'mostly efficient but could be tightened' rather than the lean level 3.

2 / 3

Actionability

It gives concrete executable commands ('uv run apm <verb> --help', 'grep -n src/apm_cli/', 'python -c "import ..."'), named scripts, schema-validated returns, and specific wave shapes — copy-paste-ready guidance rather than abstraction.

3 / 3

Workflow Clarity

The 8-step process is explicitly sequenced with validation checkpoints (schema validation of returns, alignment-loop re-grep, max 2 redrafts, single-writer git interlock), satisfying the feedback-loop requirement for batch operations.

3 / 3

Progressive Disclosure

SKILL.md is a clear overview with well-signaled, one-level-deep references to real bundle files (assets/subagent-prompt-template.md, assets/panelist-return-schema.json, scripts/scan-cross-corpus-drift.sh), all present; content is appropriately split rather than inlined. The referenced evals/ dir is absent but that does not undermine the structure.

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.

A precise, trigger-rich description that clearly separates this whole-corpus audit skill from its per-PR sibling. It answers what, when, and how to route, with natural maintainer phrasing.

DimensionReasoningScore

Specificity

The description names multiple concrete actions ('run a holistic regrounding pass... page-by-page', 'emit surgical fixes for stale claims'), matching the 'lists multiple specific concrete actions' anchor rather than the single-domain level 2.

3 / 3

Completeness

It explicitly answers both what (whole-corpus regrounding pass + surgical fixes) and when ('Activate when the maintainer wants a WHOLE-CORPUS audit... typical triggers include...'), so it is not capped at 2 for a missing trigger clause.

3 / 3

Trigger Term Quality

It lists natural phrases a maintainer would actually say ('audit the docs', 'reground the corpus', 'check every page against code', 'pre-release docs sweep', 'the docs have drifted everywhere', 'we just reshaped the TOC, find dead links'), giving strong coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

It explicitly carves a distinct niche ('SIBLING to docs-sync, not a replacement') with non-colliding triggers (per-corpus maintainer ask vs per-PR diff), making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 suspicious

Warning

Total

15

/

16

Passed

Repository
microsoft/apm
Reviewed

Table of Contents

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.