CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

docs-audit-and-refresh

Audit the repository's docs/ content against the current codebase, find missing, incorrect, or stale documentation, and refresh the affected pages. Use when the user asks to review docs coverage, find outdated docs, compare docs with the current repo, or fix documentation drift across features, settings, tools, or integrations.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

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

A tight, well-structured instruction-only skill: lean prose, a clear five-step audit-to-refresh workflow, and proper progressive disclosure to a real, useful reference file. The residual gaps are minor — validation lacks an explicit fix-and-retry loop, and a couple of steps could be made copy-paste executable.

Suggestions

Add an explicit error-recovery loop to step 5 (e.g., "If any check fails, fix the affected page and re-run the sweep before finishing") to reach the level-5 workflow anchor.

Make the validation sweeps copy-paste executable by supplying the actual search command (e.g., `grep -rn "<old term>" docs/`) instead of only describing the search.

Consider moving the qc-helper index-table detail from step 5 into references/audit-checklist.md, which already covers it, to keep the main workflow steps scannable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence throughout — no concept explanations, no padding, every section carries instructions (e.g., "Remove dead or misleading text instead of layering warnings on top"). It matches the level-5 anchor: every token earns its place; it is clearly above the level-4 anchor, which tolerates trimmable over-explanation, and none is present.

5 / 5

Actionability

Guidance is mostly executable and specific: exact paths to check ("packages/core/src/skills/bundled/qc-helper/SKILL.md"), concrete edits ("Update the nearest `_meta.ts`"), and a concrete search directive ("search for `docs/users/` across `.qwen/skills/` and `packages/core/src/skills/bundled/`"). It is not 5 because a few directives stay imperative rather than copy-paste ready (e.g., no actual grep command for the old-terminology sweep), and not 3 because the guidance is genuinely concrete rather than incomplete pseudocode.

4 / 5

Workflow Clarity

The five-step workflow is clearly sequenced with a dedicated validation section ("Search `docs/` for old terminology", "Check neighboring pages for conflicting guidance", "Confirm new pages appear in the right `_meta.ts`"), so the batch-edit validation cap does not apply. It falls short of 5 because there is no explicit error-recovery feedback loop (no "if a check fails, fix and re-verify" step), which the level-5 anchor requires.

4 / 5

Progressive Disclosure

The body is a well-organized overview with a single clearly signaled, one-level-deep reference — "Read [references/audit-checklist.md](references/audit-checklist.md) before a broad audit" — and that file exists in references/ and contains the detailed checklist content rather than forwarding elsewhere. This matches the level-5 anchor: easy navigation with an appropriate split between overview and detail.

5 / 5

Total

18

/

20

Passed

Description

88%Weight 40%Scale 1-5

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 strong description: third-person voice, three concrete capabilities, and an explicit multi-phrase 'Use when' trigger clause. The only weaknesses are mild — a few missing natural synonyms and some residual overlap risk with generic docs-editing skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Audit the repository's docs/ content against the current codebase", "find missing, incorrect, or stale documentation", "and refresh the affected pages" — covering the full audit-to-fix workflow comprehensively, matching the level-5 anchor. It is not a 4 because coverage here is complete rather than having minor gaps; it clearly exceeds the several-actions-with-gaps example.

5 / 5

Completeness

It explicitly answers both questions: the "what" is stated as three concrete capabilities (audit, find, refresh), and the "when" is an explicit trigger clause — "Use when the user asks to review docs coverage, find outdated docs, compare docs with the current repo, or fix documentation drift". This matches the level-5 anchor exactly and exceeds the level-4 example, whose 'when' is terser and less specific.

5 / 5

Trigger Term Quality

Natural phrases users would say are well covered: "review docs coverage", "find outdated docs", "compare docs with the current repo", "fix documentation drift", plus the surface list "features, settings, tools, or integrations". It falls short of 5 because some common variations and synonyms are missing (e.g., "update the docs", "documentation is wrong", file extensions like .md), though it is noticeably above the 3 anchor's partial coverage.

4 / 5

Distinctiveness Conflict Risk

The docs-drift niche is fairly distinct — triggers like "fix documentation drift" and "compare docs with the current repo" would not fire for unrelated skills. It is not 5 because the docs/editing space is crowded and phrases like "review docs coverage" could overlap with a general documentation-writing skill, leaving minor overlap risk with closely related skills.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

QwenLM/qwen-code

Path

.qwen/skills/docs-audit-and-refresh/SKILL.md

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.