audit-content

Comprehensive content quality and maintenance assessment. Evaluates documentation quality, relevance, maintenance needs, and provides actionable recommendations.

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/audit-content/SKILL.md

Quality

Content

57%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.

The content is well-structured and self-contained with clear inputs, steps, and outputs, but it is held back by repeated purpose statements, a lack of concrete scoring methodology, and the absence of a validation checkpoint before FIX_MODE applies changes.

Suggestions

Add a validation/verification checkpoint before FIX_MODE applies any fix (e.g., 'Review each suggested fix with the user before applying; re-scan after applying to confirm the issue is resolved') to lift workflow clarity above the cap.

Specify how Quality Score (0-100) and Link Health (%) are computed so the assessment is reproducible rather than subjective.

Remove the redundant restatement of purpose in the opening paragraph and the 'Quick Reference' section, since the description and workflow already convey it.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concepts Claude already knows, but the opening paragraph restates the description and the 'Quick Reference' section repeats the Purpose, creating moderate redundancy that could be tightened — matching the 'mostly efficient but could be tightened' anchor rather than the lean level 4.	3 / 5
Actionability	Inputs, a sequenced workflow, severity tiers, and a concrete output structure are provided, but the quality step is framed as open questions ('Is the content easy to understand?') with no method for computing the cited 0-100 Quality Score or Link Health %, leaving key execution details missing — fitting the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	Three clearly numbered steps give a sound sequence, but FIX_MODE can apply automated fixes (a modifying/batch operation) with no validation or verification checkpoint before applying, which per the judging guidelines caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The skill is a short, self-contained file with no external references and is organized into clear sections (Inputs, Workflow, Required Outputs, Quick Reference); per the simple-skill guidance, this earns the top score for well-organized structure with no need for split files.	5 / 5
	Total	14 / 20 Passed

Description

50%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.

The description conveys a clear purpose and lists several relevant actions in proper third-person voice, but it lacks any explicit 'Use when...' trigger guidance and relies on fairly abstract terms, capping completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit trigger clause, e.g., 'Use when auditing documentation freshness, checking content quality, or planning content maintenance.'

Include natural user-facing phrases and synonyms such as 'audit docs', 'stale documentation', or 'content cleanup' to improve trigger-term quality.

Make the listed actions more concrete (e.g., 'checks broken links, flags documents older than 6 months, scores readability') to lift specificity above the midpoint.

Dimension	Reasoning	Score
Specificity	Names the domain ('content quality and maintenance assessment') and lists several actions ('Evaluates documentation quality, relevance, maintenance needs, and provides actionable recommendations'), but the actions remain fairly abstract rather than concrete, fitting the 'names domain and 1-2 concrete actions' anchor better than the more granular level-4 example.	3 / 5
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3 — exactly matching the 'clear what but when missing' anchor.	3 / 5
Trigger Term Quality	Relevant terms like 'content quality', 'documentation quality', 'relevance', and 'maintenance needs' appear, but common natural phrases a user would say (e.g., 'audit my docs', 'check docs for staleness') and synonyms are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Content quality and maintenance assessment' defines a niche but 'documentation quality' and 'maintenance' are broad enough to overlap with other content/documentation skills, matching the 'somewhat specific but could still overlap' anchor rather than the clearly-distinct level 4.	3 / 5
	Total	12 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: dandye/ai-runbooks
Path: skills/audit-content/SKILL.md
Commit: 72a6863

Reviewed: 2 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.