audit-agents-skills

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.

Quality

61%

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 ./examples/skills/audit-agents-skills/SKILL.md

Quality

Content

38%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 body provides a clear phase structure and some executable detection snippets, but it is notably verbose and relies on a referenced criteria file that is not actually provided, with critical content inlined rather than split into the referenced bundle files.

Suggestions

Provide the referenced scoring/criteria.yaml as an actual bundle file (or inline the full 16 criteria) so the scoring engine is executable rather than stubbed, and remove the '# ... (16 total criteria)' placeholder.

Trim persuasion/padding sections (Why These Criteria?, Scoring Philosophy weight rationale, full LangChain industry report statistics, command-vs-skill comparison, changelog) to assume Claude's competence and cut the body well under its current length.

Add validation checkpoints to the batch workflow (confirm criteria file loaded, verify frontmatter parsed, handle missing files) before scoring proceeds, and split the full JSON report example and CI/CD configs into reference files that actually exist.

Dimension	Reasoning	Score
Conciseness	The ~540-line body contains several padded sections that explain motivation Claude does not need ("Why These Criteria?", "Scoring Philosophy", weight rationale, LangChain industry statistics, command-vs-skill comparison, changelog), fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor rather than the mostly-efficient 3.	2 / 5
Actionability	Some executable guidance is present (parse_frontmatter, has_keywords, jaccard_similarity, estimate_tokens Python snippets), but the core scoring depends on a referenced scoring/criteria.yaml shown only as a stub with "# ... (16 total criteria)", and CI/CD blocks contain placeholder comments like "# Run audit" / "# Parse JSON output", placing it between concrete-and-incomplete, matching the 3 anchor.	3 / 5
Workflow Clarity	A clear five-phase sequence exists (Discovery → Scoring → Comparative → Report → Fixes), but this is a batch operation over many files and the workflow lacks validation checkpoints (e.g., confirm criteria.yaml loaded, verify YAML parsed, handle missing files); per the batch-operation cap, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files (references/, scripts/, assets/) exist, yet the body references scoring/criteria.yaml, audit-report.md/json, and example template directories as though present, while large blocks that belong in separate files (full JSON report schema, criteria tables, CI/CD configs) are inlined, matching the 'minimal structure; content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	10 / 20 Passed

Description

83%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 clearly conveys both what the skill does and when to invoke it, with concrete trigger phrases and a well-defined niche. It is slightly short of fully comprehensive action coverage and exhaustively natural keyword variations.

Dimension	Reasoning	Score
Specificity	Names the domain ("Claude Code agents, skills, and commands") and several concrete actions ("Audit ... for quality and production readiness", "evaluating skill quality", "checking production readiness scores", "comparing agents against best-practice templates"), but coverage of distinct actions is not fully comprehensive, fitting the 'several specific actions; minor gaps' anchor rather than a 5.	4 / 5
Completeness	It explicitly states both what (audit/evaluate/check/compare agents, skills, commands for quality and readiness) and when ("Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates" provides good natural-keyword coverage with synonyms (evaluating, checking, comparing), though a few common user phrasings are absent, matching the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The Claude Code agent/skill/command auditing niche with explicit triggers is mostly distinct from general code-quality skills, with only minor overlap risk, fitting the 'mostly distinct; minor overlap risk' anchor rather than a clearly-conflict-free 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (548 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Path: examples/skills/audit-agents-skills/SKILL.md
Commit: 752edfe

Reviewed: about 7 hours 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.