audit
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (multi-domain technical quality checks producing scored severity reports), when to use it (accessibility checks, performance audits, quality reviews), and uses natural trigger terms. The description is concise, uses third-person voice correctly, and carves out a distinct niche that differentiates it from general code review skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'accessibility, performance, theming, responsive design, and anti-patterns' checks, plus 'scored report with P0-P3 severity ratings and actionable plan.' These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan') and when ('Use when the user wants an accessibility check, performance audit, or technical quality review') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'accessibility check', 'performance audit', 'technical quality review', plus domain terms like 'responsive design', 'theming', and 'anti-patterns' that users working in frontend development would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of technical quality checks across specific domains (accessibility, performance, theming, responsive design) with a scored P0-P3 severity report creates a clear, distinct niche. Unlikely to conflict with general code review or linting skills due to the specific audit/report framing. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured audit skill with strong actionability and clear workflow sequencing. The five diagnostic dimensions are concrete with specific check items and scoring rubrics, and the report template is thorough with severity classifications. The main weakness is that the content is somewhat verbose for a single SKILL.md file — the detailed scoring criteria and report template could benefit from being split into referenced documents, and some instructions at the end restate things Claude inherently knows.
Suggestions
Consider moving the detailed 0-4 scoring criteria for each dimension into a referenced SCORING_RUBRIC.md file to reduce the main skill's token footprint.
Remove the NEVER list at the end — items like 'Report issues without explaining impact' and 'Forget to prioritize' are things Claude already understands and waste tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some verbose sections, particularly the detailed scoring criteria descriptions and the NEVER list at the end which states things Claude already knows (e.g., 'Report issues without explaining impact'). The report template section is necessarily detailed but could be tighter. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific check items per dimension, exact scoring rubrics (0-4), a defined report template with table format, severity classifications (P0-P3), and a structured output format for each finding including location, category, impact, and recommendation. This is copy-paste ready for execution. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: mandatory preparation → diagnostic scan across 5 dimensions → generate report (health score → anti-patterns verdict → executive summary → detailed findings → patterns → positives → recommended actions). The explicit instruction to not fix issues but only document them is a clear constraint, and the re-audit step at the end provides a validation feedback loop. | 3 / 3 |
Progressive Disclosure | The skill references external resources well (frontend-design skill, teach-impeccable command) and uses clear section headers, but the content is quite long and monolithic. The detailed scoring criteria for each dimension and the full report template could potentially be split into referenced files, especially since this exceeds 100 lines of dense content. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- pbakaus/impeccable
- Commit
3a4fc70
- 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.