Purrfectionist audit
Audit a web or app interface without modifying files. Use when the user asks for a report-only UI review, pre-release visual QA, accessibility findings, responsive or interaction inspection, vibe-code diagnosis, or explicitly invokes $purrfectionist-audit. Return prioritized, evidence-backed findings.From its SKILL.md
npx -y skills add Blackajiro/Purrfectionist --skill purrfectionist-auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 23 days oldThe repository was created 23 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.3 KB, 210 tokens by cl100k_base, as published. Nobody here has run it
Purrfectionist Audit
Read and follow the shared Purrfectionist rules, then read anti-vibe.md and quality.md. Read other routed references only when the interface needs them.
Stay report-only. Do not create, edit, delete, or format project files. Inspect the repository, current diff, rendered interface, visible states, controls, console, and relevant checks with read-only operations where available.
Separate objective failures from subjective taste. Rank only findings that materially change quality and attach each one to concrete evidence: route, component, selector, file, state, viewport, or screenshot region.
Use the shared HISS / GROOM / SHIP audit format. Never return SHIP without
browser proof of the actual implementation. End with the smallest coherent
repair cluster that should happen first.
What ships with it: 1 file
280 B alongside SKILL.md
agents/
- openai.yaml280 B