Menu
Use when the user runs `lyse`, asks to fix design-system drift, or after a Lyse audit. Fixes token/a11y/component/AI-readiness issues a Lyse scan found.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when executing implementation plans with independent tasks in the current session
Use when you have a spec or requirements for a multi-step task, before touching code
Based on SOC occupation classification
| name | lyse |
| description | Use when the user runs `lyse`, asks to fix design-system drift, or after a Lyse audit. Fixes token/a11y/component/AI-readiness issues a Lyse scan found. |
| version | 1.0.0 |
Lyse scans a design system and scores its health (0–100). Your job: fix the issues it found, in the working tree.
lyse audit (or read the handoff findings.json + tokens.json if provided).tokens.json maps each raw value to its token path; prefer the single exact match.lyse explain <ruleId> for the rationale + good/bad examples (the canonical recipe).lyse audit --scope uncommitted (audits only the files you changed in the working tree) and confirm those findings are gone. For the overall result, run lyse audit and confirm the Health Score went up. If a rule still fires, your fix was incomplete.lyse audit --format=json gives the full machine-readable report.LYSE.md at the repo root.