Agent skills, portable by design

Measures how well a repository is set up for coding agents, then fixes what it finds. The skill runs the deterministic npx @paniolo/cli scan diagnostic — a static, read-only pass that never writes a file — presents your scores across the six harness dimensions with findings grouped by severity, and leads with the lowest-scoring dimension, where remediation pays off most.

Then your agent does the repair: pick findings (High + Medium is the default), the agent applies them in your working tree, and the scan re-runs so you can see the grade move. An opt-in AI review can add model judgment on top of the deterministic checks — fenced off, so it never touches the scores.

Writes a starter paniolo.config.json — the file that tells the scanner which AI harnesses your repository is tuned for. It inspects the adapters already present (CLAUDE.md, .cursor/, Copilot instructions, AGENTS.md, GEMINI.md, .agents/), asks which of the six supported harnesses you want, and writes a deliberately minimal config.

The file grows with the rule set, so the skill never pre-populates it — and if a config already exists, it shows you what's there before touching anything. The scanner only ever reads this file; this skill is the only thing that writes it.