improve rulesync skill for better agent matching

[fernandezbaptiste]

hey @dyoshikawa, thanks for building rulesync. really like the unified approach to AI rule file management across tools. kudos on getting close to 1k stars! just starred it.

ran your rulesync skill through some evals and improved agent performance from ~37% to ~99%:

• improved description with concrete actions, specific file types (.cursorrules, CLAUDE.md), and trigger terms for better agent matching
• replaced the table-of-contents body with an inline quick start, core workflow steps, and key commands table so agents can act immediately
• updated scripts/sync-skill-docs.ts to generate the improved SKILL.md so the build stays clean
• kept all existing linked reference docs intact in a compact detailed reference section

these were straightforward changes to bring the skill in line with what performs well against Anthropic's best practices. honest disclosure, I work at tessl.io where we build tooling around this. not a pitch, just fixes that were straightforward to make.

you've got 17 skills here, if you want to do it yourself, spin up Claude Code and run tessl skill review. alternatively, let me know if you'd like an automatic review in your repo via GitHub Actions. it doesn't require signup, and this means you and your contributors get an instant quality signal before you have to review yourself.

[dyoshikawa]

@fernandezbaptiste thank you. please check the cicheck failure.

[fernandezbaptiste]

fixed! the cicheck was failing because oxfmt wanted to reformat the files. pushed a new commit with the formatter applied — all checks pass now. also improved the skill further (quick start workflow, command reference table, error recovery section).