improve changelog-generator skill structure + eval score

[fernandezbaptiste]

hey @ECNU-ICALK, thanks for publishing AutoSkill. really like the experience-driven lifelong learning approach to skill self-evolution. Kudos on passing 250 stars! I've just starred it.

ran your changelog-generator skill through agent evals and spotted a few quick wins that took it from ~49% to ~100% performance:

• expanded description with trigger terms like release notes, version history, semantic versioning, commit parsing so agents reliably match user requests

• restructured into clear workflow steps + added verification checkpoints for changelog quality

• cut verbose educational content + tightened into actionable tables and rules

these were easy 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 5896 skills, 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.

[fernandezbaptiste]

glad this was useful! opened #4 with a couple of lightweight CI workflows that auto-score skill.md changes on PRs - should help keep skill quality consistent as the project grows.