ux-patterns-for-developers

Hey @thedaviddias 👋 I ran your skills through at work and found some targeted improvements. Since your skills are auto-generated via , I improved the generation script () rather than editing SKILL.md files directly — so improvements persist through regeneration and benefit all 93 skills. Here's the before/after for the 5 lowest-scoring skills: This PR improves all 93 generated skill(s) in the repo by targeting the generation source. What changed in the generation script (pattern-skills-lib.mjs) Added to frontmatter for all generated skills Added array derived from slug, title, and aliases for better discoverability Improved description quality — descriptions now include the first sentence from frontmatter (the "what") plus a "Use when..." clause (the "when"), and alias trigger terms when available Fixed description grammar — changed fallback from "Use when implementing..." to "Use when you need to..." which reads correctly with verb-based summaries Added inline code examples — extracts the first code block from the MDX "Examples" section and includes it as a "Quick-start example" in the SKILL.md body Merged "When to use" and "When to avoid" into a single compact section Improved implementation workflow — 5 concrete steps referencing with specific validation checkpoints instead of abstract directives Added early progressive disclosure — blockquote at top directing to for full examples What changed in the test (pattern-skills-lib.test.mjs) Updated description assertion regex to accommodate the richer description format Added assertions for and in generated output Tessl Skill Review GitHub Action ✅ I've also included a GitHub Action () that automatically reviews any changed in future PRs and posts scores as a PR comment. What this gives you: 🔍 Automatic runs on every PR touching 💬 One updated PR comment with scores and improvement feedback 🔓 Zero extra accounts — contributors don't need a Tessl login; only is used ✅ Non-blocking by default* — feedback-only, no surprise red CI (add later if you want a hard gate) 📈 Covers future skills incrementally as contributors edit them Note: this workflow complements your existing — it reviews skill quality on PRs, while your existing workflow verifies generated files stay in sync. Want automatic AI optimization on every SKILL.md change? 🚀 The action I've added gives you review scores on PRs. We also have a more powerful variant — — that can: Run AI-powered optimization suggestions on every PR (requires adding as a repo secret) Let contributors accept suggested improvements by commenting Still works in review-only mode with zero secrets Interested? Tick the box and I'll raise a follow-up PR: [ ] Yes please! Add the action so every SKILL.md PR gets AI optimization suggestions + the flow [ ] No thanks — the review scores action is enough for now Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide and ask it to optimize your skill. Ping me — @rohan-tessl — if you hit any snags. Thanks in advance 🙏 Summary by CodeRabbit Release Notes New Features Pattern skill pages now include automatically extracted Quick-start code examples. Enhanced skill metadata with invocability markers and computed trigger information. Documentation* Consolidated "When to use" and "When to avoid" sections with improved clarity and labeling. Updated skill descriptions to include trigger alias information for better context.