feat: optimize 5 skill scores from 0% to 90-94%

[rohan-tessl]

Hey @Sir-chawakorn 👋

I ran your skills through tessl skill review at work and found some targeted improvements.

Here's the full before/after:

Skill	Before	After	Change
ai-pair-programming	0%	84%	+84%
auto-debug	0%	89%	+89%
code-explanation	0%	92%	+92%
commit-message	0%	94%	+94%
pr-review	0%	86%	+86%

All five skills were scoring 0% because their YAML frontmatter was placed after the H1 heading instead of at the very start of the file — a formatting issue that blocked the Tessl judge from evaluating them at all. This PR fixes that and also improves each skill's description and content.

This PR intentionally caps changes at five skills to keep it reviewable. The included GitHub Action workflow (see below) will surface Tessl feedback on future SKILL.md changes automatically, so the rest of the library can improve incrementally.

Changes summary

All five skills:

• Moved YAML frontmatter (--- block) to the very beginning of the file (was incorrectly placed after the H1 heading)
• Rewrote descriptions to include specific "Use when..." trigger clauses with concrete actions
• Used quoted-string format for descriptions (Tessl best practice)
• Streamlined content: removed emoji clutter, tightened prose, improved workflow clarity
• Preserved all domain-specific knowledge and patterns
• Ensured third-person voice and actionable structure throughout

Skill-specific improvements:

• ai-pair-programming: Clarified the three collaboration modes (driver-navigator, ping-pong, AI-first) with concrete workflows; added communication and code quality best practices table
• auto-debug: Consolidated error pattern tables into a single reference section; added clear 5-step debug workflow with iteration loop
• code-explanation: Structured the three explanation levels (overview, step-by-step, line-by-line) with concrete examples; added explanation workflow with verification step
• commit-message: Consolidated commit types into one reference table; added generation workflow from diff analysis to final message
• pr-review: Organized five review dimensions (quality, correctness, security, performance, testing) with specific "what to look for" guidance; added structured summary template

Tessl Skill Review GitHub Action

This PR also adds .github/workflows/skill-review.yml — a lightweight GitHub Action that automatically reviews SKILL.md files on future PRs:

• What runs: On PRs that change **/SKILL.md, the workflow runs tesslio/skill-review and posts one PR comment with Tessl scores and feedback (updated on new pushes).
• Zero extra accounts: Contributors do not need a Tessl login — only the default GITHUB_TOKEN is used to post the comment.
• Non-blocking by default: The check is feedback-only — no surprise red CI. You can add with: fail-threshold: 70 later if you want a hard gate.
• Not a build replacement: This is review automation for skill markdown only, not a substitute for any compile/transform pipeline.
• Why only five skills edited here: This PR caps manual optimization so it stays reviewable. After merge, every PR that touches SKILL.md gets automatic review comments — so the remaining 45+ skills can improve incrementally.

---

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 🙏