feat: improve 5 skill scores + add Tessl review workflow

[rohan-tessl]

Hey @okwinds 👋

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
demo-skill	11%	80%	+69%
repo-analyzer	0%	75%	+75%
incident-triager	0%	81%	+81%
ci-log-analyzer	0%	86%	+86%
research-planner	0%	85%	+85%

This PR intentionally caps changes at 5 skills to keep review manageable. 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

Across all 5 skills:

• Fixed name format — 4 skills used underscores (repo_analyzer) instead of required kebab-case (repo-analyzer), which blocked the Tessl validator entirely (0% score). This is the single biggest improvement.
• Expanded descriptions — replaced short Chinese-only descriptions with detailed English descriptions including specific actions, tool names, and explicit "Use when..." trigger clauses.
• Added structured workflows — each skill now has a clear numbered workflow showing the step-by-step process the agent should follow.
• Added concrete examples — input/output examples showing exactly what the skill produces.
• Added metadata.version — resolves the missing version warning.

Per-skill details:

• demo-skill (11% → 80%): Added Purpose section, 4-step workflow, bash example with expected output, and notes pointing to production examples.
• repo-analyzer (0% → 75%): Renamed to repo-analyzer, added analysis checklist (bugs, test coverage, anti-patterns), structured diagnosis output format, and pipeline context.
• incident-triager (0% → 81%): Renamed to incident-triager, added 5-step human-in-the-loop workflow, example with log parsing and clarification questions, triage summary output.
• ci-log-analyzer (0% → 86%): Renamed to ci-log-analyzer, added shell_exec pytest example, failure parsing workflow, diagnosis output format with file/line/function targeting.
• research-planner (0% → 85%): Renamed to research-planner, added 4-phase decomposition (prepare → search → read → synthesize), update_plan status tracking example.

Tessl Skill Review GitHub Action

This PR also adds .github/workflows/skill-review.yml so future PRs that touch SKILL.md files get automatic review feedback.

What this workflow does and why it helps

• What runs: On PRs that change **/SKILL.md, the workflow runs tesslio/skill-review and posts one comment with Tessl scores and feedback (updated on new pushes).
• Zero extra accounts: Contributors do not need a Tessl login — only the repo's default GITHUB_TOKEN is used to post the comment.
• Non-blocking by default: The check is feedback-only — no surprise red CI. Unless you add fail-threshold, it never fails the build.
• Not a build replacement: This is review automation for skill markdown only — it doesn't replace your existing CI/Tier-0 pipeline.
• Optional gate: You can add with: fail-threshold: 70 later if you want PRs to fail on low skill scores.
• Why only 5 skills here: This PR caps manual optimization so it stays reviewable. After merge, every PR that touches SKILL.md gets automatic review comments, so the rest of the 70+ 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 🙏