feat: optimize tdd skill (89% → 99%)

[rohan-tessl]

Hullo @mfranzon 👋

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
tdd	89%*	99%	+10%

*Note: The raw "before" score was 15% because the frontmatter used non-standard field names (skill: instead of name:, trigger: instead of description:), which blocked the LLM judge entirely. I fixed the field names first to get a meaningful 89% baseline, then optimized from there.

Changes made

Frontmatter fixes:

• Renamed skill: to name: (standard field)
• Renamed trigger: to description: (standard field)
• Expanded description with concrete actions: "Writes failing tests, implements minimal passing code, runs the full test suite, and suggests refactoring"

Content improvements (conciseness):

• Removed repeated pause/no-pause rules from the Rules section that were already stated inline in the workflow steps
• Tightened parenthetical explanations throughout (e.g., removed "this means either..." phrasing)
• Simplified conditional phrasing in Phase 1 input type detection
• Cut "no pause needed" / "no pause" redundancies from GREEN and REFACTOR sections

All domain expertise preserved — TDD methodology, Red-Green-Refactor workflow, language-specific configs, and decomposition patterns are untouched.

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 - @popey - if you hit any snags.

Thanks in advance 🙏