feat: improve skill scores for beastmode

[rohan-tessl]

Hey @BugRoger 👋

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
design	72%	94%	+22%
validate	76%	94%	+18%
plan	79%	94%	+15%
release	76%	89%	+13%
implement	81%	90%	+9%

This PR is intentionally scoped to 5 skills to keep it reviewable — the remaining beastmode skill (82%) can be improved in a follow-up.

Changes summary

Across all 5 skills:

• Expanded frontmatter descriptions with explicit "Use when..." clauses listing natural trigger phrases (e.g., "spec out a feature", "cut a release", "run tests") so agents select the right skill more reliably
• Added concrete action lists in descriptions instead of vague verbs — e.g., "executes unit and integration tests, runs linters, checks type correctness" instead of "testing, linting, validating"
• Added example TodoWrite structure inside each HARD-GATE block so agents have a concrete first-action reference without needing to load phase files
• Added validation feedback loops in Phase 2 descriptions (e.g., "If failures → fix and re-run before proceeding") to make error recovery visible at the top level
• Quoted description strings in frontmatter for standard YAML formatting

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 🙏