feat: improve skill review scores for 5 skills

[rohan-tessl]

Hey @jaktestowac 👋

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
prd-generator	47%	90%	+43%
tech-debt-analysis (plugin)	61%	90%	+29%
code-review	67%	90%	+23%
designing-test-data	77%	93%	+16%
creating-prompts	77%	87%	+10%

This PR intentionally covers 5 of 20 skills to keep the contribution focused and reviewable — more can be improved in follow-ups or via automated review on future PRs.

Changes summary

prd-generator (47% → 90%)

• Rewrote frontmatter description as a quoted string with explicit "Use when" triggers
• Added argument-hint and user-invocable fields
• Stripped all emoji from headings
• Condensed from ~302 lines to ~133 lines — removed explanatory text, tightened phases, compacted PRD output schema into a numbered reference
• Added operating principles and common failure modes sections
• Preserved all domain expertise (strategy classification, structured discovery, AI/ML requirements, stakeholder alignment)

tech-debt-analysis (plugin) (61% → 90%)

• Rewrote description with "Use when" triggers and natural search terms
• Added argument-hint and user-invocable fields
• Removed emoji from headings, condensed from ~234 to ~138 lines
• Compacted output schema while keeping all 6 report sections
• Added a concrete inline debt item example (TD-042 payment test flakiness)
• Merged self-review and quality rules into tight sections

code-review (67% → 90%)

• Replaced generic description with trigger-specific text mentioning PRs, diffs, and merge sign-off
• Added argument-hint and user-invocable fields
• Removed "Prompt Pattern" section (agent identity anti-pattern)
• Added 4-phase workflow: Scope → Review → Categorize → Verdict
• Added concrete inline example showing a null-check finding with before/after TypeScript

creating-prompts (77% → 87%)

• Made description more action-specific with concrete trigger phrases
• Added inline .prompt.md example after Phase 3 (complements existing resource files)
• Compacted Phase 2 frontmatter guidance
• Added two new trigger phrases to "When to Use"

designing-test-data (77% → 93%)

• Expanded description with granular actions and natural trigger synonyms (mock data, sample data, dummy records)
• Added concrete User Registration data pack example table
• Inlined minimal test data catalog template structure
• Consolidated failure modes into design rules
• Action-verb "When to Use" bullets

Want your remaining skills optimised too? 🚀

This PR covers 5 of your 20 skills to keep the contribution focused and reviewable. We have tooling that can go further:

• Optimize remaining 15 skills automatically (same AI-powered pass as above)
• Add a GitHub Action — tesslio/skill-review-and-optimize — that automatically reviews (and optionally optimizes) any SKILL.md changed in future PRs. Review mode works with zero secrets; maintainers can add TESSL_API_TOKEN for AI suggestions and the /apply-optimize comment flow.

Interested? Just tick the box below and we'll raise a follow-up PR:

• Yes please! Raise a follow-up PR: optimize the remaining 15 skills + add the Tessl skill-review-and-optimize GitHub Action
• No thanks — happy with the 5 skills in this PR

---

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 🙏