feat: improve skill review scores for 5 skills

[rohan-tessl]

Hey @3rdn4Li 👋

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
find-testcases-covering-function	17%	99%	+82%
static-analysis	18%	89%	+71%
retrieval	47%	89%	+42%
neo4j	49%	89%	+40%
fuzz	53%	89%	+36%

This PR intentionally covers 5 of your 23 skills to keep the contribution focused and reviewable — more can be improved in follow-ups.

Changes summary

find-testcases-covering-function (17% → 99%)

• Fixed name validation: renamed from find_testcases_covering_function (underscores) to find-testcases-covering-function (kebab-case)
• Added explicit "Use when..." clause with natural trigger terms (test coverage, which tests hit a function)
• Added concrete usage example with realistic parameter values
• Expanded parameter documentation with defaults and clarifications
• Switched description from vague to specific with Neo4j node types (TESTCASE, METHOD)

static-analysis (18% → 89%)

• Fixed name validation: renamed from static_analysis (underscore) to static-analysis (kebab-case)
• Fixed description format: replaced trailing-newline YAML pipe style with quoted string
• Added "Use when..." clause covering static analysis, call graphs, Joern, vulnerability detection
• Replaced flat bullet list with structured tool table (tool / purpose / key use)
• Added 5-step analysis workflow (identify → explore → trace → slice → query)
• Removed filler "Common Use Cases" section

retrieval (47% → 89%)

• Added "Use when..." clause with natural triggers (find definition, locate symbol, list functions)
• Replaced flat bullet list with structured tool table including "When to use" column
• Added 3-step workflow connecting retrieval to downstream analysis
• Removed redundant "Common Use Cases" section that restated tool descriptions

neo4j (49% → 89%)

• Added "Use when..." clause covering Cypher, graph queries, code property graph
• Added tool table with purpose and usage context
• Added 3-step workflow (query → interpret → combine)
• Added concrete example Cypher queries (listing methods, finding testcases)
• Removed vague "Usage" one-liner

fuzz (53% → 89%)

• Added "Use when..." clause with broad trigger coverage (fuzz testing, AFL++, crash analysis, security testing)
• Replaced flat bullet list with structured tool table
• Added 4-step fuzzing workflow (instrument → fuzz → extract → analyze)
• Removed filler "Common Use Cases" section

Want your remaining skills optimised too? 🚀

This PR covers 5 of your 23 skills to keep the contribution focused and reviewable. We have tooling that can go further:

• Optimize remaining 18 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 18 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 🙏