From dataslayer-marketing-skills
Internal development tool that performs a comprehensive quality audit of all marketing skills and agents. Reviews description overlap, format consistency, feature adoption, and structural patterns. Use when the user says "audit skills", "skill quality review", "check skill health", "are my skills consistent", "monthly skill review", or before releasing a new version of the skills repo.
npx claudepluginhub dataslayer-ai/marketing-skillsThis skill is limited to using the following tools:
You are a Claude Code skills architect performing a periodic quality review.
Audits and optimizes Agent Skills (SKILL.md files) across 8 dimensions using session transcripts and static analysis, prioritizing P0-P2 fixes for better triggering.
Diagnoses and optimizes Agent Skills (SKILL.md) using session transcripts and static analysis. Generates P0-P2 prioritized reports for Claude Code, Codex, and compatible agents.
Audits agents and skills across plugin ecosystem for health, quality, and consistency using a seven-dimension checklist covering invocation, location, descriptions, and more.
Share bugs, ideas, or general feedback.
You are a Claude Code skills architect performing a periodic quality review. Your job is to find structural problems, inconsistencies, and missed opportunities across the entire skills collection — not just validate individual files (that's ds-lint's job).
Read every SKILL.md and agent .md file in this repository. For each, extract:
Compare every pair of skill descriptions and identify:
Present as a matrix:
| Skill A | Skill B | Overlapping phrases | Risk level |
|---|---|---|---|
| ... | ... | ... | High/Med/Low |
And list any coverage gaps:
Compare the output format sections across all skills:
Present inconsistencies as a table:
| Pattern | Skills that follow | Skills that don't | Fix needed |
|---|---|---|---|
| ... | ... | ... | ... |
Check which advanced Claude Code features each skill uses:
| Feature | ds-brain | ds-paid-audit | ds-channel-report | ds-seo-weekly | ds-content-perf | ds-churn-signals | ds-report-pdf |
|---|---|---|---|---|---|---|---|
| allowed-tools | |||||||
| model | |||||||
| argument-hint | |||||||
| $ARGUMENTS | |||||||
!context injection | |||||||
| ${CLAUDE_SKILL_DIR} | |||||||
| disable-model-invocation | |||||||
| Related skills section |
Mark each cell as: Yes / No / N/A
For ds-brain and its four subagents:
Present misalignments as specific findings.
For each file:
After all five checks, produce a prioritized list of improvements:
End with a simple health score:
| Dimension | Score (1-5) | Notes |
|---|---|---|
| Description quality | ||
| Triggering accuracy | ||
| Format consistency | ||
| Feature adoption | ||
| Agent alignment | ||
| Maintainability | ||
| Overall |