gardenerlisted

Monthly catalog hygiene audit for Claude Code plugin marketplaces. Inventories every skill and agent, scores each against a 7-dimension rubric via parallel Opus Agents, detects description collisions via Bedrock Cohere v4 embeddings with pairwise cosine, and writes a delta report vs. the prior audit. Proposes resolutions; does not auto-apply. Use when the user asks to audit the catalog, run the gardener, find skill collisions, check plugin hygiene, generate a monthly audit report, or mentions catalog drift.
theagenticguy/agentic-plugins · ★ 2 · AI & Automation · score 81

Install: claude install-skill theagenticguy/agentic-plugins

## Contents | Reference | When to load | | ------------------------------------ | --------------------------------------- | | `references/orchestrator.md` | Running `/gardener` — the 4-phase flow | | `../../references/rubric.md` | Scoring dimensions (shared) | | `../../references/write-protocol.md` | Copied verbatim into every Agent prompt | | `templates/inventory-skeleton.md` | Inventory output file | | `templates/scorecard-skeleton.md` | Per-skill scorecard output file | | `templates/collisions-skeleton.md` | Collisions output file | | `templates/clusters-skeleton.md` | HDBSCAN taxonomy output file | | `templates/report-skeleton.md` | Final audit report | # Gardener Monthly catalog hygiene. Orchestrator runs inside a forked subagent. Walks every skill and agent across the marketplace, scores them in parallel, detects collisions via Bedrock Cohere v4 embeddings, runs an HDBSCAN taxonomy check, and composes a delta report against the prior audit. Proceeds autonomously — planning is reversible. Gates only at the point of writing fixes back to SKILL.md files, which it does not do: it proposes. ## How it works Read `references/orchestrator.md` and follow its phases. Short version: 1. **Inventory** — walk the marketplace, extract frontmatter and file stats, write `audit/YYYY-MM/inventory.md`. 2. **Col