Skill Library Analysis

Analyze, deduplicate, cluster, and select skills from a large skill library or cloned upstream sources. Use when maintaining AI_Skills_Collection, comparing external skill repos, or deciding whether to merge, add, archive, or ignore skills.

YuukiAS Updated

File contents

Skill Library Analysis

Use this to keep a large skill collection coherent. The goal is to reduce duplicates and preserve provenance, not to maximize skill count.

Workflow

  1. Inventory candidate skills with path, name, description, provenance, license, and upstream commit.
  2. Group by user task, not by repository.
  3. Compare each group against existing local skills:
    • exact duplicate;
    • same trigger with stronger references;
    • complementary capability;
    • plugin-only or software-only source;
    • unclear license or provenance.
  4. Choose one action:
    • merge into existing skill;
    • create one new local skill;
    • record only;
    • reject as software/non-skill;
    • defer because of conflict.
  5. Record decisions in a tracked source log before deleting scratch clones.

Quality Rules

  • Do not bulk-import a repository when a distilled local skill is enough.
  • Do not keep multiple active skills with the same trigger boundary.
  • Do not hide conflicts; record them for user decision.
  • Prefer profile and marketplace aggregation over many near-duplicate installable skills.

YuukiAS/AI_Skills_Collection/tree/main/skills/core/codex-system/skill-library-analysis commit 943013a574

Frequently asked questions

npx skillmds@latest add yuukias/skill-library-analysis