Find out which of your agent's skills can actually be found, then route a query to the right one. Claude Code / OpenClaw / Hermes. Pure stdlib.
rushindrasinha/skill-audit-router
Skill Claude CodeCodex
Audit installed agent skills for retrievability, then route a query to one. skillaudit.py resolves which SKILL.md files are truly on the runtime load path (excluding marketplace clones, cross-tool mirrors, dev checkouts, duplicates), scores every description, and emits a rewrite brief; skillrouter.py indexes the…
rushindrasinha/skill-audit-router
Skill Claude CodeCodex
Reviews code for quality and correctness issues. Use when asked to review a pull request or check code quality.
rushindrasinha/skill-audit-router
Skill Claude CodeCodex
Reviews code for correctness and quality problems. Use when asked to check a pull request or review code quality.
rushindrasinha/skill-audit-router
Skill Claude CodeCodex
Converts a markdown file into a paginated PDF with a cover page and clickable table of contents. Use when asked to "make a PDF", "export this to PDF", or "turn this markdown into a document". Do NOT use for generating slide decks or presentations.
rushindrasinha/skill-audit-router
Skill Claude CodeCodex
Demonstrates an unroutable description: no output stated, no trigger phrasing, no anchors. The audit should score this near zero.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: