Skills Librarian AI Agent

What this agent does

As a workspace accumulates skills, "do we already have something for this?" becomes a real question nobody can answer from memory. This agent indexes every SKILL.md in your workspace and answers that question instantly — point it at a task and it tells you which skill (if any) already covers it, or confirms there's a gap.

1. skill-indexer — walks every skills directory in your workspace, parses each SKILL.md's frontmatter and description, and builds a single searchable index.
2. skill-matcher — given a plain-language description of a task, searches the index and returns the best-matching skill(s) with a confidence note, or reports that no existing skill covers it.

The index is rebuilt incrementally, so adding a new skill to your workspace makes it discoverable on the very next query without a full re-scan.

Requirements

• Works on OpenClaw — this agent is built specifically around OpenClaw's project-scoped skills convention (SKILL.md files with AgentSkills-format frontmatter).
• No external API required — indexing and matching both run on your existing OpenClaw model access.

Setup

1. Unzip the package into your workspace, keeping the folder structure intact.
2. Edit config/skills-roots.md to list the directories where your skills live (defaults to the standard OpenClaw skills locations).
3. Run the starter prompt in starter-prompts.md to build the initial index.
4. From then on, just ask "which skill handles X?" and the agent queries the index directly — no need to re-run indexing manually unless you add skills outside the watched directories.

What's included

• Skills/skill-indexer/SKILL.md and Skills/skill-matcher/SKILL.md
• config/skills-roots.md — editable list of directories to index
• config/skills-index.md — the generated index (rebuilt incrementally)
• installation-prompt.md — install instructions for OpenClaw
• starter-prompts.md — example prompts for building the index and querying it
• assets/ — pipeline diagram