🧭 SkillRoute

Local-first skill routing for agent builders

Index full SKILL.md bundles into a local catalog, route any request to ranked skills with confidence and evidence, and serve it all to your agents over MCP.

Quick start · Skill Atlas · Agent setup · How it works · Docs

_{Skill Atlas — every skill in your library on one interactive map, with live route previews.}

Why

Most agents choose skills from a one-line description and hope for the best. SkillRoute treats your skill library like a real corpus:

• Full-bundle indexing — parses complete SKILL.md bundles (headings, triggers, templates, relationships), not just frontmatter.
• Explainable routes — every ranked skill carries confidence, reasons, and source evidence. Uncertain routes return clarification questions instead of guesses.
• Local first — one SQLite file, no services to run. Add the Astra DB backend when you outgrow it.

Quick start

One guided line (confirms each step, sets up detected agent clients with backups):

curl -fsSL https://raw.githubusercontent.com/erichare/skillroute/main/scripts/install.sh | bash

Or hands-on, in a checkout:

uv run skillroute index --root examples/skills
uv run skillroute route "Build an MCP server that exposes routing tools"

Ranked skills:
1. mcp-server-patterns (mcp-server-patterns-99fdd0b3d944c32a) confidence=0.3563
   Build MCP servers with Node and TypeScript using tools, resources, Zod schemas, and stdio transport.
   reason: Matched request terms against skill name, description, tags, or excerpts.
   reason: local-token retrieval returned this skill as a candidate.
   reason: Skill graph relationships provide supporting context.
   evidence[description]: Build MCP servers with Node and TypeScript using tools, resources, Zod schemas, and stdio transport.
   evidence[headings]: MCP Server Patterns; When to Use
2. python-testing (python-testing-19ef6ae9ced445b2) confidence=0.1373
   Test Python applications with pytest fixtures, parametrization, temporary paths, and regression coverage.
   ...

The default catalog lives at ~/.skillroute/catalog.db. A .skillroute/catalog.db in the working directory is used instead when one already exists, so existing project catalogs keep working; point elsewhere with --catalog <path> or SKILLROUTE_CATALOG_PATH.

Skill Atlas

Your whole library, mapped. Facet nebula, skill graph, and matrix views; filters for domains, relationship types, orphans, and conflicts; a detail panel with excerpts and source references; and a route preview bar that highlights the chosen path through the graph.

uv run skillroute ui

Plug it into your agent

The bundled MCP server exposes three tools over stdio — skillroute.route, skillroute.search, and skillroute.inspect_skill. One command writes the config for your harness (JSON edits are backed up first):

uv run skillroute harness install claude-code
uv run skillroute harness detect        # what is installed here
uv run skillroute harness list          # everything SkillRoute knows about

Supported harnesses: amp · claude-code · claude-desktop · codex · cursor · gemini-cli · goose · hermes · ibm-bob · opencode · pi · vscode · windsurf · zed

Each one is a single declarative manifest in harnesses/, so adding a new tool is usually a data change with no Python — see Harness Packs.

Route observability

Every route is a trace you can replay: inputs, candidates, scores, and the evidence behind each decision. Golden-route evals keep your catalog honest as it grows.

uv run skillroute traces list
uv run skillroute eval run --fresh --index-root examples/skills --cases examples/evals/golden_routes.json

How it works

flowchart LR
    A["SKILL.md bundles"] --> B["Indexer<br/>parser + metadata review"]
    B --> C[("SQLite catalog<br/>skills · excerpts · graph · traces")]
    C --> D["Router<br/>lexical + retrieval + graph signals"]
    D --> E["CLI"]
    D --> F["Skill Atlas UI"]
    D --> G["MCP server"]
    G --> H["Your agent"]

• Python core — parsing, catalog persistence, hybrid routing, evals, CLI.
• Skill Atlas — FastAPI server + React Flow frontend, bundled into the Python wheel.
• MCP server — TypeScript stdio transport around the Python bridge.
• Backends — local token retrieval by default; SQLite FTS5 (BM25) for larger local libraries, Astra DB Data API and a LangChain-compatible adapter when you want more.

CLI at a glance

Docs

Development

uv sync --extra dev   # dev includes the `ui` extra
uv run --extra dev pytest --cov=skillroute
uv run --extra dev ruff check . && uv run --extra dev mypy

See CONTRIBUTING.md for the full dev setup (web UI, MCP server) and the release process.