Skip to main content

Agent Skill Search

Portable skill catalog search for AI agents. MCP server + CLI.

Skills folders eat your agent's context window — every SKILL.md loads whether the task needs it or not. Move them into a catalog and the agent fetches a skill only when it's relevant. Use grep-like search terms to find the right one for your task.

Install

# recommended — isolated tool install
uv tool install agent-skill-search
# or
pip install agent-skill-search

The PyPI distribution is agent-skill-search — the name skill-search on PyPI belongs to an unrelated package. The commands stay skill-search and skill-search-mcp.

Usage

CLI

skill-search --version               # show version
skill-search update                # upgrade to the latest release
skill-search update --check        # show current version only

# Shorthand: `skill-search "<query>"` == `skill-search search "<query>"`.
skill-search "react performance"

# Default catalog dir is `~/.agents/skills-catalog` (persist a custom one with
# `skill-search dirs --set DIR`). Override per command with `--dirs` or
# `SKILL_CATALOG_DIRS=dir1:dir2`. Bare `skill-search` prints help plus the
# active dirs.

export SKILL_CATALOG_DIRS="$HOME/.hermes/skills"

skill-search search "react performance"
skill-search search "planning|prd|guide"   # multiple keywords (OR search)
skill-search view "vercel-react-best-practices"
skill-search list

# Also scan well-known agent skills dirs (opencode, claude, codex, ...).
# Same-named skills are deduplicated; off by default.
skill-search --include-known list        # or SKILL_INCLUDE_KNOWN=1

# `add` COPIES skill dirs into the default catalog (`~/.agents/skills-catalog`
# unless changed with `dirs --set`); the source tree is left untouched.
skill-search add ~/.hermes/skills

# Always shows the active dirs (stderr); inspect or change the default:
skill-search dirs                # show default, config file, known dirs, active dirs
skill-search dirs --set ~/skills # persist DIR as the default catalog
skill-search dirs --reset        # back to ~/.agents/skills-catalog (also: `dirs --set ""`)

MCP server

One command installs it into your client:

skill-search install claude-code   # or opencode / codex / gemini / openclaw / hermes / pi / claude-desktop / chatgpt

See INSTALL.md for per-client details, manual config snippets, the ChatGPT remote-HTTP setup, and troubleshooting.

Agents without an MCP connection can use the CLI directly. Opt in to append a short usage snippet to existing CLAUDE.md/AGENTS.md files (marker-checked, append-only, never created from scratch):

skill-search install gemini --cli-hint

License

MIT — see LICENSE.

Release files for agent-skill-search 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agent-skill-search 0.4.0
File Size Uploaded
agent_skill_search-0.4.0.tar.gz 28.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for agent-skill-search 0.4.0
File Interpreter ABI Platform
agent_skill_search-0.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 51.1 kB

Release files / agent_skill_search-0.4.0.tar.gz

Download URL agent_skill_search-0.4.0.tar.gz
Size 28.5 kB
Tags Source
SHA-256 checksum
How to use checksums
0460edbddd6bf1fcf9129ff1456c35a17de5903495f18f3e0f8992601b64eb49
BLAKE2b-256 checksum
How to use checksums
a97ac0ec7129d3f36462c883150791a2014c486435e5e2924e35df9c48d28507
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / agent_skill_search-0.4.0-py3-none-any.whl

Download URL agent_skill_search-0.4.0-py3-none-any.whl
Size 22.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
28fcc945b0812143e07e80f2f91454fd2bed16b034c419042ae7451fcde1a04b
BLAKE2b-256 checksum
How to use checksums
6fb55a40c4087a4e76b515d1acb8f9a30c30c5df43a44e00ce05a55f56a4b9f0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release history Release notifications | RSS feed

This release

0.4.0 This release

2 release files

0.3.0

2 release files

0.2.0

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page