Skip to main content
New here? Read the Welcome page for the full story, then Quick start and Installation.
FastSkill overview

​
What is FastSkill?

Package manager and operational toolkit for Agent AI Skills. FastSkill enables discovery, installation, versioning, and deployment of skills at scale. It implements the same SKILL.md conventions used by Claude Code–compatible agents, and adds manifests, lockfiles, validation, optional fastskill eval runs, search, and publish flows when you ship skills to others. Modern agents read installed skills directly from the skills directory — no metadata-file sync step. The project is designed around a CLI-first workflow; local fastskill serve exposes an HTTP API and web UI for browsing and integration.

​
What you can do

Package & lifecycle

add, install, update, remove, list, read with skill-project.toml and skills.lock.

Validation

Structure checks on install and reconciliation across manifest, lock, and disk. See Skill validation.

Evals

fastskill eval validate | run | report | score for defined quality suites. See eval command.

Discovery & search

Catalog search by default; --local for installed skills, embeddings, and keyword fallback.

Diagnostics

fastskill doctor reports configuration and environment readiness, including whether semantic search is available. See tooling commands.

Publish & catalogs

package and publish when you distribute; repos for remote sources. See Registry overview.

​
Quick start (CLI)

fastskill -V
fastskill init            # in a skill directory, when authoring
fastskill add ./my-skill -e --group dev
fastskill install
fastskill list
Then optional: fastskill reindex, fastskill search "…" --local, fastskill eval validate, fastskill doctor. Full walkthrough: Quick start.

​
How it fits together

  • You: edit SKILL.md and manifests; agents read skill content. FastSkill does not execute skill logic as a runtime sandbox.
  • CLI: single entry point for installs, checks, search, evals, and packaging.
  • Optional serve: HTTP API and UI on your machine for browsing and integrations.

​
Use cases (summary)

  • Authors: init, validate, eval, and package when ready; publish requires an operator build with registry-publish.
  • Developers: install, list, read, search for what agents load.
  • Teams: shared manifest + lock; groups for optional stacks.
  • Automation: install --lock, package, and optional publish in CI (patterns in CI/CD).

​
Next steps

1

Install

Installation for the fastskill binary.
2

Learn the model

Welcome and Manifest system.
3

Operate skills

Skill validation, Evals and quality, CLI reference.
4

Integrate

Cursor integration or CI/CD.

​
Getting help

Continue with Quick start or the CLI reference.