Package manager and operational toolkit for Agent AI Skills.
FastSkill helps you manage AI skills with a clean, repeatable workflow:
- Install skills from local folders, git repositories, or registries
- Keep installs reproducible with
skill-project.tomlandskills.lock - Discover skills with remote and local search
- Validate and evaluate skill quality before sharing
- Diagnose your environment with
fastskill doctor
fastskill -V
fastskill init
fastskill add ./skills/my-skill -e --group dev
fastskill install
fastskill listOptional local search flow:
fastskill reindex
fastskill search "text processing" --localskill-project.toml is the project manifest for skill dependencies.
It keeps installs reproducible across teammates and CI together with skills.lock.
Minimal example:
[dependencies]
demo-skill = { source = "local", path = "./skills/demo-skill", editable = true, groups = ["dev"] }Typical workflow:
fastskill add ./skills/demo-skill -e --group dev
fastskill install
fastskill listfastskill add ./skills/pptx-helper -e --group dev
fastskill installfastskill add https://github.com/org/skill.git --branch main
fastskill installfastskill add scope/pptx@1.0.0
fastskill install --lock| Command | What it does |
|---|---|
fastskill add <source> |
Add a skill dependency from local, git, zip, or registry |
fastskill install |
Apply dependencies from skill-project.toml |
fastskill list |
List installed skills |
fastskill read <id> |
Print a skill's full SKILL.md (add --meta for metadata, --tree for its dependency tree) |
fastskill search "<query>" |
Search remote catalog (default) |
fastskill search "<query>" --local |
Search installed skills |
fastskill eval validate |
Validate eval configuration and checks |
fastskill doctor |
Diagnose configuration and environment (e.g. whether semantic search is available) |
fastskill package |
Package skills for distribution |
This repository is a Rust workspace with three primary crates:
crates/fastskill-cli: CLI binary and command routing.crates/fastskill-core: reusable service/library layer.crates/fastskill-evals: standalone evaluation engine primitives.
Each crate has its own docs:
crates/fastskill-cli/README.mdcrates/fastskill-cli/CONTRIBUTING.mdcrates/fastskill-core/README.mdcrates/fastskill-core/CONTRIBUTING.mdcrates/fastskill-evals/README.mdcrates/fastskill-evals/CONTRIBUTING.md
Apache-2.0