Skip to main content

Overview

The FastSkill CLI is how you install and operate skills: manifests and skills.lock, validation and fastskill eval, search, plus serve when you want a local HTTP surface.
The CLI supports both interactive and scripting use cases, with comprehensive help text and validation for all commands.

Installation

Use the same install method as the Installation guide (release binary recommended). After install, confirm the CLI is on your PATH:
For Git-based skill sources, use a build that includes Git support if your distribution splits binaries that way. See Installation for details.

Basic Usage

Get Help

1

General help

This shows all available commands and global options.
2

Command-specific help

Global Options

Command Categories

Project and lifecycle

fastskill init

Create skill-project.toml for a skill (authors). See init Command.

fastskill install

Install skills from skill-project.toml (supports groups and --lock). See install Command.

fastskill update

Update skills to latest from source with version strategies. See update Command.

fastskill reindex

Rebuild the search index for semantic discovery. See reindex Command.

fastskill serve

Start the HTTP server (--host, --port). Web UI and API routes are served with the process. See serve Command.

Skills

fastskill add

Add skills from registry ID, git, zip, or local folder (supports -r for recursive folder add, --branch, --tag, -e, --group). See skill commands.

fastskill read

Retrieve skill documentation and base directory path in agent-optimized format. See skill commands.

fastskill list

List locally installed skills with reconciliation status (supports --format table|json|grid|xml, --json). See skill commands.

fastskill remove

Remove skills by ID. See skill commands.

fastskill search

Search remote catalogs by default; use --local for embedding search on installed skills. See search Command.

fastskill repos

Manage repositories (list/add/remove/info/update/test/refresh) and browse remote skill catalog with authentication and priority. See repos Command.

Diagnostics and tooling

fastskill version

Show CLI version.

fastskill eval

Validate and run skill evaluation suites. See eval Command.

fastskill analyze

Similarity matrix, clusters, duplicates. See tooling commands.

fastskill doctor

Check environment readiness (skills directory, embedding provider, auth). See tooling commands.

Version Command

fastskill version

Display the FastSkill CLI version information.
What it shows:
  • CLI version number (e.g., fastskill 0.9.3)
  • Based on the version defined in Cargo.toml
Use cases:
  • Verify FastSkill installation
  • Check version for compatibility
  • Include in bug reports
Example output:

Configuration

Configuration Files

The CLI uses .fastskill/config.yaml for service-level configuration:
.fastskill/config.yaml
Project-level configuration (skill dependencies and repositories) is stored in skill-project.toml at your project root:
skill-project.toml
For opt-in registry publishing builds, see the platform-managed deploy workflow. Skill distribution is handled by the platform operator rather than a self-hosted CLI publish path.

Environment Variables

Scripting and automation

Use the CLI in scripts the same way you would run git or uv: non-interactive flags (--yes, --force, --json) are preferred for automation.

Batch operations

JSON Output

Exit Codes

The CLI returns appropriate exit codes for scripting:

Examples

Example: local project

Example: reproducible install

For running fastskill in automation (build machines, sandboxes), install the CLI in the job image, check out your repo, then run the same commands with secrets injected for registry tokens and OPENAI_API_KEY when needed.

Troubleshooting

Common Issues

Path issue: Ensure FastSkill is installed and in your PATH.
File permissions: Ensure you have read/write permissions for skill directories.
Service permissions: Run with appropriate privileges for system-wide operations.
Port conflicts: Check if the default port (8080) is available.

More verbose output

Some distributions document extra logging variables; check your install notes if you need trace-level diagnostics.

Best Practices

1

Commit manifest and lock

Commit skill-project.toml and skills.lock together for reproducible installs.
2

Reindex after changes

Run fastskill reindex after adding or updating skills so search stays fresh.
3

Use groups for optional skills

Use groups (for example --group dev) and install with --without dev when you want a smaller production skill set.
4

Check the server when you use serve

Confirm http://<host>:<port>/ responds after upgrades or config changes.
5

Back up manifests before big changes

Keep copies of skill-project.toml, skills.lock, and any custom .fastskill config before bulk edits.
Commands can change installed skills and manifest files. Try changes on a copy of the project or a branch first if you are unsure.