First steps with Kasetto

After installing Kasetto, you can check that it is available by running the kst command:

$ kst
An extremely fast AI skills manager

Usage: kst <COMMAND>

...

You should see a help menu listing the available commands.

Creating a config

Create a skills.config.yaml in your project to declare the skills you want:

agent: claude-code

skills:
  - source: https://github.com/org/skill-pack
    branch: main
    skills:
      - code-reviewer
      - name: design-system

Tip

Use the agent field to target any of the 35+ supported agents, or use the destination field for a custom install path.

Syncing skills

Run kst sync to install the declared skills:

$ kst sync
Syncing skills from 1 source...
  ✓ code-reviewer (installed)
  ✓ design-system (installed)
Synced 2 skills in 1.2s

Kasetto reads the config, pulls the skills, and installs them into the right agent directory. Next time you run sync, only changed skills are updated.

Syncing from a remote config

Kasetto can fetch configs from any HTTPS URL — useful for sharing a single config across a team:

$ kst sync --config https://example.com/team-skills.yaml

Previewing changes

Use --dry-run to preview what would change without writing anything:

$ kst sync --dry-run
Would install: code-reviewer, design-system
Would remove: old-skill

Exploring what's installed

Browse installed skills interactively:

$ kst list

Navigate with J / K, scroll with Page Up / Page Down, jump with G G / Shift+G. Set NO_TUI=1 or pipe the output to get plain text instead.

Check your local setup:

$ kst doctor

This prints version, manifest DB path, installation paths, last sync time, and any failed skills.

Using JSON output

All commands support --json for scripting and CI:

$ kst sync --json
$ kst list --json
$ kst doctor --json

Next steps

See the configuration reference for the full config schema, or browse the commands reference for all available flags.