agentleFS
Sign inStart free
aaronfloreyaaronflorey/agent-skills/skills/kasetto/SKILL.md

kasetto

Skill2 starsChanged 7 months agoMITView on GitHub

Use this skill when you need to install, configure, sync, inspect, or troubleshoot Kasetto, including `kst` commands, config files, multi-agent skill installs, MCP integration, private git-host auth, and upgrade-specific behavior.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only the relevant reference file instead of loading everything.

    line 23
  2. Distinctive:

    Prefer exact upstream command syntax and the smallest config that solves the user's case.

    line 24
  3. Very specific:

    Call out destructive commands like kst clean and kst self uninstall before recommending them.

    line 26
  4. Distinctive:

    Start from bundled examples when the user needs a config snippet or a quick command sequence.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

kasetto

Kasetto is a declarative AI agent environment manager for syncing skills and MCP configs across one or many supported agents.

Use This Skill When

  • You need the right kst command, flag, or config shape for install, sync, inspection, cleanup, upgrade, uninstall, or completions.
  • You need to create or debug a kasetto.yaml config for skills or MCP sources.
  • You need to target agent presets such as Codex, Cursor, Claude Code, OpenCode, Copilot, Gemini CLI, or Windsurf.
  • You need to understand non-interactive output, auth for private git hosts, or version-specific behavior.

Working Approach

  • First identify the task type: install/setup, config authoring, sync/list/doctor/clean, MCP integration, auth, or upgrade behavior.
  • Read only the relevant reference file instead of loading everything.
  • Prefer exact upstream command syntax and the smallest config that solves the user's case.
  • For automation or CI, prefer documented non-interactive options such as --json, --plain, NO_TUI=1, and --dry-run when appropriate.
  • Call out destructive commands like kst clean and kst self uninstall before recommending them.
  • Start from bundled examples when the user needs a config snippet or a quick command sequence.

References

  • references/getting-started.md: install methods, first sync, minimal config, scopes
  • references/core-patterns.md: config model, source patterns, agent presets
  • references/api-reference.md: commands, flags, config keys
  • references/testing-debugging.md: dry-run, JSON, plain output, diagnostics
  • references/integrations-plugins.md: MCP support, agent integrations, private host auth
  • references/upgrades.md: feature-by-version lookup
  • references/issues.md: current issue snapshots
  • references/file_structure.md: upstream repo layout

Examples

  • examples/common-commands.md: quick command sequences for setup, inspection, and cleanup
  • examples/minimal-config.yaml: smallest working skill sync config
  • examples/multi-source-config.yaml: mixed skill and MCP config with pinned refs and explicit paths

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free