Audit-first skill and plugin management for Codex, Claude Code, and Copilot CLI.
Keep ~/.skills as the source of truth, export only the discovery surfaces each client should see, and repair drift without guessing hidden client state.
Repository: skill-install-plus-plus | Package: skillpp | CLI: skillpp
- Why This Exists
- What Skillpp Manages
- Highlights
- Support Matrix
- Install
- Quick Start
- Source-of-Truth Model
- Why Audit-First Matters
- Development
- Release Model
- Contributing
- Security
- License
AI assistant skill setups drift quickly once you mix:
- standalone local skill folders
- Git-backed skill repositories
- hybrid repositories that export skills plus bundle metadata
- plugin bundles with manifests, agents, hooks, and runtime files
Copies go stale, links diverge, and it becomes unclear which files are managed versus accidental.
skillpp gives those assets one managed home under ~/.skills, then projects
only the explicit SKILL.md surfaces into client discovery roots.
It is intentionally conservative: audit first, mutate second.
- Standalone local skills normalized into
~/.skills/custom - Git-backed skill repositories stored under
~/.skills/repos/<owner>/<repo> - Plugin bundles stored under
~/.skills/plugins/<publisher>/<name> - Explicit skill exposures for Codex, Claude Code, and Copilot CLI
- Non-destructive alignment when client discovery roots drift away from managed state
- One managed source-of-truth tree under
~/.skills - Supports standalone skills, Git-backed repos, hybrid repos, and plugin bundles
- Audit-first workflow for drift, broken links, legacy copies, and missing exposures
- Safe alignment that creates missing links without rewriting unrelated client state
- Public Python CLI available through
uvx,uv tool install, andpipx - GitHub Actions CI plus PyPI release automation via Trusted Publishing
| Client | Status | Discovery root | Notes |
|---|---|---|---|
| Codex | Supported | ~/.agents/skills |
Respects existing aggregate custom exposures where already in place |
| Claude Code | Supported | ~/.claude/skills |
Injects explicit skill surfaces only |
| Copilot CLI | Supported | ~/.copilot/skills |
Injects explicit skill surfaces only |
uvx skillpp audituv tool install skillpppipx install skillpp- Audit the current managed state:
skillpp audit- Bootstrap the current project into the managed tree:
skillpp bootstrap --source .- Install a skill from GitHub:
skillpp install --repo jackwener/OpenCLI --path skills/opencli-browser- Install a plugin bundle:
skillpp install-plugin --publisher acme --name suite --repo acme/suite- Create missing non-destructive exposures:
skillpp align --apply- Refresh managed repositories and git-backed bundles:
skillpp updateEverything managed by skillpp lives under ~/.skills:
~/.skills/
|- custom/
|- repos/<owner>/<repo>/
|- plugins/<publisher>/<name>/
`- registry.json
Client discovery roots stay separate:
- Codex:
~/.agents/skills - Claude Code:
~/.claude/skills - Copilot CLI:
~/.copilot/skills
This keeps the managed tree explicit while preserving each client's discovery model.
Blind installers are convenient until they overwrite something you needed.
skillpp treats that as a design problem, not a user problem. The tool:
- inventories managed sources before mutating discovery roots
- surfaces legacy copies and mismatched links explicitly
- creates only safe missing links during alignment
- avoids guessing undocumented client plugin registries
That boundary matters most for larger bundles where exported SKILL.md files
are only one part of the package surface.
Run the test suite:
uv run python -m unittest tests.test_manager tests.test_cli -vBuild the package:
uv run --with build python -m buildCheck built artifacts:
uv run --with twine python -m twine check dist/*skillpp is PyPI-first.
Recommended usage modes:
uvx skillpp ...for ephemeral runsuv tool install skillppfor persistent installspipx install skillppas a familiar Python CLI alternative
There is no npm package or npx wrapper in v1.
Contributions are welcome. Start with CONTRIBUTING.md for development workflow, test expectations, and contribution scope.
Security reporting guidance lives in SECURITY.md.
MIT. See LICENSE.