caliber-ai-org/ai-setup

Adding a Command guides the creation of new CLI commands following the Commander.js pattern, including registration in src/cli.ts, telemetry tracking via tracked(), and option parsing. Use when adding a new command or subcommand, not for modifying existing ones.

Caliber Setup installs the Caliber CLI and pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions sync automatically on every commit. Use it when hooks are missing or agent configs need to stay in sync.

Caliber Testing writes Vitest tests following project patterns: __tests__ directories, vi.mock() with vi.hoisted(), global LLM mock, environment save/restore, and cleanup in afterEach. Use when asked to write tests, add coverage, or debug test failures.

Find Skills searches a public community skill registry and installs relevant skills into the current project when the user mentions a technology, framework, or task lacking existing skills.

LLM Provider adds a new LLM provider that implements the LLMProvider interface with call() and stream() methods, integrates with provider factory, config detection, and usage tracking. Use when adding a new model backend or third-party LLM API.

Save Learning captures user instructions and preferences as persistent project or personal learnings for future AI sessions. Use it when a user says 'remember this', states a convention, or expresses a preference they want applied going forward.

Scoring Checks adds new deterministic checks in src/scoring/checks/ that evaluate AI agent config quality. Use it when adding or modifying scoring criteria, ensuring checks follow the Check[] return pattern and point constants from src/scoring/constants.ts.

Writers Pattern adds new platform writer modules in src/writers/ that generate and write agent config files for a supported platform. Use this when adding platform support for a new agent, integrating a new code AI tool, or extending caliber to support new targets.