poku

Empirical performance comparison playbook for poku covering hypothesis lenses, a standalone harness with a byte-identical correctness gate, variant generation, sequential hyperfine measurement, composition re-testing, and anomaly forensics. Use when measuring, comparing, or proving the performance of any project logic, when the user asks for benchmarks or optimization validation, or when a micro-optimization claim needs evidence before touching src/.

Documentation deep-dive for the poku website covering Docusaurus setup, language policy, feature-to-docs mapping, conventions, JSDoc, and the changelog. Use when editing or adding docs or mapping a feature to its page.

Run the mandatory pre-commit checks for the poku repository before staging a commit. Use this whenever the user asks to commit, prepare a commit, push, open a PR, or verify a change is ready. Runs typecheck, lint:fix, build, and the local test suite in order, plus runtime-sensitive suites when the change touches runtime detection, isolation, child-process spawning, environment-variable plumbing, or any Bun or Deno specific code path.

Testing deep-dive for poku covering test structure, commands, patterns, fixtures, utils, Docker compatibility, and coverage. Use when writing, organizing, or running tests, adding fixtures, or working on coverage.

Architecture deep-dive for poku covering project structure, execution flow, config discovery, runtime detection, and competitive context. Use when navigating the codebase or understanding how components fit together.

Engineering deep-dive for poku covering performance, code, and security patterns, TypeScript config, build pipeline, developer experience, and CI/CD. Use when implementing or optimizing code, writing performance-sensitive logic, touching the build, or applying code-style and security rules.