Transforms marketing content across languages and markets through transcreation — adapting message, tone, and cultural references instead of translating word for word — while honoring per-locale brand rules and a do-not-translate glossary. Use when localizing content or when a locale is set. Trigger with…
Turn one versioned résumé file (JSON Resume) into an ATS-friendly PDF in the template that fits you best — no Node, no keys, no network; just a browser.
Render a JSON Resume file through an HTML template into a self-contained, ATS-friendly document ready for the browser's Save-as-PDF. Use when the user asks to render, build, generate, or export their résumé/CV.
Grounds Claude in documentation matched to the library versions installed in your project — across npm, PyPI, crates.io, and Go. Zero-config, no API key.
Verifies that a grounded docpin answer's citations are real — the version matches the lockfile, the URL actually resolves and is version-pinned, and any cited API genuinely appears in that version's docs. Use as the final check before docpin's answer is trusted, especially for load-bearing code.
Runs docpin's resolve → fetch → distill loop for ONE library in isolation, keeping the multi-step lookup out of the main session's context. Use when the main session needs version-matched docs for a library and you want the fetch/registry-lookup noise kept out of its context.
Use when about to write or explain code that imports or calls a third-party library, or when the user asks how to use a named library/framework — resolves the version installed in the project and grounds the answer in version-matched documentation.
Keeps your tests and types green while you code — fixes red with minimal changes, maintains behavioral tests, and won't let you walk away from red. No fake-green.
Fixes one failing test or type/compile error with the smallest correct change and re-runs to confirm. Applies the anti-fake-green rules. Use to turn a specific red item green.
Verifies that a fix or new test made something genuinely green and did not cheat. Enforces the anti-fake-green rules and runs revert-verification. Use as the final check before green-keeper reports success.
Writes or updates a behavioral test for changed code, following test-quality, and verifies the test actually exercises the change. Use to cover new/changed code.
Use whenever fixing a failing test/type error or writing a test, to guarantee the fix is real and not a cheat. Defines what counts as fake-green and how to verify a fix is legitimate.
Use to figure out how to run a repo's tests and type/compile checks, and to write the green-keeper config. Covers common ecosystems and the config schema.