Fix errors
Finding and fixing common error messages and things that break.
13 skills. Each one is plain markdown you can paste into ChatGPT, Claude, Gemini or any AI chat, or install in Claude Code or Cursor. How it works
debug-cors-errors
Diagnoses and fixes CORS errors such as "No 'Access-Control-Allow-Origin' header" or failed preflight OPTIONS requests between a frontend and an API. Use when the browser console says blocked by CORS policy, fetch fails only in the browser, or cookies are not sent cross-origin.
Not yet model-tested; testing Jan 2027Fix errorsdebug-systematically
A four-phase method for any bug, error, failing test or strange behaviour - find the root cause first, compare with working code, test one hypothesis at a time, then fix with a failing test. Use when something is broken and you do not know why, a fix did not work, or you keep guessing at changes.
Not yet model-tested; testing Jan 2027Fix errorsfix-failing-ci-checks
Diagnoses red checks with the gh CLI - list what failed, pull the failed GitHub Actions job log, find the first real error, reproduce it locally, then propose a fix and apply it only after approval. Use when CI or pull request checks fail, a build job turns red, or code that works locally breaks in CI.
Not yet model-tested; testing Jan 2027Fix errorsfix-git-conflicts
Resolves git conflicts hunk by hunk by first reading the commits, PRs and issues behind each side, keeping both intents where they fit, then running the project's checks and completing the merge or rebase. Use when git stopped with conflicts, a rebase is stuck, there are conflict markers in files, or the user asks to resolve merge conflicts.
Not yet model-tested; testing Jan 2027Fix errorsfix-nextjs-build-errors
Fixes a Next.js build that fails on next build or in a Vercel deploy - read the first real error, then work through type errors, server-only code in client components, missing env vars at build time, bad imports and prerender failures. Use when next build fails, a Vercel build log is red, or the app runs in dev but will not build.
Not yet model-tested; testing Jan 2027Fix errorsfix-react-hydration-errors
Finds and fixes React and Next.js hydration mismatch errors where server-rendered HTML differs from the first client render. Use when the console shows "Hydration failed", "Text content does not match server-rendered HTML", or content flickers or changes after the page loads.
Not yet model-tested; testing Jan 2027Fix errorsreview-and-triage-issues
Triages GitHub issues and outside pull requests with an AI agent - labels each as bug or enhancement, reproduces the bug, checks it is not already built or rejected, asks the missing questions and writes an agent-ready brief. Use when the user has a pile of issues to sort, bug reports to triage, wants to know what an agent can pick up, or asks to move an issue to ready-for-agent.
Not yet model-tested; testing Jan 2027Fix errorstest-before-claiming-done
Makes an AI agent prove work is finished before it says so - run the command that proves the claim, read the full output and exit code, then report what it shows. Use when the AI says done, fixed or tests pass without proof, before committing or opening a PR, or when checking a sub-agent's "success" report.
Not yet model-tested; testing Jan 2027Fix errorstest-first-with-tdd
Test-driven development in plain steps - write one small failing test, watch it fail for the right reason, write the least code to pass, then tidy up while staying green. Use when adding a feature, fixing a bug, refactoring, or when the user asks for TDD, red-green-refactor or tests first.
Not yet model-tested; testing Jan 2027Fix errorstest-site-with-agent-browser
Gives an AI agent a real browser from the shell with the agent-browser CLI - open a page, read its accessibility snapshot, click and fill by ref, wait, screenshot and read console errors - to check its own UI work on a live site. Use when the agent should check its own UI change in the running app, read console errors, grab a screenshot, or drive a page from the shell without a test file.
Not yet model-tested; testing Jan 2027Fix errorstest-web-app-with-playwright
Tests a local web app in a real headless browser with Playwright - start the dev server, wait for the page to load, look before you click, then script the flow and capture screenshots and console errors. Use when the user wants to check a page works, click through a flow, take a screenshot, or see browser console logs.
Not yet model-tested; testing Jan 2027Fix errorswrite-python-tests-with-pytest
Writes clear, fast Python tests with pytest - arrange-act-assert structure, fixtures in conftest.py, parametrize for many cases, mocking only at the edges, and coverage reports. Use when the user wants to add Python tests, set up pytest, test a function or API, or fix flaky or slow Python tests.
Not yet model-tested; testing Jan 2027Fix errorswrite-unit-tests-with-vitest
Writes fast JavaScript and TypeScript unit tests with Vitest - set it up, test pure functions and async code, mock modules and timers sparingly, and test React or Vue components with Testing Library. Use when the user wants JavaScript tests, to set up Vitest or migrate from Jest, or to test a component or function.
Not yet model-tested; testing Jan 2027