Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

local-build-check

Run local docs build checks on pending content/ changes before opening a PR. Catches broken directives, bad refs, missing includes, invalid substitutions, and indentation errors using the Snooty RST parser. Applies unambiguous fixes from a learned per-repo knowledge base, surfaces ambiguous ones, and appends new errors to a local log. Use when the user is about to commit or open a PR and the pending changes include: edits to .txt or .rst files, changes to YAML extract files in source/includes/, any file renamed/moved/ deleted in content/ (could break :ref:, literalinclude, or include paths), or snooty.toml changes. Also use when the user asks to "check the build", "test before PR", "lint the build", or wants to validate edits work. Do NOT trigger for image-only changes, code-example file edits that don't touch RST, or non-RST config files with no path impact.

771 repo starsObserved in 1 repos

Testing & Quality

GitHub

codex-review

A standalone adversarial PLAN-review loop where Claude Code (builder) and OpenAI Codex (read-only critic) tag-team an implementation plan before any code is written. Use this when you ALREADY have a plan or a clear idea and just want the cross-model stress-test — no requirements interview first. Claude drafts/loads the plan into PLAN.md, Codex reviews it in a read-only sandbox and returns VERDICT:APPROVED or VERDICT:REVISE, Claude revises and re-submits to the SAME Codex session (context preserved) until APPROVED or a configurable MAX_ROUNDS cap is hit. Human approves the converged plan before code. Use when the user says "/codex-review", "codex review my plan", "have Codex review my plan", "argue this plan with Codex", "adversarial plan review", "make Claude and Codex argue/fight over the plan", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants a second-model sanity check on the PLAN before implementation. For a guided requirements interview BEFORE the review, use /grill-me-codex instead. NOT for reviewing already-written CODE (that is the Codex plugin's /codex:review) and NOT for trivial changes.

770 repo starsObserved in 1 repos

Testing & Quality

GitHub

fix-wpt-reftest-failure

Fix Vivliostyle.js bugs found by WPT reftest and reftest-diff failures. Use when: investigating FAIL results from yarn test:reftest or yarn test:reftest-diff, comparing test vs reference render, fixing longstanding WPT failures or regressions, or working through grouped WPT issues such as #1915.

770 repo starsObserved in 1 repos

Testing & Quality

GitHub

playwright-expert

Writes E2E tests with Playwright including test scripts, page objects, test fixtures, reporters, CI integration, API mocking, and visual regression testing.

770 repo starsObserved in 1 repos

Testing & Quality

GitHub

resolve-issue

Resolve a Vivliostyle.js GitHub issue end-to-end. Use when: reproducing a bug, fixing an issue, creating test case from issue, verifying issue behavior, debugging rendering problems. Fetches issue content, creates an HTML test file, reproduces the bug visually with the VS Code integrated browser, and falls back to Chrome DevTools MCP when DevTools-specific diagnostics are needed.

770 repo starsObserved in 1 repos

Testing & Quality

GitHub