voidmatcha

Review and edit Korean technical docs, READMEs, UI copy, and prompts when terminology sounds machine-translated or a canonical English term was unnecessarily translated. Classify each disputed term as canonical English to preserve, established Korean to keep, or an awkward calque to rewrite naturally. Also strips surface AI-tell symbols from Korean prose — em/en dashes and spaced --, arrows (→), curly/smart quotes, ellipsis (…), and middle-dot (·) bullets or noun enumerations. Use for 기술 용어, 번역투, 직역, 영어로 써야 할 표현, 원어 유지, 한글화가 어색함, 용어 통일, 화살표 제거, em대시 없애, 가운뎃점 없애, AI 티 기호, AI slop 기호, Korean technical writing, or terminology review. Do not use as a general spelling or tone checker.

Auto-research and improve a repo's skills, hooks, and scripts: external real-world web research + internal audit + Codex cross-model verification, behind a propose then approve then apply gate with freeze-on-success and auto-revert. Use when asked to improve, audit, harden, or research-improve skills/hooks/scripts in the current repo.

Use public web, GitHub, social/community, video, RSS, and career search surfaces from the CLI/MCP when local repo evidence is not enough. Routes to public-only research tools while avoiding internal/company URLs and secret-bearing pages.

Clean up runaway/orphaned agent processes: stuck zip/tail/python/node, high CPU, dead Claude/Codex/OMX sessions.

Audit installed Claude/Codex agents, skills, commands, metadata-level reference counts, and source-level token pressure to decide what to prune, keep, or route. This inventory skill does not mine historical correction content or decide the current session's handoff state.

Diagnose codegraph/serena MCP setup, Codex config, and per-repo indexes when code intelligence is broken or stale.

Check Claude/Codex/OMX context, cache, headroom, and handover pressure; advise continue, compact, clear, or hand off.

Verify dotfiles install scripts, plugin manifests, hooks, TOML/JSON/plist config, and CI-style smoke checks.

Use this skill to find the root cause of a Cypress end-to-end test that has already run and failed, and fix it. Reach for it whenever someone shares a failing Cypress spec and wants to know why — a Timed-out-retrying command, a selector that never resolves, a cy.intercept alias that never matches or a request that races the assertion, a hook that skips the rest of the suite, a flake that only passes on retry, a hydration or timing race, or a passes-locally-but-fails-in-CI split. It applies given any failure evidence: a mochawesome or JUnit report, an error message or stack, screenshots or videos, or CI artifacts (a GitHub run id to download). Use it to determine whether the failure is a real product regression or a brittle test, and to propose the concrete fix. Do not use it for writing new Cypress tests, reviewing a passing suite, non-Cypress test failures (Playwright, Jest, Vitest), or debugging the app/backend with no Cypress test involved.

Static review of Playwright/Cypress E2E specs and Page Objects (POM) — catch tests that pass CI but prove nothing. Triggers: review tests, audit test quality, find weak/flaky/silently-passing tests, missing awaits, anti-patterns, coverage gaps, tests pass but miss bugs. Not for runtime failure debugging (use playwright-debugger / cypress-debugger). Flags 24 anti-patterns grouped P0 (must-fix, silent always-pass), P1 (poor diagnostics), P2 (maintenance).

Use this skill to find the root cause of a Playwright end-to-end test that has already run and failed, and fix it. Reach for it whenever someone shares a failing Playwright spec or test and wants to know why — a TimeoutError, a broken or ambiguous selector, a whole spec breaking after a deploy, a flake that only passes on retry, a hydration or timing race, or a passes-locally-but-fails-in-CI split. It applies given any failure evidence: an error message, a playwright-report/ or HTML report, a trace.zip, screenshots, or CI artifacts (including a GitHub run id to download). Use it to determine whether the failure is a real product regression or a brittle test, and to propose the concrete fix. Do not use it for writing new Playwright tests, speeding up or reviewing a passing suite, non-Playwright test failures (Cypress, Jest, Vitest), or debugging the app or backend when no Playwright test is involved.

Use this skill to generate new Playwright end-to-end tests from scratch — for a page, a user flow, a form, or a component — taking them from zero to reviewed, passing specs. Reach for it whenever someone wants to add, write, create, or scaffold Playwright E2E coverage, fill coverage gaps for uncovered routes, or bootstrap the first e2e test for a project and set up its conventions. It explores the live page to discover real selectors, proposes a scenario plan for approval, generates Page Object or flat specs that match the existing project style, then runs an e2e review and the suite before handing back. Do not use it for debugging an existing failing Playwright test (use playwright-debugger), reviewing or auditing tests that already pass (use e2e-reviewer), generating Cypress tests, or writing unit, component, or integration tests with Jest, Vitest, or Testing Library.

Capture or record visual behavior from a website — scroll transitions, hover, mousemove/parallax, auto-timers. Also for side-by-side comparison between a reference site and a local clone. Triggers on "take baseline screenshots of <URL>", "record the hover effects", "capture scroll animations", "record the parallax", "capture every transition on <URL>", "compare <ref> vs <localhost>", "diff against the reference". Works standalone or from ui-reverse-engineering / ralph workflows.

Clone or replicate a live website URL as React + Tailwind. Triggers on "clone <URL>", "copy the hero from <URL>", "make it look like <URL>", "rebuild this in react", "remake this site", "match this design from <URL>", "reverse-engineer this layout", "extract the animation from <URL>". Adjacent tools (do NOT trigger this skill — different category): v0/Lovable (prompt → UI, no URL input), screenshot-to-code (screenshot → code, no live URL), Builder.io/Anima (Figma → code). Key signal — the user has a **reference URL**, not a prompt or screenshot. Outputs React components with real extracted values (getComputedStyle, DOM, JS bundle grep for GSAP/Framer/Lenis params, Webflow IX2 timelines). Accepts screenshot/video as fallback (Claude Vision approximation). Does NOT apply to general CSS help or building UIs from scratch without a reference.

Compare original site vs implementation with automated AE/SSIM diff — near-zero vision tokens. Triggers on "it looks different", "doesn't match", "compare with original", "what's wrong", "why is the impl off", "diff against ref", "verify the clone". Uses auto-diagnose to find mismatched elements from diff images without vision tokens. Falls back to reading diff images only when auto-diagnose finds nothing.