Skill rating

Copy-not-move organizer for document trees: hash inventory, dry run, labeled copies, search catalog, verify every source survived. Use when "organize my Downloads", "sort my company folders", or "file

Make an existing Expo/RN or Capacitor app feel native: system tabs, sheets, edge-to-edge, back, haptics, springs, lists. Use when "feels like a website", "not native", "add haptics", "immersive full s

Instant in-site navigation: Speculation Rules, View Transitions, bfcache, 103 Early Hints. Use when "instant navigation", "prerender", "early hints", "back button reloads", or "second page is slow". F

Optimize slow queries, indexes, and N+1s. Use when "slow query", "database performance", "add an index", or "N+1". Schema consistency → audit-db-schema. RLS access control → plan-rls-audit.

Implement error-handling patterns: boundaries, toasts, one API error shape. Use when "error boundary", "error toast", or "standardize API errors". Plan-only audit → plan-error-handling. Sentry triage

Create algorithmic visuals with p5.js, Canvas, or SVG using seeded randomness and interactive controls. Use when "generative art", "procedural visuals", "flow fields", "particle system", or "art from

PDCA quality audit of LLM features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", or "audit AI costs". Jailbreaks → audit-llm-security. Cost c

Build interactive, accessible charts and dashboards with Recharts, D3, or Victory. Use when "chart", "graph", "data visualization", "analytics dashboard", "metrics display", "time-series", "D3", or "R

Repository maintenance: sync the README, remove confirmed dead artifacts, update dependencies safely. Use when "housekeep", "clean up repo", "update README", or "update dependencies". Unused exports →

Audit and fix runtime performance (Core Web Vitals, load priority). Use when "slow page", "LCP/INP/CLS", "fetchpriority", "long tasks", or "bfcache". JS payload → audit-bundle-size. Instant nav → enha

A spec → plan → TDD loop before writing a line. Use when "spec first", "TDD", "do it properly", or LLM output keeps being wrong. Feature through PR → workflow-build-feature. One bug → workflow-fix-and

Apply backend patterns — queues, caching, rate limits, serverless/edge. Use when "queue jobs", "caching layer", "rate limiting", "server actions", or "edge function". Which architecture to pick → audi

Implement real-time features with WebSockets, Supabase Realtime, or Server-Sent Events. Use when "real-time", "live updates", "WebSocket", "notifications", "chat", "presence", "collaborative", "live d

Headed exploratory QA of a live app as guest, then logged in, with junk input and navigation abuse. Use when "monkey test", "wander like a confused user", or "guest vs logged in". CRUD stories → test-

Polish an existing page's hierarchy, spacing, type, and visual personality. Use when "make this page polished/premium", "less crowded", or "better visual hierarchy". Readability → enhance-readability.

NN/g-grounded fix of one existing page's flows. Use when "fix UX of /xxx" or "improve information density". Repo-wide slop plan → plan-antislop. Composition/type → enhance-web-ui. Reading level → enha

Build a new design system (tokens, variants, theming). Use when "create a design system" or "component library from scratch". Drifted existing system → housekeep-design. Plan-only unification → plan-u

Audit frontend API calls against backend implementation for contract alignment and network shape. Use when "API audit", "FE-BE contract", or "review frontend API integration". Live 4xx/5xx reproductio

Release an npm package: version, CHANGELOG, publish, verify. Use when "publish this package", "release to npm", or "ship a new npm version". Running-app production deploy → workflow-ship-and-observe.

Design REST and GraphQL APIs: naming, versioning, error shapes, auth. Use when "design an API", "create endpoints", "REST vs GraphQL", or "API contract".

Write unit and integration tests for a named module or change. Use when "write unit tests" or "add tests for this function". Coverage plan → plan-test-coverage. Mutation score → test-mutation. Browser

playwright-cli guardrail: headed, named -s= sessions, one real action at a time, max 4 attempts, then a BLOCKER. Read before browser work, or when "the browser is stuck", "playwright hangs", or agents

Read-only audit of payment and money-movement code, scoped from Stripe Checkout to in-house ledgers. Use when "audit payment system", "double charge / idempotency", "ledger / reconciliation", or "webh

Operate Sentry: triage and fix unresolved issues, cut noise, audit instrumentation, monitor after deploy. Use when "check Sentry" or "review production errors". One bug → workflow-fix-and-ship. Plan-o

QA a native Android or Expo dev-client build on the emulator: UI, Supabase, Sentry per CRUD step. Use for "test on emulator", "QA Android build", "white screen", or "adb reverse".

Closure mode for one approved plan: finish every open item and connected deferral, verify each acceptance criterion, require completion-judge PASS. Use when "complete everything", "don't defer", "fix

Remove dead code by category — one commit each, typecheck and tests between, bisect on red — then add a Knip ratchet. Use when "delete the dead code" or "wire up Knip". Audit first → plan-dead-code. R

Plan-only OWASP Top 10 and Supabase-first hardening burndown. Use when "security audit plan", "OWASP audit", "hardening plan", or "security burndown". Auth flows → audit-auth-flows. RLS → plan-rls-aud

Plan-only, user-story-driven test coverage audit. Use when "test coverage plan", "traceability matrix", "fake-green tests", or "what's not tested". Mutation score → test-mutation.

Measure and fix a slow coding-agent setup: status line, hooks, instruction bloat, effort, worktree pile-up, antivirus and indexer scans. Use when "Claude is slow" or "CPU is pinned". App speed → audit

Cross-page UX audit of user stories, task completion, and IA. Use when "audit user flows", "IA audit", "can users find X", "navigation audit", or "funnel drop-off". Per-page heuristics → audit-ux.

Plan-only sweep for stubs, dead buttons, fake components, unwired handlers, and dead links, then a wiring plan. Use when "find dead buttons", "stub checker", "fake components", "unwired handlers", or

Interview the user about a plan, decision, or idea one question at a time until you agree. Use when "grill me", "stress-test this plan", "interview me about this", "poke holes in this", "challenge my

Build Model Context Protocol (MCP) servers that expose services, APIs, and data as typed tools for agents. Use when "build an MCP server", "give Claude access to X", "create an MCP tool", "expose my A

Read-only audit of unhappy-path UI states — empty, loading, error, offline, zero-results, permission, overflow — then a fix plan. Use when "check empty/error states", "audit loading states", or "what

Measured fix pass on one screen or flow against seven Laws of UX: Fitts, Hick, Miller, Jakob, Zeigarnik, Goal-Gradient, Von Restorff. Use when "too many choices", "hard to tap", or "users drop off mid

Plan-only performance audit across web, mobile, backend, and data; measures first, fixes nothing. Use when "performance audit plan", "perf burndown", "measure before optimize", or "N+1 audit plan". Ap

Audit and fix app code against OWASP (injection, headers, dependencies). Use when "review security" or "check vulnerabilities". Auth gates → audit-auth-flows. Plan-only → plan-security-audit. RLS → pl

Plan-only audit of documentation against actual code behavior. Use when "docs drift", "sync docs with code", "audit documentation", "stale README", "onboarding docs broken", "phantom docs", or "docs o

Create museum-quality visual art as .png or .pdf: posters, infographics, certificates, badges, banners, social graphics, print. Use when "create artwork", "design graphic", "visual identity", or "prin

Design and build transactional and marketing email templates. Use when "build an email template", "welcome email", "password reset email", "React Email", "MJML", "dark mode email", or "email copy revi

Create and maintain lightweight Architecture Decision Records as agent-readable decision memory: what was decided, why, and what was rejected. Use when "record this decision", "set up ADRs", or "the a

Plan-only GTM audit: monetization, positioning, activation funnel, SEO/AEO, distribution, and a founder interview. Use when "GTM", "go-to-market", "get more users", "grow traffic", or "should this be

Audit and fix email deliverability: SPF, DKIM, DMARC, reputation, bounces and complaints, list hygiene, unsubscribe compliance. Use when "emails go to spam", "set up SPF/DKIM", or "check deliverabilit

Turn raw feedback — bug reports, review comments, Sentry, QA, audit output — into deduplicated tickets and drive each to verified closure. Use when "triage this feedback", "process the bug backlog", o

Full native UI/UX run on a Capacitor, Expo, or RN app: plumbing, native feel, a11y, device QA, PR. Use for "fix our mobile UI/UX", "native pass to a PR", or "feel native and ship".

Plan-only audit of dependencies for hallucinated or slopsquatted packages, supply-chain risk, and license gaps. Use when "check my dependencies", "is this package real", "slopsquatting", "SBOM", or "d

Guardrails for writing, editing, refactoring, or debugging code: surface assumptions, simplicity first, surgical changes. Use when vibe-coding keeps producing wrong results, or for "think before codin

Prove runtimes, installs, tools, services, env names, and the repo's verification commands work before a long run. Use when "preflight the repo", "set up the environment", or tests cannot start. Faili

Capacitor native layer: system bars, keyboard, back, plugins, push, deep links, OTA, native CI. Use for "keyboard covers the input", "status bar overlaps", "add push", or "OTA update".