Skill rating

Add or upgrade PWA features: manifest, service worker, offline mode, install prompt, push, background sync. Use when "make it a PWA", "offline support", or "install prompt". Native → mobile-capacitor-

Design and run a k6 or Artillery load profile: throughput, latency percentiles, error rate, breaking point. Use when "load test this", "will it handle launch traffic", or "find the breaking point". Co

Modify Cursor/VSCode user settings in settings.json. Use when user wants to change editor settings, preferences, themes, font size, tab size, keybindings, or mentions "settings", "preferences", "theme

Diagnose and fix frontend↔backend contract failures by tracing requests, server logs, validation, auth, and responses on both sides. Use for API 4xx/5xx, mismatched payloads, or "frontend and backend

Enforce architecture boundaries in CI with dependency-cruiser or eslint-boundaries: layer direction, feature isolation, forbidden imports. Use when "enforce module boundaries" or "stop spaghetti impor

Plan-only audit mapping real personal-data flows to the privacy policy, GDPR, Japan APPI, and store labels. Use when "privacy compliance", "what data do we collect?", "App Store privacy labels", or be

Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assista

Read-only audit of mobile IAP and subscriptions (StoreKit 2, Play Billing, RevenueCat): receipt validation, restore, lifecycle sync, grace periods, entitlements. Use when "audit our IAP" or "restore p

Read-only audit of a skill pack for contradictory directives, overlapping triggers, stale cross-refs, and context bloat. Use when "audit my skills", "conflicting skills", "wrong skill triggered", or a

Boot the Android emulator and Metro (Expo or bare RN) in order: check terminals, kill stale ports, pick an AVD. Use when "start Metro", "start emulator", "Cannot connect to Expo", or a stuck dev loop.

Read-only check that a codemod or bulk transform preserved behavior — compiling is not proof. Use when "did this codemod break anything", "audit this bulk refactor", or before merging a mass find-repl

WCAG 2.2 AA audit via playwright-cli: axe-core, keyboard, contrast, target size, focus, ARIA. Use when "audit accessibility", "check a11y", "WCAG audit", "check keyboard nav", or "test screen reader".

Create Cursor hooks. Use to create a hook, write hooks.json, add hook scripts, or automate behavior around agent events.

Read-only OWASP LLM Top 10 audit of app-facing AI: prompt injection, data leakage, unsafe output or agency, RAG risks, unbounded spend. Use when "audit LLM security", "prompt injection", "jailbreak my

Read-only audit of app-layer auth: route×gate matrix, session lifecycle, OAuth, provider traps (getSession vs getUser, middleware-only gates, CVE-2025-29927). Use when "audit our auth" or "check middl

Read-only audit of config parity across dev, staging, and prod: missing or misnamed vars, drifted flags, hardcoded values, reused secrets. Use when "works locally but not in prod", "audit our environm

Read-only audit of CI gate logic: silent bypass, ratchet gaming, required-but-not, duplicate gates. Use when "can CI be bypassed" or "why did a regression pass CI". Cost → audit-cicd. Rule content → a

Read-only audit of hosting, database, storage, egress, and serverless spend (Supabase, Vercel, S3/R2, edge). Use when "hosting bill is high", "cut infra costs", or a bill jumps. CI minutes → audit-cic

Read-only audit of product-analytics events (PostHog, Amplitude, Mixpanel, GA4): taxonomy, funnels, consent-gated firing, dead or duplicate events. Use when "audit our analytics", "are we tracking the

Audit a database schema for consistency, constraints, naming, indexes, and migrations. Use when reviewing schema design. Destructive-op gates → plan-data-integrity. RLS → plan-rls-audit. Restore/RPO →

Consolidate accreted CI gates, ratchets, and hooks into one required aggregator check. Use after audit-gate-logic, or when "clean up our CI checks", "we have three lint jobs", or "make one quality gat

Read-only audit of custom lint and ratchet rules: is each rule right on the merits, not just enforced. Use when "is this lint rule wrong", "the ratchet banned a legitimate pattern", or "audit our guar

Plan-only audit of whether a project can actually recover from data loss, not just whether backups exist. Use when "can we recover if the DB dies", "audit our backups", "what's our RPO/RTO", or "disas

Create a live React canvas beside chat for standalone analytical artifacts that benefit from visual layout: quantitative/security/ architecture analyses, data-heavy timelines/charts/tables, interactiv

Pass/fail health check across every Mushi Mushi pipeline component — CLI credentials, API reachability, edge functions, BYOK key pool, QA cron. Use when "is mushi working", "mushi health check", "chec

Audit GitHub Actions CI/CD for cost, speed, and safety. Use when the Actions bill or minutes are high, runners cost too much, CI is slow, cache storage grows, or "CI/CD / workflow audit". Bypass or ra

Generate Product Requirements Documents through structured conversation for any project. Use when starting a new feature, documenting requirements, creating specs before implementation, or needing cla

Plan-only ASO audit of App Store and Google Play listings: keywords, localized metadata, screenshots, ratings prompts. Use when "optimize our store listing", "improve app downloads", or "ASO". Submiss

Third-party skill — Vercel Web Interface Guidelines compliance (focus, forms, animation, copy). Use when the user names Vercel or web interface guidelines. Generic a11y → audit-accessibility.

Plan-only Capacitor native-layer security audit: WebView, token storage, deep links, OAuth, cleartext, exported activities. Use when "is my Capacitor app secure?". Store readiness → plan-mobile-readin

Run multiple agents in parallel via git worktrees, cloud agents, or multi-model comparison. Use for "run agents in parallel", "best-of-N", "compare approaches", "multi-model", "parallel worktrees".

Implement correlated errors, traces, and structured logs with PII redaction. Use when "add logging", "instrument this", or wiring Sentry/Langfuse. Plan-only audit → plan-error-handling. Sentry triage

Write honest "X vs Y", "alternatives to X", and "migrate from X" pages from verified facts, each unique and dated for review. Use when "comparison page", "vs page", "alternatives to", "competitor page

Fix React Native / Expo speed, size, and upgrade issues: Hermes, FlashList, Reanimated, 16KB alignment, SDK upgrades. Use when "janky scroll", "slow cold start", "app size too big", or "memory leak".

Plan-only App Store / Google Play submission audit for Capacitor and RN: privacy, permissions, signing, target SDK. Use when "ready for App Store?" or "will Google Play reject this?".

Build a project's domain model: a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Decision records (INDEX.md, rejected alternatives

Split current work into small reviewable PRs. Use when the user asks to split a chat, branch, or change set. Whole dirty tree to one merge-ready PR → workflow-release-prep.

Review a PR or diff for correctness, security, and maintainability. Use for a pull request, a named change set, or "review my changes". Repo-wide anti-patterns → audit-code-quality. Bulk transforms →

Add purposeful 3D/WebGL and scroll choreography to an existing site with Three.js/R3F, GSAP, or Motion. Use when "add 3D", "WebGL hero", "React Three Fiber", or "scroll-driven 3D". Motion without 3D →

Inventory parked work — unfinished plans, deferred phases, TODO/FIXME, skipped tests, open findings — into a living BACKLOG.md that diffs new/done/stale. Use when "what's left behind", "inventory TODO

Drive a planned mechanical change to 100% repo coverage after a run stopped early. Use when "finish the burndown", "it stopped halfway", "apply this everywhere", or "half-migrated". One plan plus defe

Co-author structured documents (specs, PRDs, RFCs, proposals) in three stages: gather context, draft, reader-test. Use when writing a proposal, technical spec, or similar long-form document. Decision

Plan-only authenticity / AI-slop audit across prose, UI, code, and IA. Use when "looks like AI slop", "reads like ChatGPT", or "authenticity burndown". One-page UX apply → enhance-web-ux. Visual polis

Diagnose one bug with hypotheses and runtime evidence before fixing. Use when "debug this error" or behavior is unexpected. FE↔BE mismatch → debug-fe-be-integration. Bug to PR → workflow-fix-and-ship.

Compact the current conversation into a handoff document for a fresh agent: state, next steps, suggested skills, gotchas, saved to the OS temp dir. User-invoked via /handoff; an optional argument sets

Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when the user wants to migrate rules or comm

Pre-release quality gate across red-team, security, bundle size, performance, and unit tests. Use when "is this ready to ship?", "quality gate", or "pre-release checklist". Working tree to a PR → work

Take the local working tree to a merge-ready PR against main: review, split if needed, commit, push, open the PR, drive CI green; never merge. Use when "prepare this for a PR" or "get my working tree

Polish one existing React Native screen so it feels native. Use for "this screen looks off", "clunky on iOS", "Android looks wrong", "jank when scrolling", or "button is unreachable".

Run the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants the following text executed directly in the terminal.