gmackie/agent-skills - 第 3 页

principle-type-system-discipline

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants,…

原文语言：英语

prototype

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

原文语言：英语

react-debugging-advanced

Advanced React debugging techniques using browser DevTools, React DevTools, performance profiling, and error boundaries. Use for troubleshooting complex React applications and performance issues.

原文语言：英语

react-native-expo-release-readiness

Use when preparing a React Native or Expo app for internal release, TestFlight, Play internal testing, or store submission. Discovers the project's release surface, sequences Maestro QA, Expo validation, versioning, environment, OTA, and review-note checks,…

原文语言：英语

react-project-init

Initialize a modern React project with Vite, TypeScript, TanStack Query, Zustand, and shadcn/ui. Use when creating new React applications or setting up React development environments.

原文语言：英语

react-ui-shadcn-tailwind

Generate modern React UI components using shadcn/ui and Tailwind CSS. Create forms, dashboards, data tables, and interactive components with consistent design patterns.

原文语言：英语

read-plans

Fetch, parse, and act on plans published with postplan (postplan.dev). Use when given a postplan URL, when asked to review, execute, resume, or update "the plan", or to list published plans. Plans are HTML documents authored per the html-plans skill. This…

原文语言：英语

recall

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working…

原文语言：英语

research

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

原文语言：英语

resolving-merge-conflicts

Use when you need to resolve an in-progress git merge/rebase conflict.

原文语言：英语

sentry-release-triage

Use when a web app or service has Sentry installed and the task is to verify release readiness, source map correctness, environment wiring, or basic issue-triage hygiene before or after shipping. Inventories SDK setup, config files, release markers, and…

原文语言：英语

setup-matt-pocock-skills

Configure this repo for the engineering skills by setting up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

原文语言：英语

setup-pre-commit

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

原文语言：英语

setup-pstack

Configure which models pstack uses per role. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.

原文语言：英语

show-me-your-work

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or…

原文语言：英语

stripe-payments-integration

Integrate Stripe payments into Next.js and Expo applications with subscriptions, one-time payments, webhooks, and customer management. Use for SaaS billing and e-commerce.

原文语言：英语

tdd

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

原文语言：英语

technical-writing

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

原文语言：英语

to-spec

Turn the current conversation into a spec and publish it to the project issue tracker. Do not interview the user; synthesize what you've already discussed.

原文语言：英语

to-tickets

Break a plan, spec, or the current conversation into tracer-bullet tickets that declare their blocking edges. Publish edges as text in one file per ticket locally or as native blocking links on a real tracker.

原文语言：英语

triage

Move issues and external PRs through a state machine of triage roles by categorising, verifying, grilling when needed, and writing agent-ready briefs.

原文语言：英语

typescript-best-practices

TypeScript best practices. Use when reading or editing any .ts or .tsx file.

原文语言：英语

unity-debug-workflow

Debug Unity projects using console logs, breakpoints, profiler, and unity-mcp integration. Use when troubleshooting Unity games, performance issues, or runtime errors.

原文语言：英语

unity-project-setup

Initialize a new Unity game project with proper structure, settings, and essential packages. Use when creating Unity games, prototypes, or interactive applications.

原文语言：英语

unity-scripting-advanced

Advanced Unity C# scripting patterns, component architecture, and AI-assisted development with unity-mcp. Use for complex gameplay systems, performance optimization, and maintainable code.

原文语言：英语

unslop

Cut AI tells from any writing. Must always apply.

原文语言：英语

vinext-cloudflare-hardening

Use when a vinext project already builds or runs, but the Cloudflare deployment surface still needs hardening. Reviews Wrangler config, assets and image bindings, cache strategy, environment boundaries, and production-risk gaps, then writes a concrete…

原文语言：英语

wayfinder

Plan work too large for one agent session as a shared map of decision tickets on your issue tracker. Resolve the tickets one at a time until the way to the destination is clear.

原文语言：英语

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat,…

原文语言：英语

wizard

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover.…

原文语言：英语

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

原文语言：英语

x402-smol-agent-workflow

Use when working on the x402 challenge, `smol-agent`, or adjacent agent-economics demos where the task involves turning a small agent system into a credible product or challenge submission. Guides repo mapping, milestone shaping, demo-path prioritization, and…

原文语言：英语

saas-turbo-bootstrap

Bootstrap a complete SaaS application using Turborepo with Next.js backend, Expo mobile app, an app-level auth layer, Stripe payments, Turso database, Sentry monitoring, PostHog analytics, tRPC, and TanStack Query.

原文语言：英语