seo-images
Use when optimizing images for SEO — alt text, filenames, formats, lazy loading, responsive sizing.
seo-internal-linking
Use when designing or auditing internal linking strategy — pillar/cluster architecture, anchors, orphan pages.
seo-local
Use when optimizing local SEO — Google Business Profile, NAP consistency, Local Pack ranking, location pages.
seo-page
Use when analyzing a single URL or local file via /seo page — meta, schema, headers, GEO readiness.
seo-plan
Use when building a strategic SEO roadmap by business type (SaaS, local, e-commerce, publisher, agency).
seo-redirects
Use when planning redirects or a site migration — status codes, link equity, redirect chains.
seo-schema
Use when detecting, validating, or generating Schema.org JSON-LD markup for any page type.
seo-sitemap
Use when analyzing or generating XML sitemaps and robots.txt. Not for redirect analysis (seo-redirects).
seo-sxo
Use when optimizing search experience (SXO) — intent matching, personas, dwell time, pogo-sticking.
seo-technical
Use when auditing technical SEO — robots.txt, sitemap.xml, Core Web Vitals, crawlability, indexability.
seo-video
Use when optimizing video SEO — VideoObject schema, YouTube metadata, transcripts, live streams.
solid-tanstack-start
Use when organizing TanStack Start code, splitting oversized routes/server functions, or reviewing architecture. Do NOT use for setup or plain React SPA.
start-auth
Use when adding auth to a TanStack Start app — route protection, server-function authorization, sessions, CSRF. Do NOT use for generic route guards.
start-core
Use when scaffolding a TanStack Start project, wiring the build tool, or debugging setup (blank page, hydration, no client JS).
start-deployment
Use when building or deploying a TanStack Start app — Cloudflare, Netlify, Vercel/Node/Bun, prerendering, or env vars. Do NOT use for app logic or generic Vite config.
start-execution-model
Use when deciding where TanStack Start code runs, fixing secret leaks, DB-in-loader bugs, or hydration mismatches.
start-middleware
Use when composing cross-cutting server logic in TanStack Start with createMiddleware — chaining, context, auth factories.
start-routing-data
Use when loading data in Start routes — isomorphic loaders, TanStack Query in a loader, mutations, or per-route SSR. Do NOT use for generic Router/Query API.
start-server-functions
Use when creating type-safe RPC server logic with createServerFn — validators, handlers, FormData, redirects. Do NOT use for raw HTTP endpoints or middleware chains.
start-server-routes
Use when building raw HTTP endpoints in TanStack Start with the server property — handlers, params, middleware. Do NOT use for internal RPC (start-server-functions).
tailwindcss-utility-classes
Use when unsure which category skill covers a given utility class and need routing to the right one. Do NOT use for concrete class lookup - go to the category skill.
ts-config
Use when creating or migrating a tsconfig.json, choosing module/moduleResolution, or fixing TS 6.0 deprecations that are hard errors in TS 7.0. Not for language syntax (ts-language-patterns).
ts-language-patterns
Use when writing or reviewing modern TS syntax — const type parameters, using/await using, standard decorators, satisfies, or LLM anti-patterns (legacy enum/namespace). Not for tsconfig (ts-config).
ts-lint-format
Use when choosing or configuring a TS linter/formatter — Biome 2.x vs ESLint 10 flat config + typescript-eslint typed linting. Not for type checking itself (ts-config).
ts-packaging
Use when publishing a TypeScript library — exports map, JSR vs npm, dual ESM/CJS, type validation, provenance. Not for application deployment.
ts-runtime-bun
Use when running TypeScript on Bun — bunfig.toml, bun test, Bun.build/--compile, or Bun workspaces. Not for Node.js runtime setup (ts-runtime-node).
ts-runtime-node
Use when running TypeScript directly on Node.js without a build step — native type stripping, its limits, or when to reach for tsx. Not for Bun (ts-runtime-bun).
ts-testing
Use when writing or configuring TypeScript tests and choosing between bun test and Vitest. Not for framework-specific testing (React → react-testing).
apex-methodology
Use when starting ANY development task -- feature, bug fix, refactor, hotfix (triggers: implement, create, build, fix, add feature, refactor, develop).
challenge
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).
fuse-browser-usage
Use when about to call any mcp__fuse-browser__* tool. Routes fetch/crawl/SERP vs live browser session vs screenshot capture, and enforces the 4 ZERO-TOLERANCE rules -- read BEFORE the tool call.
lead-orchestration
Use when you are the LEAD (main session) and an owner request arrives that needs agents -- intake, routing, briefs, follow-up, blocks, verification, learning, report. Canonical procedure from request to verified report; not for sub-agents executing a brief.
think-in-code
Use when analyzing multiple files, auditing a codebase, scanning dependencies, or counting lines -- one Bash pipeline beats N sequential Read calls.
adong-wechat-writer
|
adong-xhs-writer
|
adong-x-writer
|
agent-career-kit
面向校招到资深候选人的 Agent 开发/Agent 算法 Offer 求职系统。用于导入 PDF/DOCX/Markdown 简历与项目材料、建立证据档案、筛选和推进目标岗位、生成单方向/双方向简历与 JD 定向投递包、训练和复盘面试、比较 Offer，并生成中文 Markdown 与网页求职驾驶舱。
andrej-karpathy-perspective
|
github-to-skill
Search GitHub repositories and generate Claude Skills from them. Use this skill when users want to create a new skill based on an existing GitHub repository, need to find high-quality libraries for skill development, or want to transform a GitHub project into a reusable Claude capability. Supports repository search, quality filtering, and skill template generation.
vibe-paper-deai
Audit ML/AI papers for "vibe paper" signals (LLM-generated red flags) and de-AI polish drafts for top venues (NeurIPS, ICML, ICLR, CVPR, ACL, COLM, AAAI). Use this skill whenever the user wants to review a paper as an Area Chair, remove AI writing traces, polish formula-fragmented or bullet-heavy prose, fix overclaiming language, detect hallucinated citations, audit shallow ablations or template-style limitations, or run a pre-submission self-check. Trigger this even when the user doesn't say "vibe paper" — phrases like "AC review", "顶会审稿", "去AI味", "润色论文", "humanize my paper", "review my draft", "is this section too AI", or any submission-quality concern about an academic ML paper should activate this skill.
prompt-design
|
spec-flow
Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan', 'structured development', 'write a spec', 'feature spec', 'technical spec', '需求文档', '技术方案', '任务拆解', '规格驱动', '写个方案', '做个规划', '结构化开发', 'plan this feature', 'break this down', 'design doc'. Creates .spec-flow/ directory with proposal, requirements, design, and tasks.
antlr4-dev
ANTLR4前端开发专家，专注于词法/语法分析、AST构建、访问者模式。
compiler-dev
编译器后端开发专家，专注于IR、CFG、SSA、数据流分析和优化Pass。
ep-navigator
EP项目导航专家，提供21个EP的依赖路由、快速定位和跨EP对比。
git-committer
Git提交专家，规范化提交信息和分主题提交。
tech-blogger
技术图书写作专家，基于三层Prompt架构（系统级→章节模板→实例提示词）生成《AI Context Engineer 视角下的现代编译器实战》书籍章节。
test-dev
测试开发专家，基于JUnit 5 + AssertJ + Mockito + JaCoCo。
vm-dev
虚拟机开发专家，专注于字节码、指令、栈帧、内存管理和垃圾回收。
wix-headless-replatform
Clone, rebuild, migrate, or reverse-engineer a public website home page into a Wix Headless frontend while preserving source identity, SEO, interactions, and visual fidelity.
Page 799 of 1672 · 83563 results
