Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
section-backgrounds
Apply branding guidelines to page sections after style cleanup. Implements 60-30-10 color rule, alternates section backgrounds, and ensures visual hierarchy. Use for each page after running remove-inline-styles.
majiayu000/claude-skill-registry 163
-
dadjoke
Provides a curated list of 10+ classic and obscure dad jokes. Use this skill when an AI needs to quickly generate some humorous dad jokes, such as in casual conversation or to lighten the mood.
majiayu000/claude-skill-registry 163
-
nfr-to-user-impact
将技术性的NFR（非功能需求）约束转换为用户能感知的影响描述，用业务语言解释技术约束的价值。适合在NFR定义完成后、需要向客户或管理层解释时使用，当NFR过于技术化时。帮助不熟悉技术术语的PM/客户/BA理解NFR的业务意义，让技术约束变得亲切易懂。
majiayu000/claude-skill-registry 163
-
Cross-Site Scripting and HTML Injection Testing
This skill should be used when the user asks to "test for XSS vulnerabilities", "perform cross-site scripting attacks", "identify HTML injection flaws", "exploit client-side injection vulnerabilities", "steal cookies via XSS", or "bypass content security policies". It provides comprehensive techniques for detecting, exploiting, and understanding XSS and HTML injection attack vectors in web applications.
majiayu000/claude-skill-registry 163
-
onboarding-cro
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence.
majiayu000/claude-skill-registry 163
-
web-perf
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed.
majiayu000/claude-skill-registry 163
-
spectr-accept-wo-spectr-bin
Accept Spectr change proposals by converting tasks.md to tasks.jsonc without requiring the spectr binary.
USE WHEN you're in a sandboxed or restricted execution context and spectr is not available in your path.
DO NOT USE WHEN you need a lightweight alternative for task acceptance, but have the spectr binary available.
DO NOT USE when you have the spectr binary available.
majiayu000/claude-skill-registry 163
-
seuratclusteringofallcells
Performs coarse clustering on ALL cells (including T cells, B cells, and non-T/B cells) before cell type selection. This process identifies broad cell populations to enable subsequent T/B cell selection via `TOrBCellSelection`. Unlike `SeuratClustering` which works on already-selected T/B cells, this provides initial clustering on heterogeneous cell populations.
majiayu000/claude-skill-registry 163
-
cicd-pipelines
GitHub Actions, GitLab CI, Jenkins, and automated deployment pipelines
majiayu000/claude-skill-registry 163
-
obsidian-hello-world
Create a minimal working Obsidian plugin with commands and settings.
Use when building your first plugin feature, testing your setup,
or learning basic Obsidian plugin patterns.
Trigger with phrases like "obsidian hello world", "first obsidian plugin",
"obsidian quick start", "simple obsidian plugin".
majiayu000/claude-skill-registry 163
-
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
majiayu000/claude-skill-registry 163
-
prototyping-pretotyping
Use when testing ideas cheaply before building (pretotyping with fake doors, concierge MVPs, paper prototypes) to validate desirability/feasibility, choosing appropriate prototype fidelity (paper/clickable/coded), running experiments to test assumptions (demand, pricing, workflow), or when user mentions prototype, MVP, fake door test, concierge, Wizard of Oz, landing page test, smoke test, or asks "how can we validate this idea before building?".
majiayu000/claude-skill-registry 163
-
validation-engine
Validate plugin integrity and offer safe auto-fixes for common issues - checks agents, skills, hooks, routing config, and plugin structure
majiayu000/claude-skill-registry 163
-
domain-web
Use when building web services. Keywords: web server, HTTP, REST API, GraphQL, WebSocket, axum, actix, warp, rocket, tower, hyper, reqwest, middleware, router, handler, extractor, state management, authentication, authorization, JWT, session, cookie, CORS, rate limiting, web 开发, HTTP 服务, API 设计, 中间件, 路由
majiayu000/claude-skill-registry 163
-
os-dev-knowledge-skill
majiayu000/claude-skill-registry 163
-
remix
Builds full-stack React applications with Remix using loaders, actions, nested routes, and progressive enhancement. Use when creating Remix projects, implementing data loading, form handling, error boundaries, or deploying to various platforms.
majiayu000/claude-skill-registry 163
-
modular-design-rule
Promotes modular design with distinct files for models, services, controllers, and utilities.
majiayu000/claude-skill-registry 163
-
codebase-index
Quickly index and understand a codebase's architecture. Use at session start to get up to speed fast. Finds entry points, API routes, classes, models, configs, and patterns.
majiayu000/claude-skill-registry 163
-
audit-semo
전체 SEMO 패키지 통합 품질 감사. Use when (1) 전체 패키지 품질 점검, (2) Agent/Skill/Command 표준 준수 검토, (3) 비효율적 구조 탐지, (4) 정기 감사 수행.
majiayu000/claude-skill-registry 163
-
advanced-math-trading/robustness-risk
Tail risk, EVT, regularization, validation guardrails, and common pitfalls.
majiayu000/claude-skill-registry 163
-
docs-analyzer
Analyzes code changes and identifies documentation gaps. Scans git history, catalogs existing docs, and generates comprehensive analysis reports.
majiayu000/claude-skill-registry 163
-
forensic-refactoring-roi
Use when planning refactoring sprints, prioritizing technical debt backlog, justifying refactoring investment to executives, or creating data-driven roadmaps - calculates return on investment using effort-impact matrices and research-backed formulas
majiayu000/claude-skill-registry 163
-
voice-create
Generate custom voice profiles from natural language descriptions. Use when relevant to the task.
majiayu000/claude-skill-registry 163
-
fullstory-anonymize-users
Comprehensive guide for implementing Fullstory's User Anonymization API (setIdentity with anonymous:true) for web applications. Teaches proper logout handling, session management, privacy compliance, and user switching scenarios. Includes detailed good/bad examples for logout flows, multi-user applications, and privacy-conscious implementations.
majiayu000/claude-skill-registry 163