Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
simple-math
Perform basic arithmetic operations safely using standard operators without eval or exec
majiayu000/claude-skill-registry 163
-
sayt-lifecycle
Unified development lifecycle tool. Use when the user asks about building, testing, setting up, deploying, or configuring a development environment. Teaches how to write and fix the configuration files behind each verb and how to configure sayt itself.
majiayu000/claude-skill-registry 163
-
code-style
PHP coding standards and WordPress patterns for ActivityPub plugin. Use when writing PHP code, creating classes, implementing WordPress hooks, or structuring plugin files.
majiayu000/claude-skill-registry 163
-
swiftui-parity-components
Implement and verify SwiftUI API parity for Raven UI components. Use when asked to audit missing or mismatched SwiftUI views/modifiers, add parity components, wire examples into `Examples/TodoApp`, validate rendering in a browser (including dark mode), and prepare branch/PR deliverables.
majiayu000/claude-skill-registry 163
-
new-function
Add a new template function to jhelm (Helm or Sprig)
majiayu000/claude-skill-registry 163
-
godot-clean-conflicts
Use when Godot code has operations that conflict with each other, creating undefined behavior. Detects same property set in multiple places (_ready, _process, code + editor), same signal connected multiple times, conflicting physics modes, competing animations. Automatically resolves conflicts with clear ownership.
majiayu000/claude-skill-registry 163
-
templates-1203992808-chatgptcaricature-2
majiayu000/claude-skill-registry 163
-
kradleverse:join
Join a Kradleverse game
majiayu000/claude-skill-registry 163
-
agentv-eval-analyzer
Analyze evaluation results for quality improvements — identify LLM-judge evaluators replaceable with deterministic assertions, flag weak/vague assertions, and surface cost/quality opportunities. Use after running evals to improve your evaluation config.
majiayu000/claude-skill-registry 163
-
create-master
基于佛教经典文献，生成特定高僧大德的 AI 教学角色
majiayu000/claude-skill-registry 163
-
tasks
Autonomous task management with execution loop. Creates tasks, executes them, spawns subtasks when blocked, and NEVER stops until all tasks are complete.
majiayu000/claude-skill-registry 163
-
schema-markup
Use this skill when implementing structured data markup using JSON-LD and Schema.org vocabulary for rich search results. Triggers on adding schema markup for FAQ, HowTo, Product, Article, Breadcrumb, Organization, LocalBusiness, Event, Recipe, or any Schema.org type. Covers JSON-LD implementation, Google Rich Results eligibility, validation testing, and framework integration (Next.js, Nuxt, Astro).
majiayu000/claude-skill-registry 163
-
TanStack Router
Build type-safe, file-based React routing with TanStack Router. Supports client-side navigation, route loaders, and TanStack Query integration. Prevents 20 documented errors including validation structure loss, param parsing bugs, and SSR streaming crashes.
Use when implementing file-based routing patterns, building SPAs with TypeScript routing, or troubleshooting devtools dependency errors, type safety issues, Vite bundling problems, or Docker deployment issues.
majiayu000/claude-skill-registry 163
-
orchardcore-background-tasks
Skill for creating background tasks and scheduled jobs in Orchard Core. Covers IBackgroundTask implementation, scheduling configuration, and background service patterns.
majiayu000/claude-skill-registry 163
-
minimax
Custom skill for minimax
majiayu000/claude-skill-registry 163
-
V3 Performance Optimization
Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.
majiayu000/claude-skill-registry 163
-
things-mac
Things 3: task management, projects, areas, deadlines, repeating tasks, Things Cloud, URL scheme
majiayu000/claude-skill-registry 163
-
prompt
Use when the user asks to create, refine, evaluate, or optimize an LLM prompt. Do NOT trigger for Claude Code skills (use skill-creator) or when rewriting an existing skill (use transformer). Example triggers - "write a prompt for my summarizer", "tighten this system prompt", "evaluate this agent prompt".
majiayu000/claude-skill-registry 163
-
skill-bootstrap
Bootstrap new skills quickly from natural language descriptions. Use when you need to create a new skill fast, generate utility capabilities, or scaffold documentation. For critical discipline-enforcing skills, follow up with skill-hardening. Triggers on "create skill", "bootstrap skill", "new skill", "generate skill".
majiayu000/claude-skill-registry 163
-
postgres-patterns
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
majiayu000/claude-skill-registry 163
-
writing-design-documents
Use when adapting requirements to system-specific design during Phase 2 - interactive whiteboard workflow, design decisions with rationale, and MVP-filtered architecture evaluation
majiayu000/claude-skill-registry 163
-
weather-svg-creator
Creates an SVG weather card showing the current temperature for Dubai. Writes the SVG to orchestration-workflow/weather.svg and updates orchestration-workflow/output.md.
majiayu000/claude-skill-registry 163
-
marketing-psychology
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.
majiayu000/claude-skill-registry 163
-
weather-fetcher
Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API
majiayu000/claude-skill-registry 163