Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
arcanea-revision-ritual
Transform rough drafts into polished work through systematic revision. Multiple passes, specific focus, and the discipline to kill your darlings. The alchemical process of making good work great.
majiayu000/claude-skill-registry 163
-
video-subtitle
동영상에서 자막을 자동 생성하고 발표자료 기반으로 교정하는 스킬.
"자막 생성", "영상 자막", "STT", "subtitle" 요청에 사용.
mlx-whisper로 추출 → 중복 정리 → 발표자료 기반 교정까지 자동화.
majiayu000/claude-skill-registry 163
-
programming-ruby
Best practices when developing in Ruby codebases
majiayu000/claude-skill-registry 163
-
tcr-repertoire-analysis-agent
majiayu000/claude-skill-registry 163
-
cli-interactive-testing
Test and validate DyGram machines using CLI interactive mode. Step through execution, provide intelligent responses, debug behavior, and create test recordings.
majiayu000/claude-skill-registry 163
-
percentile-analyzer
Analyze percentile analyzer operations. Auto-activating skill for Performance Testing.
Triggers on: percentile analyzer, percentile analyzer
Part of the Performance Testing skill category. Use when analyzing or auditing percentile analyzer. Trigger with phrases like "percentile analyzer", "percentile analyzer", "analyze percentile r".
majiayu000/claude-skill-registry 163
-
aptos-token-standards
Expert on Aptos token standards including fungible tokens (Coin, Fungible Asset), non-fungible tokens (Digital Asset standard, Token V1/V2), collections, metadata, minting, burning, and transfer patterns. Triggers on keywords token, nft, fungible asset, coin, digital asset, collection, mint, burn, metadata, royalty
majiayu000/claude-skill-registry 163
-
run-server
Start the Gambit game server on 0.0.0.0:1234. Use when the user wants to run just the server, test server functionality, or manually test with clients.
majiayu000/claude-skill-registry 163
-
zz-code-recon
Deep architectural context building for security audits. Use when conducting security reviews, building codebase understanding, mapping trust boundaries, or preparing for vulnerability analysis. Inspired by Trail of Bits methodology.
majiayu000/claude-skill-registry 163
-
create-commits-and-push
Creates atomic git commits and pushes to remote. Use when you want to commit changes and push without creating a PR (e.g., "commit and push my changes" or "push this up").
majiayu000/claude-skill-registry 163
-
mlx
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
majiayu000/claude-skill-registry 163
-
spring-boot
Provides comprehensive guidance for Spring Boot development including project creation, auto-configuration, dependency injection, web development, data access, security, testing, and deployment. Use when the user asks about Spring Boot, needs to create Spring Boot applications, configure Spring Boot, or implement Spring Boot features.
majiayu000/claude-skill-registry 163
-
board-readiness-kit
Narrative and artifact system for preparing SaaS board/investor updates.
majiayu000/claude-skill-registry 163
-
feed-reader
Aggregate news and social feeds to stay informed
majiayu000/claude-skill-registry 163
-
agent-selection
Systematic framework for selecting the optimal specialized agent for any task. Use when delegating to subagents via the Task tool to ensure the most appropriate specialist is chosen based on framework, domain, task type, and complexity. Applies decision tree logic to match tasks with agent expertise.
majiayu000/claude-skill-registry 163
-
complex-state-management
Production patterns for managing complex application state in React without Redux, Zustand, or other state libraries. Includes multi-stage loading, command patterns, refs for performance, and parallel data fetching. Use when building complex UIs with interconnected states, need loading stages and progress tracking, or implementing command patterns.
majiayu000/claude-skill-registry 163
-
fifteen-factor-app
The Fifteen-Factor App methodology for modern cloud-native SaaS applications. This skill should be automatically invoked when planning SaaS tools, product software architecture, microservices design, PRPs/PRDs, or cloud-native application development. Extends the original Twelve-Factor App principles with three additional factors (API First, Telemetry, Security). Trigger keywords include "fifteen factor", "12 factor", "SaaS architecture", "cloud-native design", "application architecture", "microservices best practices", or when in a planning/architecture session.
majiayu000/claude-skill-registry 163
-
file-operations
Analyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.
majiayu000/claude-skill-registry 163
-
maven-builder-for-foolish-language
Comprehensive Maven build strategies for mixed Java/Scala projects with parallel execution, intelligent test running, and targeted debugging workflows. Use this skill when user asks to build the project, run tests, compile code, clean build, run Maven commands, fix compilation errors, or analyze test failures. Automatically invoked for requests like "make a fresh build", "run all tests", "build and test", "clean and compile", or any Maven-related build tasks.
majiayu000/claude-skill-registry 163
-
Ad Copy Writer
Write high-converting advertising copy for paid media campaigns
majiayu000/claude-skill-registry 163
-
working-with-buildkite-builds
Use when working with Buildkite CI - checking status, investigating failures, and reproducing issues locally. Provides workflows for monitoring builds, progressive failure investigation, and local reproduction strategies. Use when tempted to use GitHub tools instead of Buildkite-native tools, or when a Buildkite tool fails and you want to fall back to familiar alternatives.
majiayu000/claude-skill-registry 163
-
using-generics
Teaches generic constraints, avoiding any in generic defaults, and mapped types in TypeScript. Use when creating reusable functions, components, or types that work with multiple types while maintaining type safety.
majiayu000/claude-skill-registry 163
-
supabase-evidence
Initialize and manage the evidence collection directory for professional security audits with documented proof of findings.
majiayu000/claude-skill-registry 163
-
bull-call-spread
Analyzes bull-call-spread debit spreads for bullish directional plays with defined risk. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting moderate price increase, comparing vertical spread configurations, analyzing debit spread opportunities, calculating Greeks for multi-leg positions, or evaluating defined-risk bullish strategies on liquid optionable securities.
majiayu000/claude-skill-registry 163