Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
repo-navigator
Navigate and map this monorepo structure. Find files, packages, and dependencies. Use when asked to locate code, understand package relationships, find where something is defined, or explore repo structure.
majiayu000/claude-skill-registry 163
-
agent-csharp-developer
Expert C# developer specializing in modern .NET development, ASP.NET Core, and cloud-native applications. Masters C# 12 features, Blazor, and cross-platform development with emphasis on performance and clean architecture.
majiayu000/claude-skill-registry 163
-
green-mirage-audit
Use when reviewing test suites, after test runs pass, or when user asks about test quality - performs exhaustive line-by-line audit tracing code paths through entire program, verifying tests actually validate what they claim. Outputs structured report compatible with fix-tests skill.
majiayu000/claude-skill-registry 163
-
GDScript Format
Format and lint GDScript files using gdscript-formatter. Use after editing GDScript files to ensure code style consistency.
majiayu000/claude-skill-registry 163
-
claude-md-sync
CLAUDE.md にプロジェクトの現在の状態を反映する。
簡潔さを保ち、詳細ドキュメントへの参照で重複を避ける。
majiayu000/claude-skill-registry 163
-
tool-design
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.
majiayu000/claude-skill-registry 163
-
kotlin-spring-boot
Kotlin/Spring Boot 3.x patterns - use for backend services, REST APIs, dependency injection, controllers, and service layers
majiayu000/claude-skill-registry 163
-
bootstrap
majiayu000/claude-skill-registry 163
-
infrastructure-verification
Verify AWS infrastructure configuration before deployment. Use when validating VPC endpoints, NAT Gateway capacity, security groups, or debugging network path issues that cause Lambda connection timeouts.
majiayu000/claude-skill-registry 163
-
ha-emby-github
Use for ALL GitHub operations on this project - covers project board queries, issue management, PR linking, commit formatting, and the VIOLATION rule. Required reading before any code changes.
majiayu000/claude-skill-registry 163
-
analyzing-codebases
Generates LLM-optimized code context with function call graphs, side effect detection, and incremental updates. Processes JavaScript/TypeScript codebases to create compact semantic representations including multi-level summaries, entry point identification, and hash-based change tracking. Provides 74-97% token reduction compared to reading raw source files. Useful for understanding code architecture, debugging complex systems, reviewing pull requests, and onboarding to unfamiliar projects.
majiayu000/claude-skill-registry 163
-
generating-output-styles
Creates custom output styles for Claude Code that modify system prompts and behavior. Use when the user asks to create output styles, customize Claude's response format, generate output-style files, or mentions output style configuration.
majiayu000/claude-skill-registry 163
-
review-architecture
アーキテクチャレビュースキル（設計整合性、コーディング規約、ドキュメント整合性の確認）
majiayu000/claude-skill-registry 163
-
dual-mode-library
Use when building reusable PyPI package with pgdbm - provides complete pattern for libraries that work standalone or embedded without needing examples
majiayu000/claude-skill-registry 163
-
research-and-fact-checker
Performs accurate research and fact-checking using reliable sources. Ideal for validating claims, clarifying complex topics, summarizing findings, and ensuring information accuracy.
majiayu000/claude-skill-registry 163
-
snapshot-test-refactorer
Refactors brittle snapshot tests into resilient, focused assertions. Provides strategies for reducing snapshot size, extracting meaningful assertions, and maintaining snapshots. Use for "snapshot testing", "snapshot refactoring", "brittle tests", or "assertion improvement".
majiayu000/claude-skill-registry 163
-
incremental-development
Structured incremental development workflow that enforces explicit scoping before implementation. Use when: (1) User says 'build', 'implement', 'develop', 'create feature', or 'add functionality', (2) Task involves multiple files or could have ripple effects, (3) User wants to avoid scope creep or premature implementation, (4) Breaking down complex tasks into verifiable steps. This skill prevents AI agents from jumping into code without a validated plan.
majiayu000/claude-skill-registry 163
-
refactoring-07-documentation-usage
Use when documenting Python research code usage, setup, and experiment reproduction.
majiayu000/claude-skill-registry 163
-
execute-tasks
majiayu000/claude-skill-registry 163
-
write_adr
Document architectural decisions with context and consequences.
majiayu000/claude-skill-registry 163
-
flutter
majiayu000/claude-skill-registry 163
-
skill-authoring
Create or update project-specific skills in this repo. Use when asked to make new skills, modularize workflows, or build skill packs for this codebase.
majiayu000/claude-skill-registry 163
-
stanley-druckenmiller-investment
スタンレー・ドラッケンミラーの投資哲学と戦略に基づいた投資アドバイスを提供。30年間無敗、年率30%近いリターンを達成した伝説的投資家の思考法を活用し、マクロ経済分析、リスク管理、ポジション構築、市場サイクルの読み方などについて実践的な指導を行う。投資判断、市場分析、リスク管理、ポートフォリオ構築などの相談時に使用。
majiayu000/claude-skill-registry 163
-
agentuity-cli-dev
Build and run the development server
majiayu000/claude-skill-registry 163