Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
go-dev-guidelines
This skill should be used when writing, refactoring, or testing Go code. It provides idiomatic Go development patterns, TDD-based workflows, project structure conventions, and testing best practices using testify/require and mockery. Activate this skill when creating new Go features, services, packages, tests, or when setting up new Go projects.
majiayu000/claude-skill-registry 163
-
ruff-linter
Pythonコードのリンタ、フォーマッタ、コードレビュー。Pythonファイル(.py)を編集・作成・修正した後に必ず実行する。ruffによる品質チェックとフォーマット、さらにコードレビューを行い問題があれば修正する。
majiayu000/claude-skill-registry 163
-
jj-conflicts
Help users identify, understand, and resolve conflicts in jj repositories. Use when user mentions 'conflict', 'resolve conflicts', 'merge conflict', 'conflicted commits', '2-sided conflict', or encounters conflict-related errors.
majiayu000/claude-skill-registry 163
-
langchain-orchestration
Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration
majiayu000/claude-skill-registry 163
-
matlab-performance-optimizer
Optimize MATLAB code for better performance through vectorization, memory management, and profiling. Use when user requests optimization, mentions slow code, performance issues, speed improvements, or asks to make code faster or more efficient.
majiayu000/claude-skill-registry 163
-
antipattern-catalog
Document technical debt, anti-patterns, and patterns to avoid from analyzed frameworks. Use when (1) creating a "Do Not Repeat" list from framework analysis, (2) categorizing observed code smells and issues, (3) assessing severity of architectural problems, (4) generating remediation suggestions, or (5) synthesizing lessons learned across multiple frameworks.
majiayu000/claude-skill-registry 163
-
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
majiayu000/claude-skill-registry 163
-
activations
Query activation logs to check for errors and view volume
majiayu000/claude-skill-registry 163
-
wsr-generator
Generate professional weekly status report entries from git history and Azure DevOps activity.
Use when asked for: wsr, status, weekly report, status entry, what did I complete,
status update, generate report, weekly summary, send wsr, send status.
Requires: azure-devops skill configured (.ado/config.json), git repository.
majiayu000/claude-skill-registry 163
-
creating-bookmarklets
Creates browser-executable JavaScript bookmarklets with strict formatting requirements. Use when users mention bookmarklets, browser utilities, dragging code to bookmarks bar, or need JavaScript that runs when clicked in the browser toolbar.
majiayu000/claude-skill-registry 163
-
Content Personalization
Adapts textbook content complexity based on user's software/hardware background to optimize learning experience.
majiayu000/claude-skill-registry 163
-
dotnet-run-file
Run script-like CSharp programs using dotnet run file.cs. Use this skill when users want to execute CSharp code directly, write one-liner scripts via stdin, or learn about run file directives.
majiayu000/claude-skill-registry 163
-
docstring
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
majiayu000/claude-skill-registry 163
-
memcached-config-helper
Memcached Config Helper - Auto-activating skill for Backend Development.
Triggers on: memcached config helper, memcached config helper
Part of the Backend Development skill category.
majiayu000/claude-skill-registry 163
-
Plugin Management
Use when the user wants to list, configure, update, or remove installed Claude Code plugins
majiayu000/claude-skill-registry 163
-
expert-panel
Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.
majiayu000/claude-skill-registry 163
-
senior-ios
Native iOS development expertise for Swift 5.9+, SwiftUI, UIKit, and Apple ecosystem integration. Covers modern concurrency, architecture patterns, App Store submission, and Xcode workflows. Use when building iOS-specific features, migrating to SwiftUI, optimizing performance, or submitting to App Store.
majiayu000/claude-skill-registry 163
-
streaming
Server-Sent Events (SSE) streaming for Claude API with support for text, tool use, and extended thinking. Activate for real-time responses, stream handling, and progressive output.
majiayu000/claude-skill-registry 163
-
editorial-calendar
Use when structuring pillar calendars, approvals, and cadence governance.
majiayu000/claude-skill-registry 163
-
presentation-reviewer
Cette skill devrait être utilisée pour réviser des présentations PowerPoint selon les standards de conseil (McKinsey, BCG), avec analyse de la structure, clarté, design, storytelling et conformité DSFR. Utiliser quand l'utilisateur demande une révision, analyse ou amélioration de présentation, avec ajout de commentaires directement dans les slides.
majiayu000/claude-skill-registry 163
-
summoner
Multi-agent orchestration skill for complex tasks requiring coordination, decomposition, and quality control. Use for large implementations, refactoring projects, multi-component features, or work requiring multiple specialized agents. Excels at preventing context bloat and ensuring SOLID principles. Integrates with oracle, guardian, and wizard.
majiayu000/claude-skill-registry 163
-
update-component-reference
This skill should be used when the user wants to add components (commands, agents, skills, hooks, or MCP servers) to the Component Reference section of the website.
majiayu000/claude-skill-registry 163
-
quality-code-check
Code quality validation through linting, type checking, and build verification.
Multi-language support for automated quality gates.
Use when validating code quality:
- After implementation to validate code meets standards
- Before creating pull requests or commits
- When debugging build/type/lint issues
- User explicitly requests quality checks
Provides language-specific tool commands and validation workflows for:
- JavaScript/TypeScript (ESLint, tsc, build tools)
- Python (Ruff, MyPy, Pyright)
- Go (golangci-lint, go build)
- Rust (Clippy, cargo check/build)
- Java (Gradle, Maven)
Focuses on detecting issues early through systematic automated checks.
majiayu000/claude-skill-registry 163
-
Shodan Reconnaissance and Pentesting
This skill should be used when the user asks to "search for exposed devices on the internet," "perform Shodan reconnaissance," "find vulnerable services using Shodan," "scan IP ranges with Shodan," or "discover IoT devices and open ports." It provides comprehensive guidance for using Shodan's search engine, CLI, and API for penetration testing reconnaissance.
majiayu000/claude-skill-registry 163