Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
multi-service-debug
多服务调试技能：针对 Vercel + GCP Cloud Run 混合架构的调试工作流。
Use when: 跨服务问题排查、日志聚合分析、服务间通信调试、生产环境故障定位。
Triggers: "调试", "debug", "日志", "logs", "错误", "error", "服务", "service", "通信", "超时", "timeout"
majiayu000/claude-skill-registry 163
-
linear-method
Linear's proven methodology for software development and project organization. Use when helping users plan work, create issues, structure projects, set direction, prioritize tasks, or organize development workflows. Applies Linear's principles of momentum, simplicity, and focus—not API integration. For solo developers and teams organizing software projects.
majiayu000/claude-skill-registry 163
-
dioxus-pwa-development
Build Progressive Web Apps with Dioxus framework. Use when developing Dioxus web applications, creating PWA features, or working with WASM targets.
majiayu000/claude-skill-registry 163
-
chat-assistant
Interactive developer assistant with tool access for codebase exploration
majiayu000/claude-skill-registry 163
-
workbench-work-items
Work item management for Workbench CLI. Use when creating, updating, linking, or closing work items and tracking execution status.
majiayu000/claude-skill-registry 163
-
apple-tv-troubleshooter
Expert troubleshooting for Apple TV (tvOS) React Native development. Use when users have issues with Siri Remote, focus management, TVEventHandler, TVFocusGuideView, ScrollView not scrolling, tvOS-specific problems, parallax animations, or tvOS vs Android TV differences.
majiayu000/claude-skill-registry 163
-
helloagents
用于处理软件开发/维护类请求（常见说法包括但不限于：修改、修复 bug、新增功能、开发模块、重构/优化、补充/编写/运行测试、生成并执行计划）。会自动判定是问答/改动/命令（~auto/~plan/~exec/~init），并选择咨询问答/微调/轻量迭代/标准开发/完整研发路径；需要写入时生成方案包（why/how/task）、执行与验证、同步知识库（helloagents/wiki、CHANGELOG、history/index），最终按统一输出格式汇总结果。
majiayu000/claude-skill-registry 163
-
biblical-exegesis-expert
Scholar of biblical interpretation covering Hebrew Bible and New Testament with historical-critical and literary methods
majiayu000/claude-skill-registry 163
-
moai-lang-c
C programming language patterns, memory management, and systems programming
majiayu000/claude-skill-registry 163
-
cpp-interface-purpose-comments
Add a standard Purpose comment above each pure virtual method declaration in C++ interface header files (.h/.hpp). Use when asked to batch annotate interface classes or enforce a consistent comment block above `virtual ... = 0;` declarations.
majiayu000/claude-skill-registry 163
-
mcp-chrome-devtools
This skill provides guidance for using Chrome DevTools MCP for browser debugging and automation. Use when debugging web pages, analyzing performance, inspecting network requests, viewing console messages, or interacting with Chrome DevTools features programmatically.
majiayu000/claude-skill-registry 163
-
virtual-environment-usage
Mandates the use of virtual environments for isolating project dependencies and ensuring reproducibility.
majiayu000/claude-skill-registry 163
-
audio-systems
Game audio systems, music, spatial audio, sound effects, and voice implementation.
Build immersive audio experiences with professional middleware integration.
majiayu000/claude-skill-registry 163
-
bio-restriction-fragment-analysis
Analyze restriction digest fragments using Biopython Bio.Restriction. Predict fragment sizes, get fragment sequences, simulate gel electrophoresis patterns, and perform double digests. Use when analyzing restriction digest fragment patterns.
majiayu000/claude-skill-registry 163
-
xcode-workflows
Xcode build system guidance for xcodebuild operations. Use when building iOS projects, running tests, analyzing build failures, or configuring schemes. Covers build/clean/test operations, interpreting xcodebuild output, and troubleshooting common build errors.
majiayu000/claude-skill-registry 163
-
invoice-generator
Generate professional PDF invoices from line items with customizable templates, tax calculations, and branding. Supports batch generation from CSV.
majiayu000/claude-skill-registry 163
-
tool-interface-analysis
Analyze tool registration, schema generation, and error feedback mechanisms in agent frameworks. Use when (1) understanding how tools are defined and registered, (2) evaluating schema generation approaches (introspection vs manual), (3) tracing error feedback loops to the LLM, (4) assessing retry and self-correction mechanisms, or (5) comparing tool interfaces across frameworks.
majiayu000/claude-skill-registry 163
-
compaction-advisor
Provides context-aware compaction guidance with intelligent checkpointing. Monitors context during long tasks and suggests checkpoints before compaction interrupts your work.
majiayu000/claude-skill-registry 163
-
new-scanner
Use this skill ONLY when creating a new data scanner (e.g., Twitter scanner, Bloomberg scanner). Do not use for agents or strategies.
majiayu000/claude-skill-registry 163
-
audit
Generate usage report for MiniMax and token optimization Use when: (1) /audit is invoked, (2) task relates to audit functionality.
majiayu000/claude-skill-registry 163
-
axios
Promise-based HTTP client for making requests from browser and Node.js
majiayu000/claude-skill-registry 163
-
openapi_docs
Generate comprehensive REST API documentation using SpringDoc OpenAPI 3.0 and Swagger UI in Spring Boot 3.x applications. Use when setting up API documentation, configuring Swagger UI, adding OpenAPI annotations, implementing security documentation, or enhancing REST endpoints with examples and schemas.
majiayu000/claude-skill-registry 163
-
copilotkit-pitch-deck
Production-ready CopilotKit pitch deck wizard in main application. Use when enhancing AI conversation features, optimizing Edge Function integration, debugging chat interface, or improving pitch deck generation flow. System is PRODUCTION READY (98/100).
majiayu000/claude-skill-registry 163
-
tool-connect
Connect to external tools via MCP (GitHub, databases, APIs)
majiayu000/claude-skill-registry 163