ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
managing-agent-skills
Creates, analyzes, updates, and improves Claude Code agent skills including YAML frontmatter, allowed-tools field, progressive disclosure, and skill authoring workflows. Use when user asks how skills work, what agent skills are, explaining skill concepts, understanding SKILL.md structure, describing .md files organization, skill authoring process, asked to create a new skill, evaluate existing skills for improvements, optimize skills for AI/Claude effectiveness, suggest converting current logic into a skill, update outdated skill information, or when user mentions skill validation, best practices, supporting files, skill security, API integration, or technical architecture.
majiayu000/claude-skill-registry 163
-
extracting-code-structure
Extracts file structure (functions, classes, exports) efficiently without reading entire files, using ast-grep, Dart/Flutter analyzer, ctags, or other language-specific tools to get outlines and signatures. Use this skill when listing all methods, functions, or classes in a file, exploring unfamiliar code, getting API overviews, or deciding what to read selectively
majiayu000/claude-skill-registry 163
-
analyze_repo_capabilities
Detect repo tooling and patterns, then record a dynamic manifest.
majiayu000/claude-skill-registry 163
-
Puzzle Fetcher
Download and parse Advent of Code puzzles using aoc-cli. Extracts examples, expected outputs, and problem requirements from puzzle descriptions. Use when needing to fetch AoC puzzles, parse puzzle examples, or when user mentions downloading or reading AoC puzzle data.
majiayu000/claude-skill-registry 163
-
hover-interactions
Use when creating mouse hover effects - button highlights, card lifts, link underlines, image zooms, or any pointer-triggered animation.
majiayu000/claude-skill-registry 163
-
memory-management-optimization
Debug memory leaks, profile memory usage, optimize allocations. Use when heap grows unexpectedly, OOM errors occur, or profiling shows memory bottleneck. Covers C++ (Valgrind, ASAN, RAII), Python (tracemalloc, objgraph), and general patterns.
majiayu000/claude-skill-registry 163
-
api-rest-design
Apply when designing RESTful APIs, defining endpoints, HTTP methods, status codes, and response formats.
majiayu000/claude-skill-registry 163
-
sentry-rate-limits
Manage Sentry rate limits and quota optimization.
Use when hitting rate limits, optimizing event volume,
or managing Sentry costs.
Trigger with phrases like "sentry rate limit", "sentry quota",
"reduce sentry events", "sentry 429".
majiayu000/claude-skill-registry 163
-
detecting-type-confusion
Detects type confusion vulnerabilities by identifying unsafe type casts, vtable corruption, and polymorphism issues. Use when analyzing object-oriented code, type casting, or investigating C++ memory safety issues.
majiayu000/claude-skill-registry 163
-
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.
majiayu000/claude-skill-registry 163
-
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
majiayu000/claude-skill-registry 163
-
FastAPI Endpoint Builder
Create secure FastAPI routes for task CRUD with search/filter/sort query params and JWT auth when backend endpoints are needed
majiayu000/claude-skill-registry 163
-
video-download
YouTube等から動画をダウンロード。オフライン視聴、教育コンテンツ保存、クリエイティブ素材収集に使用。
majiayu000/claude-skill-registry 163
-
large-500-800ms
Use when building larger movement animations between 500-800ms - hero transitions, complex reveals, animations that tell a story and deserve attention
majiayu000/claude-skill-registry 163
-
swift-composable-architecture
The Composable Architecture (TCA) - A library for building Swift applications with state management, composition, and testability
majiayu000/claude-skill-registry 163
-
polars
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
majiayu000/claude-skill-registry 163
-
crafting-instructions
Generate optimized instructions for Claude (Project instructions, Skills, or standalone prompts). Use when users request creating project setups, writing effective prompts, building Skills, or need guidance on instruction types for Claude.ai.
majiayu000/claude-skill-registry 163
-
pydantic-ai-agent-creation
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
majiayu000/claude-skill-registry 163
-
code-implementer
Implements production code for PHP/CakePHP applications based on functional design specifications
majiayu000/claude-skill-registry 163
-
env-config
Implement environment variable management with .env files, validation, and environment-specific configs. Use when setting up configuration, handling secrets, or managing different deployment environments.
majiayu000/claude-skill-registry 163
-
tunnel-debug
隧道调试技能。诊断和排查隧道连接问题，包括连接失败、数据传输异常、性能问题等。关键词：调试、排查、诊断、问题、连接失败、超时。
majiayu000/claude-skill-registry 163
-
backend-instance-creator
Creates a permanent backend instance for Claude Imagine. Use this skill when the user wants to set up a new persistent backend server.
majiayu000/claude-skill-registry 163
-
agent-generator
ユーザーの責任範囲定義から、Agentのマークダウンファイルを生成する。エージェント作成時、プラグイン要素生成時、またはユーザーがエージェント定義、責任範囲、Agent生成、エージェントドキュメントに言及した際に使用する。
majiayu000/claude-skill-registry 163
-
embedded-thinking
提供嵌入式系统软硬件协同思考框架，涵盖硬件层、软件架构、资源约束、实时性、测试调试五大维度。当需要设计嵌入式应用、评审物联网系统、或需要全局视角审视 MCU/MPU 与软件配合时使用。支持裸机/RTOS 选型、功耗优化、内存预算、中断响应、OTA 升级等嵌入式特有场景决策。
majiayu000/claude-skill-registry 163