Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
layer-architect
레이어 아키텍트. 기능을 헥사고날 레이어에 매핑. 기존 코드 영향도 분석.
수정 vs 신규 판단 (TDD vs Doc-Driven 분기). Serena MCP 검색 활용.
/plan 명령 시 자동 활성화. 구현 순서 및 전략 결정.
majiayu000/claude-skill-registry 163
-
alfworld-object-locator
This skill scans the current environment observation to identify the presence and location of a target object needed for a task. It should be triggered when the agent's goal requires an object that is not currently in the agent's inventory, and the observation does not explicitly state where the object is. The skill analyzes the textual observation to find receptacles that likely contain the target, based on common sense or domain knowledge (e.g., a 'dishsponge' might be on a 'cart'), and outputs the identified target receptacle location for navigation.
majiayu000/claude-skill-registry 163
-
mem0-sync
Auto-sync session context, decisions, and patterns to Mem0 for cross-session continuity
majiayu000/claude-skill-registry 163
-
data-normalization-tool
Process data normalization tool operations. Auto-activating skill for ML Training.
Triggers on: data normalization tool, data normalization tool
Part of the ML Training skill category. Use when working with data normalization tool functionality. Trigger with phrases like "data normalization tool", "data tool", "data".
majiayu000/claude-skill-registry 163
-
uniprot-database
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.
majiayu000/claude-skill-registry 163
-
Python Pyupgrade Syntax Modernizer
Use pyupgrade to automatically upgrade Python syntax to newer versions. Activate when: (1) Migrating code from Python 2 to 3, (2) Removing deprecated syntax like 'class Foo(object)', (3) Converting old-style string formatting to f-strings, (4) Updating type hints to modern union syntax (X | Y), (5) Removing obsolete __future__ imports, or (6) Upgrading to a newer Python minimum version.
majiayu000/claude-skill-registry 163
-
typescript-lsp
REQUIRED for searching code in *.ts, *.tsx, *.js, *.jsx files. Use INSTEAD of Grep for TypeScript/JavaScript - provides type-aware symbol search that understands imports, exports, and relationships. Activate before reading, editing, or searching TypeScript code to verify signatures and find references.
majiayu000/claude-skill-registry 163
-
qa-check
PR作成前の品質保証チェックを実行します。Lint、テスト、ビルド、カバレッジ確認を自動で行い、合格/不合格を判定します。フロントエンドのみ、バックエンドのみ、または両方のチェックが可能です。
majiayu000/claude-skill-registry 163
-
write-reference
Create information-oriented documentation for lookup and reference. PROACTIVELY activate for: (1) API documentation, (2) configuration reference, (3) glossaries and terminology, (4) technical specifications, (5) parameter documentation. Triggers: "write reference", "create reference docs", "API documentation", "config reference", "document parameters", "glossary", "specification"
majiayu000/claude-skill-registry 163
-
sales-email-sequence
Create high-converting email sequences for sales, launches, and nurture campaigns. Use when the user needs email sequences, drip campaigns, launch emails, or automated email workflows.
majiayu000/claude-skill-registry 163
-
dialogue-verify-logging-compliance
Verify that required logging occurred during a process execution. Use before presenting work for approval to ensure decisions and observations were captured. Triggers on "verify logging", "check compliance", "validate logs".
majiayu000/claude-skill-registry 163
-
voice-ai-development
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice.
majiayu000/claude-skill-registry 163
-
nextjs-shadcn
Creates Next.js 16 frontends with shadcn/ui. Use when building React UIs, components, pages, or applications with shadcn, Tailwind, or modern frontend patterns.
majiayu000/claude-skill-registry 163
-
ruby-on-rails-development
Rails skills router and knowledge base. Routes your request to the appropriate specialist skill. Contains core Rails principles and conventions. Use when unsure which specialist to choose or for general Rails questions.
majiayu000/claude-skill-registry 163
-
seo_technical
Performs technical SEO audits covering site speed, crawlability, indexability, mobile-friendliness, security, and structured data. Identifies technical issues preventing optimal search performance.
majiayu000/claude-skill-registry 163
-
ops-safety
当用户执行系统级命令（sysctl、iptables、systemctl、Docker 配置、数据库 DDL）或进行服务器运维操作时触发。提供运维安全规范。
majiayu000/claude-skill-registry 163
-
rag-skills
RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.
majiayu000/claude-skill-registry 163
-
pdf-reader
Read and extract content from PDF files using multiple methods.
LOAD THIS SKILL WHEN: User says "讀取 PDF", "read PDF", "打開論文", "看這篇" | has PDF file path | needs to extract text from PDF.
CAPABILITIES: PDF to markdown conversion, text extraction, figure detection, citation extraction.
majiayu000/claude-skill-registry 163
-
cm
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture transforms scattered sessions into persistent, cross-agent learnings with confidence decay, anti-pattern learning, and scientific validation.
majiayu000/claude-skill-registry 163
-
redis-integration
Redis and Upstash Vector integration patterns for rate-limiting, vector search, embeddings, and memory systems. Use when implementing caching, rate-limiting, or semantic search features.
majiayu000/claude-skill-registry 163
-
testing-ai-agents
Use when testing AI agent code with pytest. Covers TDD for agent APIs, mocking LLM calls (NOT evaluating LLM outputs), pytest-asyncio patterns, FastAPI testing with httpx, SQLModel testing, and agent tool testing. NOT for evaluating LLM reasoning quality (use evals skill).
majiayu000/claude-skill-registry 163
-
linkhub-wrap
LinkHub 세션 마무리. 문서 업데이트 분석, 후속 작업 제안, 학습 내용 정리.
majiayu000/claude-skill-registry 163
-
couple-weekly-report
Generate weekly relationship health report showing affect ratios and repair rates for both partners across 3 weeks (current + 2 prior) with message quotes.
majiayu000/claude-skill-registry 163
-
gameday-planning
Use when planning GameDay exercises, designing failure scenarios, or conducting chaos drills. Covers GameDay preparation, execution, and follow-up.
majiayu000/claude-skill-registry 163