Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
databricks-app-python
Build Python-based Databricks applications using Dash, Streamlit, or Flask.
majiayu000/claude-skill-registry 163
-
test-parallel-b
Child B for parallel test
majiayu000/claude-skill-registry 163
-
scanning-database-security
This skill enables Claude to perform comprehensive database security scans using the database-security-scanner plugin. It is triggered when the user requests a security assessment of a database, including identifying vulnerabilities like weak passwords, SQL injection risks, and insecure configurations. The skill leverages OWASP guidelines to ensure thorough coverage and provides remediation suggestions. Use this skill when the user asks to "scan database security", "check database for vulnerabilities", "perform OWASP compliance check on database", or "assess database security posture". The plugin supports PostgreSQL and MySQL.
majiayu000/claude-skill-registry 163
-
claude-code-history-files-finder
Finds and recovers content from Claude Code session history files. This skill should be used when searching for deleted files, tracking changes across sessions, analyzing conversation history, or recovering code from previous Claude interactions. Triggers include mentions of "session history", "recover deleted", "find in history", "previous conversation", or ".claude/projects".
majiayu000/claude-skill-registry 163
-
when-reviewing-pull-request-orchestrate-comprehensive-code-review
Use when conducting comprehensive code review for pull requests across multiple quality dimensions.
Orchestrates 12-15 specialized reviewer agents across 4 phases using star topology coordination.
Covers automated checks, parallel specialized reviews (quality, security, performance, architecture,
documentation), integration analysis, and final merge recommendation in a 4-hour workflow.
majiayu000/claude-skill-registry 163
-
rag-pipeline-builder
Designs retrieval-augmented generation pipelines for document-based AI assistants. Includes chunking strategies, metadata schemas, retrieval algorithms, reranking, and evaluation plans. Use when building "RAG systems", "document search", "semantic search", or "knowledge bases".
majiayu000/claude-skill-registry 163
-
Python Flynt F-String Converter
Use flynt to convert old Python string formatting to f-strings. Activate when: (1) Converting %-formatting to f-strings, (2) Converting .format() calls to f-strings, (3) Modernizing string concatenation to f-strings, (4) Improving code readability through f-string adoption, or (5) Batch-converting legacy Python codebases.
majiayu000/claude-skill-registry 163
-
google-trends-ath-detector
專注於 Google Trends 數據擷取與分析，使用 Selenium 模擬真人瀏覽器行為抓取數據，自動判定搜尋趨勢是否創下歷史新高（ATH）或出現異常飆升，並提供訊號分型（季節性/事件驅動/結構性轉變）。
majiayu000/claude-skill-registry 163
-
learning-literature-review
literature-review for evidence-based learning research and evaluation.
majiayu000/claude-skill-registry 163
-
structuring-avalonia-projects
Guides the design of AvaloniaUI solution and project structures. Use when creating new AvaloniaUI solutions or organizing projects following naming conventions and layer separation.
majiayu000/claude-skill-registry 163
-
android-workflow-production
Generate GitHub Actions workflows for production deployment with staged rollout
majiayu000/claude-skill-registry 163
-
conversion-optimization
Optimize sales page architecture, offer positioning, pricing strategy, urgency mechanics, and checkout flow for maximum conversion.
majiayu000/claude-skill-registry 163
-
managing-loading-optimization
Advanced code-splitting and lazy-loading techniques. Use to reduce initial bundle size and speed up the homepage.
majiayu000/claude-skill-registry 163
-
nanogpt
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
majiayu000/claude-skill-registry 163
-
refine-prompts
Refine vague or unclear prompts into precise, actionable instructions. Use when user asks to clarify or improve instructions or when input is vague. Not for already clear prompts or simple questions.
majiayu000/claude-skill-registry 163
-
social-media
Social media marketing with campaign analysis, platform strategies, and engagement metrics. Use for social presence building, campaign tracking, and ROI analysis. Based on alirezarezvani/claude-skills.
majiayu000/claude-skill-registry 163
-
windows-xaml-developer
Expert guidance on building modern Windows apps with WinUI 3, WPF, and the MVVM pattern.
majiayu000/claude-skill-registry 163
-
klingai-install-auth
Execute set up Kling AI API authentication and configure API keys. Use when starting a new Kling AI
integration or troubleshooting auth issues. Trigger with phrases like 'kling ai setup',
'klingai api key', 'kling ai authentication', 'configure klingai'.
majiayu000/claude-skill-registry 163
-
documenting-domains
コードベース分析からドメインドキュメントを生成
majiayu000/claude-skill-registry 163
-
aerospace-expert
Expert-level aerospace systems, flight management, maintenance tracking, aviation safety, and aerospace software
majiayu000/claude-skill-registry 163
-
agent-command-authoring
Create Claude Code slash commands and OpenCode command files that delegate to subagents. Use when creating new commands or refactoring existing ones to follow the delegation pattern.
majiayu000/claude-skill-registry 163
-
devkit-verify-skill
Validates a skill against DevKit standards (requirements, template, dependencies)
majiayu000/claude-skill-registry 163
-
docs
Documentation workflow for website/ directory, Docusaurus, MDX snippets, i18n localization. Use when editing docs/, creating documentation pages, or updating WEBSITE_DOCS.md.
majiayu000/claude-skill-registry 163
-
ultrathink-detective
⚡ PRIMARY TOOL for: 'comprehensive audit', 'deep analysis', 'full codebase review', 'multi-perspective investigation', 'complex questions'. Combines ALL detective perspectives (architect+developer+tester+debugger). Uses Opus model. REPLACES grep/glob entirely. Uses claudemem v0.3.0 AST with ALL commands (map, symbol, callers, callees, context). GREP/FIND/GLOB ARE FORBIDDEN.
majiayu000/claude-skill-registry 163