Explore AI skills for development, content, data and productivity. Compare the description and repository popularity before opening a skill.
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vuln...
Monitor codebase changes and generate standardized analysis documentation
Validates planning artifacts (spec.md, plan.md, data-model.md, contracts/) for quality, completeness, and consistency. Checks for mandatory sections, cross-artifact consistency, and constitution compliance. Alw...
This skill should be used when exporting, storing, or reapplying agent-browser cookies across sessions, especially for localhost login states.
This skill should be used when the user requests to audit, check, or improve application security by analyzing security headers, cookie configuration, RLS policies, input sanitization, rate limiting, and other...
This skill should be used when the user requests to generate, create, or add Row-Level Security (RLS) policies for Supabase databases in multi-tenant or role-based applications. It generates comprehensive RLS p...
Implement session-based authentication in FastAPI applications. Use when building login/logout flows, protecting endpoints with auth dependencies, creating user models with password hashing, managing sessions i...
Create Reference (REF) documents for conceptual models, glossaries, and catalogues. Triggers on "create reference", "document concepts", "make glossary", "catalogue these", "create lookup".
Create Theory (THY) documents that capture integrated understanding. Triggers on "capture theory", "document understanding", "write theory", "explain why this works", "record the mental model".
Master AI-powered natural language data exploration with Lumen AI. Use this skill when building conversational data analysis interfaces, enabling natural language queries to databases, creating custom AI agents...
Gather structured information from the user through framework-aware questioning. Use when you need to elicit process context, requirements, constraints, or decisions. Triggers on "gather requirements", "elicit...
Provide help with the Dialogue Framework. Triggers on "how does dialogue work", "what commands", "explain phases", "framework help", "what can you do".
This skill should be used when the user asks to 'ask the oracle', 'use the oracle', 'get a second opinion', 'consult oracle', 'deep analysis', or when facing difficult bugs, reviewing critical code, designing c...
Resolves framework reference IDs to their content. Use when you need to look up a document, decision, observation, task, or ADR by its ID. Triggers on "resolve reference", "look up THY-001", "find DEC-...", "ge...
Web research via Gemini CLI with Google Search grounding. Generates markdown report. Claude MUST append analysis section after. Use for real-time data: news, docs, code examples, fact verification.
AGENTS.md の整理・リファクタリングに特化。ユーザーが「agents.md を整理して」「AGENTS.md を更新して」などと言ったときに使う。各セッションで得た学びを汎用ルールとして AGENTS.md に反映するための提案を作成し、必ず...
This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthropic best practices, have proper structure, use current domain-specific patterns, and incl...
Guide systematic debugging through hypothesis generation, evidence collection, and verification. Uses scientific method for root cause analysis.
Research the codebase to find and explain specific topics, answering questions about architecture, configuration, data flows, and implementation details
Generate operational runbooks for services, procedures, or incident response with step-by-step procedures, troubleshooting guides, and escalation paths
Debug issues using systematic investigation
Show what's new in GSD
Workflow for systematic debugging
生成高质量的技术代码示例，支持多种编程语言和框架。使用时需要创建代码示例、演示用法、提供配置模板时。
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.