Discover Databases skills, compare source repositories and read the instructions for each workflow.
Researches implementation approaches using browser automation via /chrome, then implements the best solution. Use when building new features, solving unfamiliar problems, or need to find best practices before i...
Initialize Claude skills in the current project and verify setup. Use when user says '/init-skills', 'setup skills', 'install skills', or 'add Claude skills to this project'. Can also review and verify existing...
Execute 1-2+ hour tasks autonomously with minimal supervision. Requires Task Contract (OUTCOME, EXCLUSIONS, DURATION, GUARDRAILS) upfront, then executes with clarification → plan → autonomous work → session rep...
Implements Stripe payments correctly the first time. Handles checkout sessions, webhooks, subscriptions, and customer management following Stripe best practices.
Reset after failures, blockers, or when stuck. Use when execution hits a wall, something breaks, or we need to step back and reassess. This is the fifth system in the 5-system framework.
Explains code in beginner-friendly terms. Use when user asks 'what does this do', 'how does this work', 'explain this code', or needs to understand generated code. Breaks down complex code into simple explanati...
Performs a fast, focused code review checking for common issues, security vulnerabilities, and best practices without over-engineering. Optimized for cost-efficiency by targeting specific concerns rather than b...
Search conversation history for research context - papers discussed, citations analyzed, discoveries made, or questions explored.
Systematic deep research through discovery sources, vault, and web - refine query, collect papers, analyze, synthesize findings into comprehensive markdown report.
Guide users through creating effective research questions for automated paper discovery. Use when user wants to set up automated paper discovery or create new search queries.
Collaboratively create and refine new skills through iterative design - validate needs, design structure, draft content, test, and refine.
Defragment and clean research agent memory - consolidate paper info, organize research domains, remove redundancy from research tracking.
Set up effective automated discovery - from vague idea to working system in one streamlined conversation.
Provides expertise in converting Figma designs to HTML/CSS using Figma MCP tools, with data attributes for content tracking and comprehensive analysis. Use when converting Figma designs to web code.
Validates prompt files against best practices. Use after creating or editing rules, skills, agents, commands in .agents/ for quality review.
Extracts interaction specifications from Figma designs (hover states, transitions, animations, triggers). Updates the "インタラクション" section in screen spec.md.
Initializes and updates screen specification documents. Use as a foundation skill for all screen documentation workflows.
Compares Figma screenshots with HTML screenshots using pixel-level analysis. Use when verifying visual accuracy of Figma-to-HTML conversion.
Provides code review expertise with constructive feedback. Use when conducting self-reviews before PR creation, quality checks, or best practice validation.
Maps HTML content elements to API response fields and generates data binding specifications. Updates the "APIマッピング" section in screen spec.md.
Generates TDD-ready acceptance criteria from screen spec.md. Extracts requirements from features, interactions, flows, and API mappings in Given-When-Then format. Use when creating implementation task specifica...
Documents screen-to-screen navigation flows, user journeys, and state transitions across multiple screens. Updates the "画面フロー" section in screen spec.md.
Refines screen spec.md by incorporating details from specification documents. Use when enhancing existing screen specifications with business logic, component details, and validation results.
Extracts and documents design tokens (colors, typography, spacing, shadows, etc.) from Figma designs. Updates the "デザイントークン" section in screen spec.md.
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.