研究

PRIMARY tool for fetching library/framework documentation. PROACTIVELY use instead of WebFetch/WebSearch when user requests docs, API references, setup guides, or code examples for any programming library or framework. Use this skill immediately when detecting queries like "show me X docs", "how do I use Y", "get Z documentation", etc. Token-efficient alternative to MCP servers.

ユーザーリサーチと行動分析を支援します。ユーザビリティテスト、UXレビュー、フィードバック分析、ジャーニーマップ作成、ペルソナ定義を提供します。ユーザー理解深化、UX改善、フィードバック分析が必要な場合に使用してください。

Research the codebase to find and explain specific topics

Convert Markdown documents to professional PDF files with syntax highlighting, custom templates, and BibTeX citations. Use when creating printable documents, reports, or academic papers from Markdown.

A/B testing patterns for lead generation sites. Client-side experiments, Google Optimize alternative, analytics integration. Use for conversion optimization.

Autonomous web research for presentation topics using Claude Agent SDK. Conducts multi-step research, extracts insights, and manages citations.

Bayesian optimization partner for materials science experiments using Meta Ax. Use when researchers want to optimize material properties, formulations, or process parameters. Supports (1) Composite formulation optimization, (2) 3D printing parameter tuning, (3) Alloy composition design, (4) Any black-box optimization with continuous/categorical parameters. Handles the full workflow - setup experiments, suggest trials, validate feasibility with researcher, track results in git, generate visualizations.

Create, manage, scan, update, and clean up git worktrees for parallel development with protected branch safeguards. Use when working on multiple branches simultaneously, isolating experiments, updating protected branches (main/develop), or when user mentions "worktree", "parallel branches", "feature isolation", "branch cleanup", "worktree status", or "update main/develop".

Standard Operating Procedure for /specify phase. Covers classification, research depth, clarification strategy, and roadmap integration.

Search arXiv papers via MCP server. For psychological recovery research, deprogramming, trauma undoing - inverted for AI healing.

Use when researching GitHub issues, PRs, and discussions for community solutions and known gotchas - searches via WebSearch with site filters and extracts problem-solution patterns

This skill should be used when creating, editing, or debugging Mermaid diagrams. It provides comprehensive syntax references for all 20+ Mermaid diagram types including flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and more. Use this skill when users ask for diagrams, visualizations, flowcharts, or any Mermaid-related assistance.

Conduct systematic research with confidence scoring, source validation, and structured reporting for technology decisions and codebase analysis. Use for complex research tasks, technology selection, or best practice discovery.

Create and maintain high-quality Claude Code Skills through interactive discovery, web research, and comprehensive description writing standards. Use when building new Skills, researching latest best practices, updating existing Skills, writing skill descriptions with proper trigger keywords, or generating Skill packages backed by official documentation and real-world examples.

Orchestrate the complete LA-Bench experimental procedure generation workflow from JSONL input to validated output. This skill should be used when processing LA-Bench format experimental data to generate and validate detailed experimental procedures. It coordinates parsing, reference fetching, procedure generation, and quality validation with 10-point scoring.

Self-reference guide for Claude Code's own architecture, configuration, and extension points. Use when needing to know where Claude Code stores its configuration files, skills, plugins, hooks, MCP servers, settings, or any other internal structure. Triggers on questions like "where do skills go?", "how do I configure hooks?", "where is the settings file?", or when creating/modifying Claude Code extensions.

Execute project release workflows by locating and following project-specific RELEASE_GUIDE.md in the repository root or docs/. Use when asked to perform a release, publish a release, cut a tag, run release steps, or when a user references RELEASE_GUIDE.md.

Apply a Research → Plan → Implement → Validate workflow with Copilot CLI, including context budgeting and persistent artifacts via /share.

Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.

Curated project templates that guide feature-dev Phase 3 questions with research-backed technology choices. Provides standardized options for common project types (SaaS API, ML Service, CLI Tool, Full-Stack). Use when starting new projects or when feature-dev needs structured decision guidance. Do NOT use for existing projects with established stacks - analyze existing code instead.