Full context reload. Use after /clear, after compaction, or at session start. Loads conversation history, indexes docs, maps code, scans configs, checks git. Gets you immediately helpful.
PDF-RAG API reference. REQUIRED after any failed curl/jq to localhost:8000 (404, null, jq error). Also use when uncertain about endpoint path or response shape.
生成AIが人間に対して行う作業開始時オンボーディング。AIが"説明係"ではなく"進行役"として、探索→仮説→検証→要約→未確定の明示を回し、人間が最小スキーマ（因果・境界・不変条件・壊れ方・観測）を短時間で再構築できる状態に導く。 トリガー条件: - 新しいタスクやコード変更に着手する前（「この機能を修正して」「このバグを直して」） - 未知のコードベースを理解する必要がある時 - 「オンボーディングして」「作業開始の準備をして」「コードを理解したい」 - 複雑なタスクを始める前の文脈理解が必要な時 - 「作戦ブリーフを作成して」「安全に始められるようにして」
Search and retrieve context from previous Ralph iteration transcripts. Use when you need detailed context about what happened in a previous iteration beyond what's in progress.txt. Triggers on: read transcript, previous iteration, what happened in, search transcripts.
Use when coordinating multiple AI agents for parallel work. Triggers: "multi-agent", "parallel agents", "agent coordination", "QuantumDAG", "conflict-free". NOT for: Single-agent operations or basic jj commands.
Complete RAG (Retrieval-Augmented Generation) pipeline implementation with document ingestion, vector storage, semantic search, and response generation. Supports FastAPI backends with OpenAI and Qdrant. LangChain-free architecture.
Manage Ollama models for minions. Pull new models, list available ones, switch presets, check disk usage. Use when setting up or changing models.
実装開始時のコンテキストセットアップ。関連ナレッジを検索し、効率的な実装開始を支援。新規実装タスク開始時に自動トリガーまたは明示的に呼び出し可能。
This skill should be used when the user wants to "validate a command", "review my command", "check command quality", "audit slash command", or needs evaluation of their Claude Code custom command against best practices.
Generate new Agent Skills following the open standard specification. Use this when asked to create a new skill, teach Copilot a new capability, or capture domain expertise as a reusable skill.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
End-of-session ritual. Reflect while context is rich, then seal. Triggers on /close, 'wrap up', 'let's finish', or context nearly full. Pairs with /open. (user)
Integrate Ralph with your project's existing CLAUDE.md files, skills, and agent preferences. Run after installing Ralph, or rerun anytime you add new skills/agents.
Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD integrations, multi-agent orchestration, or programmatic Claude interactions. Covers CLI flags (-p, --output-format), session management (--resume, --continue), Python SDK (claude-agent-sdk), custom tools, and agent loop patterns.
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
.github/skills 配下の Agent Skills（各SKILL.md）をレビューして改善提案を出す。name/description妥当性、簡潔さ、progressive disclosure、例の有無、参照の深さ、ツール制限、500行制限などのベストプラクティス観点でチェックする。新規作成/改修時に使う。
This skill should be used when the user asks to "setup conda environment", "configure Python environment", "activate conda automatically", "set conda environment for workspace", or mentions conda environment activation for Claude Code. Provides automatic conda environment configuration for workspaces.
"Senior SDK Master for @google/genai v1.35.0, expert in Controlled Outputs and Structured Intelligence.
Get Unity Search provider details via uloop CLI. Use when you need to: (1) Discover available search providers, (2) Understand search capabilities and filters, (3) Configure searches with specific provider options.
