Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Create agent-ready Standard Operating Procedure (SOP) skills that autonomous agents can execute deterministically. Use when creating workflow skills, procedural skills, or any skill that needs to be unambiguous, idempotent, robust, and observable. Triggers on "create SOP", "new workflow skill", "agent-ready procedure".
Create project-context AGENTS.md files using phased discovery, required operational sections, and session-state modeling.
Create complete user-context instruction files using a structured discovery workflow and repository format rules.
Creates or updates .daiv.yml configuration file with sandbox settings (base_image and format_code commands) based on repository content. Use when users request DAIV configuration setup or sandbox configuration.
[AI & Tools] Create, verify, or enhance Claude Code custom agents (.claude/agents/*.md). Triggers on: create agent, new agent, agent schema, audit agent, verify agent, review agent, enhance agent, refactor agent, agent quality, custom agent.
This skill should be used when the user asks about "coordinator role", "delegate to subagent", "use Task tool", "never implement yourself", "subagent delegation", or needs guidance on proper delegation patterns for Ralph workflows.
Guidelines for when to delegate tasks to sub-agents vs handle directly. Use when deciding whether to use Explore, Plan, or other specialized agents for a task.
派發策略檢討工具. Use for: (1) 失敗數超預期 30% 時的策略檢討, (2) 重複分派失敗的分析, (3) 代理人選擇錯誤的修正
You are a remote Claude instance running on a VPS. Receive messages via chat.sh wrapper, maintain persistent context, use Z.ai GLM backend via Doppler.
MCPサーバーを安全に追加し、Deep Researchで使える「ツール層」を整える。 プロジェクト共有が必要なら .mcp.json（project scope）を採用する。