Guidance for working with the PolicyEngine GitHub agent bot

# Prompt Craft

# Restart Prompt Skill

Code review using RepoPrompt MCP (chat_send mode=review). Returns structured verdict.

Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.

Get a detailed summary of what's happening in a Claude Code tmux session

Detect stuck states in a Claude Code tmux session and resolve them

Create and run an agent-ready development queue from issues/PRs with progress checkpoints.

Run resilient multi-tool problem solving with explicit fallback strategy and auditable execution notes.

Use when starting any conversation — establishes skill usage rules and multi-agent routing

AI-powered X/Twitter search agent for real-time trends, news, and social media insights. Costs 0.05 USDC per request on Base network.

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Use the LLM Wiki plugin tools to maintain a cited local company wiki.

Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.

Check that required tools and env vars are configured for Home Assistant MCP

Create or edit Claude Code skills with expert guidance on structure and best practices

MCP server implementation with Express.js and TypeScript.

Gemini CLI for one-shot Q&A, summaries, and generation.

Model Armor: Sanitize a prompt for safety via the gws CLI.

Write or update a handoff document so the next agent with fresh context can continue this work.

Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.

Document Q&A with RAG using Supabase pgvector store.

AI agent with retrieval tool for document Q&A using RAG and LangGraph.

Use this agent when you need to run linting and code quality checks on Ruby and ERB files. Run before pushing to origin.

List all running ai-* Claude Code tmux sessions with their current status

Guidelines for working with LLM context stored in the .llm/ directory.

Use when producing written artifacts for humans — catches default LLM writing patterns.

Skills for web search and content scraping via DuckDuckGo MCP Server. Used when users need online searching and web scraping.

Discover the latest Claude Code resources added to Vibe Index

Use when the user wants coordinated multi-agent planning, delegation, or role-based engineering guidance.

Call cursor-agent to perform a task.

# mcp-atlassian-hint-inject

Replace with description of the skill and when the agent should use it.