Background Agent Pings

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

Search past reasoning for relevant decisions and approaches

System health check (MOT) for skills, agents, hooks, and memory

Upgrade any skill to v5 Hybrid format using decision theory + modal logic

Never Use TaskOutput

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

Identify failure modes before they occur using structured risk analysis

Create git commits with user approval and no Claude attribution

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

Analyze brownfield codebase and create initial continuity ledger

Agent Orchestration Rules

Wiring Verification

Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic

Release preparation workflow - security audit → E2E tests → review → changelog → docs

Index at Creation Time

使用jimeng-mcp-server进行AI图像和视频生成。当用户请求从文本生成图像、合成多张图片、从文本描述创建视频或为静态图像添加动画时使用此技能。支持四大核心能力：文生图、图像合成、文生视频、图生视频。需要jimeng-mcp-server在本地运行或通过SSE/HTTP访问。

Standalone Serena MCP tools for code intelligence - symbol search, file ops, memory, editing, config, workflow helpers, and shell execution without MCP server

Comprehensive guide for Effect-TS, the functional TypeScript library. Use when building Effect applications, especially MCP servers. Covers correct APIs, common misconceptions, and MCP-specific patterns.