Agent building

Use when validating UI changes in a branch require Playwright E2E testing.

Manage agent-owned RLM heartbeats from the Python REPL.

A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems.

Message an agent's parent, siblings, or direct children through the daemon.

Read-only roster and observation of an agent's parent, siblings, and direct children.

Use external MCP services generically from Python - search the supported-service catalog, inspect the user's connections, discover live tool schemas, and call…

Search Google via the Serper API.

当用户希望将任务交给员工或协作者并跟进结果时，结合本地人员资料选择负责人，写清要求、协商工期、提供帮助并验收汇报；有飞书 CLI 时派单、读取回填和回复，缺少工具或权限时交付可转发文字。支持事件队列与可配置 Agent 接入，不承担招聘、绩效排名或惩罚。

渗透测试Agent操作系统。把渗透抽象成状态空间搜索:不预设固定路径,以项目黑板 Fact 图 (upsert_project_fact)+漏洞记录沉淀认知,路径从已验证事实上涌现。覆盖全杀伤链攻击手法 (联网情报/Web/认证/服务端/源码/社工/后渗透/二进制/内网域/云/区块链/AI/无线/硬件)+0day+…

Detect privilege escalation and unauthorized access via dialogue.

Detect indirect prompt injection (goal hijack).

Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.

Detect tool misuse and unexpected code execution via dialogue testing.

Detect data exfiltration via URL path encoding and chained web_fetch navigation.

Run an evaluator-gated performance optimization workflow over Codex goal mode with durable OMX artifacts and safe goal handoffs.

把模糊提问改写成 Agent 可推理、可批评、可验证的问题说明书，并判断自动化可解程度。用户要改进问题表述、研究问题或评估 Agent 可解性时使用；任务交付目标已明确时不重复澄清目标。

Design n8n AI agents the right way.

Handle files and binary data in n8n correctly.

Write Python in n8n Code nodes (native Python, `language` pythonNative, n8n 2.x).

Expert guide for using n8n-mcp MCP tools effectively.

Use when an n8n-mcp account targets more than one n8n instance — i.e.

Build reusable, composable n8n sub-workflows.

Use when goal, constraints, and success criteria are already settled and the user wants them frozen into a formal spec an agent can execute and verify: 'turn…

设置 Claude Code hooks，在危险 git commands（push、reset --hard、clean、branch -D 等）执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks，或在 Claude Code 中阻止 git push/reset 时。