WenHub

文枢三院制 AI Agent 协作治理体系。提供决策者→管理者→经略院(任务拆解)→工造院(执行)→明鉴院(质检) 的完整协作流程，适用于需要多 Agent 协作治理的场景， 包括任务分配与分级、质量管控与评分、标准化汇报、知识沉淀与复用、安全管控与违规处理等。 配套参考资料（references/ 目录）涵盖三...

This skill appears coherent for setting up a multi-agent governance workflow. Before using it: (1) Inspect any template package you download from the referenced URL before placing files into your workspace; don't run unknown installers. (2) Keep secrets out of the created template files (.wenhub/.rules/, SOUL.md, AGENTS.md) and follow the included security-rules guidance (use env vars or encrypted stores for keys). (3) Prefer to add the templates to a private repo or branch first and review them with code review or pre-commit scanners. (4) If you need higher assurance, verify the vendor domain (wenhub.huawen-inc.com) independently and request a signed release or checksum for any template archive. If you want, I can flag all lines in the templates that might hold sensitive placeholders to avoid accidentally committing credentials.

Type: OpenClaw Skill Name: wenhub Version: 1.5.0 The WenHub skill bundle is a comprehensive governance framework designed for multi-agent collaboration and task management. It consists entirely of documentation and behavioral guidelines (Markdown) and metadata (JSON), with no executable code or scripts. The instructions focus on organizational structure (the 'Three Courts' system), quality control, and standardized reporting. Notably, the bundle includes a dedicated security policy (references/security-rules.md) that explicitly mandates the protection of sensitive data, prohibits hardcoding keys, and enforces the principle of least privilege, indicating a defensive and well-aligned security posture.