Clarify First
Enforce risk-based alignment for AI Agents. Stop Claude/Cursor from guessing on vague or high-impact tasks. 让 AI 先对齐、再动手：为 Agent 引入风险分级与澄清机制，拒绝盲目猜测，确保开发安全可控。
Clawgate
OpenClaw execution governance skill for approval gates, risk classification, confirmation policy, and action boundaries. Use it to reduce low-risk confirmation noise while hard-stopping high-risk and critical actions.
Clarify First
This skill should be used when a request is ambiguous, underspecified, conflicting, or high impact. It is intended for vague verbs like optimize, improve, fix, refactor, and add feature; for missing file paths or unknown dependencies; and for risky actions like deploy, delete, overwrite, or migrate. It should not be used for purely informational requests or explicitly scoped low-risk changes. The…