一键导入
launch-gate
Use when a launch needs a go/no-go decision with rollback and monitoring evidence.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when a launch needs a go/no-go decision with rollback and monitoring evidence.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | launch-gate |
| description | Use when a launch needs a go/no-go decision with rollback and monitoring evidence. |
Lifecycle stage: SHIP
Use before public release, merge, publication, or operational handoff.
Do not use when this trigger is absent; choose the command or skill that owns the requested state, artifact, and verification gate.
| Shortcut | Rebuttal |
|---|---|
| "This is obvious." | Write the assumption and evidence. If you cannot, it is not obvious. |
| "We can do this later." | If the missing step changes the decision, do it now or state the risk. |
| "The user wants speed." | Reduce scope; do not skip the quality bar. |
| "This does not need verification." | Every important claim or behavior needs proof. |
Launch Checklist
Use templates/launch-checklist.md. The artifact should be concise, auditable, and include evidence, blockers, and next action so another agent can resume.
Trigger: work is ready to merge, publish, or hand off. Action: check validation logs, CI state, public-copy scrub, rollback, side effects, and artifact links before launch. Output artifact: templates/launch-checklist.md with blockers and next action. Verification: cite local gate, remote status, rollback path, and unresolved risks.
Before a merge or public handoff, inspect the latest validation logs, CI state, public-copy scrub, rollback plan, and artifact links. If the branch has local-only proof or unreviewed side effects, block launch with a launch checklist instead of saying the work is ready.
Agent Brain /brain-brief: after intake, research, and grill have enough signal.
Agent Brain /brain-build: an implementation plan has a selected task and validation method.
Agent Brain /brain-design: a product brief needs ux or interaction design before planning.
Agent Brain /brain-eval: changing Agent Brain behavior or checking quality.
Agent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.
Agent Brain /brain-learn: after repeated success/failure, a tricky fix, or a shipped workflow.