launch-gate
Use when a launch needs a go/no-go decision with rollback and monitoring evidence.
ソース情報
- リポジトリ
- rohitg00/agentbrain
- ソースの最終更新活動
- 2026年5月16日 03:11
- 検出された SKILL.md の言語
- 英語
- スター
- 41
- フォーク
- 9
インストール方法
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
ソースファイルを確認
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SKILL.md を表示中
SKILL.md
ソースの指示 · 読み取り専用プレビュー- name
- launch-gate
- description
- Use when a launch needs a go/no-go decision with rollback and monitoring evidence.
# launch-gate
Lifecycle stage: SHIP
## Trigger
Use before public release, merge, publication, or operational handoff.
## When not to use
Do not use when this trigger is absent; choose the command or skill that owns the requested state, artifact, and verification gate.
## Inputs
- User request or current artifact.
- Known constraints and context.
- Relevant evidence or source links, if available.
- Current Agent Brain state.
## Procedure
1. State the current state and target artifact.
2. Identify missing blockers and ask at most three blocking questions.
3. Separate facts, assumptions, hypotheses, and open questions.
4. Apply the anti-rationalization table below.
5. Produce the required artifact: **Launch Checklist**.
6. Add evidence, risks, decision, and next state.
## Anti-Rationalization
| 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. |
## Verification
- Required artifact exists and is named.
- Facts, assumptions, and open questions are separated.
- Evidence or evidence gaps are explicit.
- Next state is stated.
- Stop conditions are honored.
## Output Artifact
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.
## Failure Modes
- Producing advice instead of an artifact.
- Accepting user assumptions without challenge.
- Skipping evidence because the task feels simple.
- Recommending an agent when a simpler system is enough.
- Hiding risks or open questions.
## Example
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.
GitHubで見る