ワンクリックで
multi-execute
Execute an approved multi-agent plan
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Execute an approved multi-agent plan
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | multi-execute |
| description | Execute an approved multi-agent plan |
| user-invocable | true |
Execute a previously approved plan using coordinated agents.
Requires an approved plan from /multi-plan or /orchestrate.
$ARGUMENTS — Phase to execute (e.g., "phase 1") or "all" for sequential executionRead the approved plan and identify:
For the specified phase:
Between phases, verify:
## Execution Progress
### Phase [N]: [Name]
- Status: COMPLETE / IN PROGRESS / BLOCKED
- Tests: X passing, Y failing
- Review: APPROVED / PENDING / CHANGES REQUESTED
### Overall Progress
[====> ] 2/5 phases complete
### Next Phase
[Description of what's next]
If any gate check fails, stop and report the issue rather than proceeding to the next phase.
Generate changelog entries following Keep a Changelog format
Generate a well-structured pull request with summary and test plan
Cluster related instincts into skills, commands, or agents
Export instincts for sharing with teammates or backup
Import instincts from teammates or community collections
View learned instincts grouped by domain with confidence levels