メニュー
Use Codex and Gemini CLIs as external reviewers for gated review chunks. They read prompt files and write reports. Use for pre-implementation review, spec validation, architecture critique, or second opinions.
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
Multi-hypothesis research campaign protocol. Use for open-ended optimization goals ("make X faster", "improve the metric") where several candidate ideas compete for a limited budget. Triages ideas cheaply, confirms survivors with full preregistered experiments, and keeps a committed ledger so dead ideas stay dead.
Controlled benchmark experiment protocol for solver, performance, routing, and optimization work. Use when testing a hypothesis against metrics, comparing implementations, or deciding whether to promote or abandon a benchmark-driven change.
Coordination-only protocol. You dispatch subagents, you do not execute code. Restricts tools to Read, Write (prompts/ and notes- only), Agent, Glob, Grep. Use when orchestrating multi-agent work.
Four-role sequential pipeline for complex, high-risk changes. Scout surveys the codebase, Coder implements with TDD, Analyst finds problems, Verifier gates the merge. Use for large refactors, architectural shifts, and interdependent multi-phase work.
Background knowledge for writing and launching subagent prompts. Covers prompt file conventions, worker identity declarations, batch dispatch patterns, and parallel swarm safety. Auto-invocable when dispatching agents.
Deletion-first fixed-point protocol for refactors, cleanup, migrations, and architectural convergence. Use when replacing old surfaces, removing helper debt, shrinking code, moving ownership boundaries, or auditing every symbol in a slice.
| name | external-agents |
| description | Use Codex and Gemini CLIs as external reviewers for gated review chunks. They read prompt files and write reports. Use for pre-implementation review, spec validation, architecture critique, or second opinions. |
| disable-model-invocation | false |
| allowed-tools | ["Read","Bash","Write"] |
Use Codex and Gemini CLIs as external reviewers for gated review chunks. They read prompt files and write reports.
codex exec --dangerously-bypass-approvals-and-sandbox "Read prompts/task.md and write report to reports/task-report.md"
--dangerously-bypass-approvals-and-sandbox enables writes (required)gemini --yolo "Read prompts/task.md and write report to reports/task-report.md"
--yolo auto-approves all actionsprompts/review-task.md with clear instructionscodex exec --dangerously-bypass-approvals-and-sandbox "Read prompts/review-task.md and write report to reports/codex-task-report.md"gemini --yolo "Read prompts/review-task.md and write report to reports/gemini-task-report.md"reports/ for outputs# Review Task: [Title]
## Context
[What's being reviewed and why]
## Files to Review
- `path/to/file1.md`
- `path/to/file2.yml`
## Questions to Answer
1. [Specific question]
2. [Specific question]
## Output
Write your review to `reports/[name]-report.md` with:
- Summary of findings
- Issues identified (if any)
- Recommendations