From protocols
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/protocols:external-agentsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use Codex and Gemini CLIs as external reviewers for gated review chunks. They read prompt files and write reports.
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
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub ctoth/protocols-plugin --plugin protocols