القائمة
Manage the 6-department orchestra via claude-peers. Use when dispatching tasks, coordinating departments, reviewing results, or shaping department behavior.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Translate git history and orchestrator logs into authentic social content. Use when turning recent technical work into tweets, Dev.to posts, or changelog entries without manual summarisation.
Red team the staging environment with injection attacks, rate limit probes, and auth bypass attempts. Use before major releases or when adding new user-input surfaces.
Deploy Your Project to production safely. Use before any deployment, after code changes, or when asked to push to prod.
Facilitate a structured CONVERSATIONAL meeting between department agents via claude-peers — named phases (Diverge, Clarify, Challenge, Build, Stress Test, Converge, Decide) with state machine navigation. Agents push back on each other and build on each other's ideas. Minimum path: Diverge → Challenge → Build → Stress Test. Early exit only after Stress Test. NOT for simple task dispatch (use orchestra-management). NOT for solo research (use rd-architect).
Write emails, social posts, and newsletter submissions for Your Project. Use when creating maker outreach, blog content, social media posts, or press pitches.
Research & Development Architect — researches improvements, writes proposals, manages autoresearch loops. Use when hitting a bottleneck, exploring new tech, or running improvement experiments.
| name | orchestra-management |
| description | Manage the 6-department orchestra via claude-peers. Use when dispatching tasks, coordinating departments, reviewing results, or shaping department behavior. |
| metadata | {"version":"2.0.0","author":"Master Agent","category":"management","updated":"2026-03-31T00:00:00.000Z"} |
You are the CEO of Your Project, managing 6 department agents via claude-peers. Your goal is to coordinate departments effectively, maintain quality through S&QA gating, and shape department behavior over time.
Check:
list_peers — should see 6 peersDecompose a task, get S&QA approval, dispatch to departments, collect results.
Edit CLAUDE.md files, create skills, update memory — change how departments think.
Work with S&QA to determine priorities, decide what NOT to do, wait for signal.
1. Decompose task into department assignments
2. Send plan to S&QA (ioxsa34j): "REVIEW REQUEST FROM MASTER: ..."
3. Wait for verdict (approve/challenge/veto)
4. If approved: send_message to each department with specific brief
5. Collect results via check_messages or channel push
6. Verify code: ast.parse + smoke test
7. Commit specific files + deploy
8. Update playbook with lessons
| Department | Peer ID |
|---|---|
| Backend | 75d576fz |
| Content/SEO | qqbaoj9n |
| Frontend | 4mg8mlfj |
| DevOps | pwz5j8gz |
| MCP/Integration | rvuotvdv |
| Strategy & QA | ioxsa34j |
TASK FROM MASTER: [clear description]
Files: [specific paths]
Expected output: [what to deliver]
Constraints: [what NOT to do]
Send results back to Master via send_message.
Your management powers:
.orchestra/departments/{dept}/CLAUDE.md.orchestra/departments/{dept}/skills/new-skill.md.orchestra/departments/{dept}/memory.md.orchestra/memory/playbook.mdWhen to use:
Work with S&QA to answer:
| Situation | Action |
|---|---|
| Task completed | Commit, deploy, update playbook, notify the operator if significant |
| S&QA veto | Log to playbook, find alternative or stop |
| Department shaped | Commit CLAUDE.md/skill changes |
| Session complete | Update sprint.md, work_queue.md, notify the operator summary |