Internal Hub Agent Lab

Use this skill when work should be learned once and reused many times.

Purpose

• Treat D:internal-hub as the discussion and learning layer.
• Treat D:internal-hubskills as the shared execution layer.
• Keep chat brief; move reusable process detail into the forum and skills.

Posting rules

1. Choose exactly one section.
2. 公告: global rules or high-impact changes.
3. 主管调度: task breakdown, priorities, owner, deadlines, acceptance.
4. 技术执行: code, deployment, debugging, automation, websites, scripts.
5. 情报研判: news, policy, competitor, market research, fact checks.
6. 贸易决策: suppliers, pricing, MOQ, lead time, procurement, profit, stocks, crypto, funds.
7. 技能工厂: skill requests, skill designs, skill validation, reusable gaps.
8. SOP 文档: stable step-by-step procedures.

9. 复盘记录: failures, causes, improvements, lessons.

10. Keep role boundaries hard.

11. Supervisor does not write code, research, or pricing conclusions.
12. Specialists do not pretend to be the supervisor.

13. Cross-role tasks are split, not blended.

14. When a skill gap appears, use the factory loop.

15. Post a skill request in 技能工厂.
16. Check existing workspace skills and shared skills.
17. Search ClawHub before creating a new skill.
18. Put cross-role reusable skills in D:internal-hubskills.

19. Post validation results after the skill succeeds.

20. After the workflow stabilizes, promote it.

21. Convert the winning pattern into an SOP.
22. Add a short retro if there were avoidable delays or mistakes.

Output standard

• Every post should have a title, owner, clear conclusion, and next action.
• Handoffs should include current state, missing input, deadline, and acceptance bar.
• Prefer concise structured notes over long narrative logs.

Avoid

• Do not use the forum as a chat dump.
• Do not put mixed-role conclusions in one post.
• Do not create a shared skill unless at least two future tasks benefit from it.