martin1847/evolab / skills/cto-orchestration
cto-orchestration
Unverified以 CTO/orchestrator 模式管理多 agent 软件交付。用户要求“你做 CTO/编排者”“派 omp/codex 去做”“goal 模式派发”、管理多会话开发或接入这套工作流时使用;“复盘/收口/retro/retrospective”“工作盘点/盘点候选/stocktake”也必须触发,盘点只提案不动工。新项目先用 repo-governance-bootstrap 建治理骨架。不用于单 agent 小任务、无需评审循环的局部改动或纯文档初始化。
references/stocktake.md
View on GitHub# 盘点仪式操作手册(stocktake)<!-- trunk:盘点仪式 -->
> SKILL §5「盘点仪式」的展开 = checklist 本体,逐条勾。触发词:盘点 / 接下来做什么 /
> 规划下一批 / stocktake——听到即走本 checklist,不即兴。与复盘的分工:复盘向后看
> (记账/教训,周期尾),盘点向前看(候选→取舍→提案,随叫随跑);本会话已有复盘产出时
> 跳过其已扫过的源,只补增量。选题取舍判据单源在此,复盘与决策队列引用不复制。
## 四步 checklist
1. **扫源(Identify)**:候选不许凭记忆,逐源机械扫——台账敞口行 · LESSONS 无门/n≥2 行 ·
DECISION_QUEUE 活跃项 · 停牌攒例项(信件/OBSERVATION)· owner 当场新增。各源的具体
路径与载体由该仓 AGENTS.md 声明;未声明或扫不到的源在产出里标 `UNKNOWN`,不默认为空。
2. **标面定档(Prioritize)**:每候选一行,固定格式
`[面 · Impact · Effort] + 一句价值判语 + 证据强度(n 计数 / [实测|读码|推断])`。
- 面与配比判据同 SKILL §2 配比轴(本文不复述)。
- Impact 档位(按序判,先命中先得):无实证(纯推断)→ 低;有实证(n≥1)且为真实用户
路径断裂 / 在售承诺缺口 → 高;其余有实证 → 中。Effort:S/M/L = 单席一轮内 / 一批内 / 多批。
- 排序(本文自有规则):主序 Impact 高→低;SKILL §2 配比闸触发时真路径类候选先于一切;
同档 Effort 小者先;证据强度只作同位 tiebreak 与置信标注,不抬 Impact。
- 判语写「谁受益、缺口多大」,不写实现方案。
3. **收口成提案**:按上述排序出 top N(N≤5,候选不足就如实少列,不凑数)+ 推荐首选
(含一句为什么是它),**必须带不做/停牌名单**——落选候选全部落停牌行不展开,显式
Don't-do 防盘点变铺大饼。候选为零、或第 1 步列出的源全部 `UNKNOWN` → 如实报现状并停,不发明候选。
4. **只提案不动工**:盘点产出 = owner 的裁决面;批了才进 goal 合同流程(大批次仍先过
方案预审)。默认对话内呈现,owner 点名留档才落文件——盘点是决策辅助,不产衍生物。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |