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/retro-hooks.json
View on GitHub{
"//": "复盘仪式压缩点提醒 wiring 真源(可选——编排位席位建议接入;提醒不阻断)。接入=command 前缀替换为本 skill 安装根绝对路径(hooks 不展开 ~、不加解释器前缀——脚本自带 shebang)。接入层级判据:编排位常驻的机器接用户级 ~/.claude/settings.json(复盘仪式是席位属性、不是项目属性,逐项目接会漏新项目——多席位机器实证 2026-07-28);仅少数项目做编排时才接项目级,两级都接会重复注入。接线是全局的,所以脚本自己认身份:只在 payload cwd 所在仓正在被编排(同仓有 LIVE 席位或今/昨相位账本 start 行,同仓 = git common dir)时输出,其余一个字不输出——与 E1 / Stop 门共用 agentctl/identity.py 的同一谓词。PreCompact 只能给用户可见 systemMessage(harness schema 不收 additionalContext,错误形态会被整体拒收、静默失败——2026-07-28 实证);模型上下文注入靠压缩后 SessionStart,脚本自判 source=compact、其余静默。UserPromptSubmit 触点(session-economics.py)只在被编排仓、且只在上下文越过 300k/450k/600k 档或闲置过缓存 1h 边界时各说一行 additionalContext(每档每会话一次、同一次闲置一次),其余每一条 prompt 零输出、零 git、零 identity 调用;它只提醒收口即 /compact(读数只算最后一个压缩边界之后那段——压缩后第一条 prompt 判不出就不说,不误报压缩前那个读数),不拦、不改状态、从不非零退出。同一个 retro-reminder.sh 还管 SessionStart source=startup|clear 的**开场指针**(零接线改动):谓词只有「payload cwd 所在 git 仓根下有 docs/ACTIVE_CONTEXT.md」一条,不叠加被编排谓词(换会话后往往还没有 LIVE 席位,叠加会恰好在最需要接上时静默);输出一行「快照在哪 + Last rewritten 日期」,不内联正文,判不出即零字节。",
"PreCompact": [
{ "matcher": "", "command": "references/retro-reminder.sh" }
],
"SessionStart": [
{ "matcher": "", "command": "references/retro-reminder.sh" }
],
"UserPromptSubmit": [
{ "matcher": "", "command": "references/session-economics.py" }
]
}
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 | Verified | 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 |