跳到正文
cccskills
免费在 GitHub 公开

loop-deliver

Use only when the user explicitly invokes /loop-deliver or names this skill. Authors a loop-deliver run. Do not use unless named. Do not execute or resume generated runtime node files.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(4)

  • SKILL.md1.9 KB
  • preset.md4.8 KB
  • README.md1.4 KB
  • README.zh-CN.md1.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

loop-deliver — a loop-graph preset for requirements

A thin authoring entry. It binds a requirement-delivery pack, starts the owner interview, then follows loop-graph to compile the normal executor, ledger, directives, ops, and supervisor artifacts. It is not a second runtime and it does not ship a second template set.

Fit check

  • Use this when a feature, integration, migration, or behavior change needs several verified slices and an independent acceptance audit.
  • Use ../loop-converge/SKILL.md when the goal is code cleanup or consolidation. Use ../loop-research/SKILL.md when the decision between approaches is still open.
  • If the requirement fits one normal host task, say so and send it directly. Do not wrap it in a graph.

On invoke

  1. Inspect the workspace and current host the same way loop-graph does. Never ask which client this is when context already identifies it.
  2. Read and bind preset.md. That pack is the North Star, supervisor requirement, interview, shape, method guards, knob overrides, and artifact emphasis. Do not redesign them.
  3. Start the owner interview immediately. Ask only the pack's unresolved choices — outcome/acceptance, authority, and launch — as recommended A/B (or A/B/C) choices. Do not ask the owner to invent a plan.
  4. Read and follow ../loop-graph/SKILL.md from When called from a preset skill through generate and deliver. Compile only from loop-graph's templates/. This skill never executes the generated nodes.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

longgraph

免费

Use only when the user explicitly invokes /longgraph or names this skill. Routes and authors a durable longgraph run. Do not use unless named. Do not execute or resume generated runtime node files.

中文简介正在准备中。当前显示原文说明。

levi-qiao/longgraph-skill782026年9月23日 更新

Use only when the user explicitly invokes /loop-converge or names this skill. Authors a loop-converge run. Do not use unless named. Do not execute or resume generated runtime node files.

中文简介正在准备中。当前显示原文说明。

levi-qiao/longgraph-skill782026年9月23日 更新

Use only when the user explicitly invokes /loop-graph or names this skill. Compiles a custom loop-graph run. Do not use unless named. Existing runtime nodes are self-contained.

中文简介正在准备中。当前显示原文说明。

levi-qiao/longgraph-skill782026年9月23日 更新

Use only when the user explicitly invokes /loop-research or names this skill. Authors a loop-research run. Do not use unless named. Do not execute or resume generated runtime node files.

中文简介正在准备中。当前显示原文说明。

levi-qiao/longgraph-skill782026年9月23日 更新

查看 levi-qiao 的全部技能

报告此技能的问题