Skip to content
cccskills
FreePublished on GitHub

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.

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (4)

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

SKILL.md (original)

Review the instructions the agent will receive before you install.

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.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

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.

The English summary is being prepared. Showing the original description.

levi-qiao/longgraph-skill78Updated Sep 23, 2026

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.

The English summary is being prepared. Showing the original description.

levi-qiao/longgraph-skill78Updated Sep 23, 2026

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.

The English summary is being prepared. Showing the original description.

levi-qiao/longgraph-skill78Updated Sep 23, 2026

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.

The English summary is being prepared. Showing the original description.

levi-qiao/longgraph-skill78Updated Sep 23, 2026

See all skills by levi-qiao

Report a problem with this skill