mcpField

loop-converge

github.com/levi-qiaoDevelopment153 installs
Repository

About loop-converge

loop-converge is a preset skill for iterative code reduction, such as removing, merging, or reusing unused and duplicate code. It binds a code-convergence pack and follows loop-graph to prepare a two-node executor-and-supervisor run; it does not execute the generated nodes.

Key features

  1. 01Binds a code-convergence preset
  2. 02Interviews the owner on scope and authority
  3. 03Uses loop-graph to compile a run
  4. 04Requires an independent supervisor audit
  5. 05Does not execute generated nodes

Use cases

  1. 01Removing unused code over verified rounds
  2. 02Merging duplicate implementations
  3. 03Reusing code with independent review

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/levi-qiao/longgraph-skill --skill loop-converge

After installing, type/loop-convergein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

preset.md
README.md
README.zh-CN.md

Details

From the project README

loop-converge — a loop-graph preset for slimming code

A thin authoring entry. It binds a code-convergence pack, starts the owner interview, then follows loop-graph to compile a normal two-node run (executor + supervisor). It is not a third runtime node and it does not ship a second template set.

Fit check

  • Use this when unused or duplicate code will take many verified rounds to remove, merge, or reuse, and an independent audit should keep the bar from sliding into a rewrite.
  • If the request is a one-shot tidy that fits a normal host task, say so and send the task directly. Do not wrap it in a graph.

On invoke

  1. Inspect the workspace and the 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, the supervisor requirement, the method guards, the knob overrides, the recommended shape, and the detector hints. Do not redesign them.
  3. Start the owner interview immediately. With this pack bound, ask at most the three questions the pack names — scope, authority, launch mode — each as a recommended A/B (or A/B/C) choice. Do not ask for a North Star. Do not offer to omit the supervisor.
  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.

Comments

Markdown supported