Run any Skill in Manus with one click

refine-restruct

Stars1

Forks0

UpdatedApril 9, 2026 at 20:10

Manually refine a prompt through the local LLM meta-prompt pipeline. Transforms a casual developer request into a structured, rules-aware prompt using a local Ollama model. Only works when features.refinement is enabled in config.yaml.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

thejustinwalsh

thejustinwalsh/claude-restruct-plugin

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	refine-restruct
description	Manually refine a prompt through the local LLM meta-prompt pipeline. Transforms a casual developer request into a structured, rules-aware prompt using a local Ollama model. Only works when features.refinement is enabled in config.yaml.

This skill transforms a casual developer request into a structured, rules-aware prompt using a local Ollama model. It reads project rules from agents.md/CLAUDE.md, gathers git context, and produces XML-structured output with objective, constraints, workflow, uncertainty protocol, and anti-patterns.

The binary is bundled in this plugin — always use the full path:

${CLAUDE_PLUGIN_ROOT}/bin/restruct refine

Usage:

echo '{"prompt":"your prompt here"}' | ${CLAUDE_PLUGIN_ROOT}/bin/restruct refine to refine a prompt
Add --dry-run to preview the refined prompt to stderr without replacing

The refinement pipeline runs entirely locally — no data leaves your machine.

More from this repository

same repository

disable-restruct

thejustinwalsh/claude-restruct-plugin

Disable restruct prompt refinement. Prompts pass through to Claude without local LLM preprocessing.

2026-04-091

enable-restruct

thejustinwalsh/claude-restruct-plugin

Enable restruct prompt refinement. Re-enables the local LLM preprocessing of prompts.

2026-04-091

init-restruct

thejustinwalsh/claude-restruct-plugin

Generate a minimal, research-backed CLAUDE.md for this project. Analyzes the codebase for non-obvious commands and conventions, interviews you for team knowledge, and produces a concise file that stays under 30 rules.

2026-04-091

review-permissions-restruct

thejustinwalsh/claude-restruct-plugin

Review tool permission decisions across sessions and propose auto-approval rules. Analyzes which tools the user consistently approves, then suggests additions to .restruct/permissions.yaml to eliminate repetitive permission dialogs.

2026-04-091

setup-permissions-restruct

thejustinwalsh/claude-restruct-plugin

Write an initial .restruct/permissions.yaml with safe defaults so the restruct permit hook can auto-approve common tool use without repeated dialogs.

2026-04-091

setup-refine-restruct

thejustinwalsh/claude-restruct-plugin

Install Ollama, pull the right model for your hardware, warm it up, and enable the restruct prompt refinement pipeline. Only runs when features.refinement is enabled in config.yaml.

2026-04-091

name	refine-restruct
description	Manually refine a prompt through the local LLM meta-prompt pipeline. Transforms a casual developer request into a structured, rules-aware prompt using a local Ollama model. Only works when features.refinement is enabled in config.yaml.

The binary is bundled in this plugin — always use the full path:

${CLAUDE_PLUGIN_ROOT}/bin/restruct refine

Usage:

echo '{"prompt":"your prompt here"}' | ${CLAUDE_PLUGIN_ROOT}/bin/restruct refine to refine a prompt
Add --dry-run to preview the refined prompt to stderr without replacing

The refinement pipeline runs entirely locally — no data leaves your machine.