plan-improve

Community

Automates plan confidence score improvements.

Authorusetheodev
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Iteratively improve a /to-plan plan's M2 score by applying deterministic fixes + LLM-driven semantic fixes via a ralph-loop-style autonomous iteration. Use after /plan-confidence returns a verdict below SHIPPABLE_WITH_CAVEATS (NON_SHIPPABLE or INVALID) and you want the system to attempt auto-improvement before human intervention.

Core Features & Use Cases

  • Deterministic fixes: apply weak-imperatives, remove loopholes, and inject TDD templates in bugfix tasks to lift scores.
  • LLM-driven semantic improvements: coordinate ADR alternatives and strategic guidance to converge toward the target verdict.
  • Loop orchestration: wraps the ralph-loop plugin with state handling, pre-flight guards, and post-promise sanity checks.

Quick Start

Trigger Plan-Improve to automatically lift a plan's M2 score by applying deterministic fixes and semantic improvements through a ralph-loop workflow.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: plan-improve
Download link: https://github.com/usetheodev/theo-ui/archive/main.zip#plan-improve

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.