autospec-refine

Community

Refine prompts for better, fewer course-corrections.

Authorberlinguyinca
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It prevents under-specified feature requests from turning into slow, error-prone implementation by iteratively upgrading the operator’s prompt using repo-grounded evidence before any coding happens.

Core Features & Use Cases

  • N-round repo-grounded prompt refinement: Applies ordered lenses (repo grounding, acceptance-criteria clarity, sizing constraints, and adversarial QA) over multiple iterations.
  • Structured artifacts for auditability: Writes per-round JSON and markdown refinement records plus a schema-validated output set.
  • Handoff to the main autospec pipeline: After approval, forwards the final refined prompt to /autospec for autonomous implementation, with options for interactive or dry-run behavior.
  • Continuous refinement loops: Supports a bounded refine → handoff → execute → report-harvest → re-refine loop for iterative progress.

Quick Start

Use autospec-refine to refine a new feature request over three rounds, then automatically hand the improved prompt off to /autospec.

Dependency Matrix

Required Modules

curlgitghjq

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: autospec-refine
Download link: https://github.com/berlinguyinca/autospec/archive/main.zip#autospec-refine

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 471,000+ vetted skills library on demand.