Skill

refine

Use when the user has an existing draft, text, code, or artifact and wants it iteratively improved through multi-model critique and weaving across multiple passes. Triggers on phrases like "refine this", "improve this", "make this better", "iterate on this", or "polish this"

From loom

Install

Run in your terminal

npx claudepluginhub tony/ai-workflow-plugins --plugin loom

Tool Access

This skill uses the workspace's default tool permissions.

Skill Content

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

138.6k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

evaluation-methodology

1 file

Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.

plugin-eval

32.9k

Stats

Parent Repo Stars1

Parent Repo Forks0

Last CommitMar 27, 2026

Actions

View Source View Plugin View on GitHub View README

Key Features

Accepts inline text or file paths (auto-detected)

--passes=N (1-5, default 2): Number of refinement cycles

Each pass: all models critique and improve, judge picks best, weaves in strengths from runners-up

Full rationale chain showing evolution across passes

Early-stop when no material improvement detected

--judge=host|round-robin: Host judges every pass, or rotate judging across models

Loom Refine

Iteratively improve an artifact through multi-model critique and weaving. Each pass is a full judge-pick-best-incorporate-strengths-address-weaknesses cycle.

When to Use

You have a draft that needs improvement
You want multiple AI models to critique and enhance an artifact
You want iterative refinement where each pass genuinely improves the output
You have output from /loom:brainstorm that you want to refine further

Key Features

Accepts inline text or file paths (auto-detected)
--passes=N (1-5, default 2): Number of refinement cycles
Each pass: all models critique and improve, judge picks best, weaves in strengths from runners-up
Full rationale chain showing evolution across passes
Early-stop when no material improvement detected
--judge=host|round-robin: Host judges every pass, or rotate judging across models

The Refinement Cycle

All models independently critique and improve the artifact
Judge scores versions, picks the best, identifies strengths in runners-up
Judge weaves a revised version incorporating all improvements
Woven version goes back to all models for another round
Repeat until passes exhausted or convergence

How to Invoke

Run the /loom:refine command with your text or file path. The command handles context gathering, model detection, the judge-weave-distribute cycle, and artifact persistence.