Massive Code Refactoring with gpt-5.6-sol-xhigh and Custom Skills

X postKyle MisteleOpinion

Kyle Mistele shares the outcome of a refactoring run where combining two specialised skills with gpt-5.6-sol-xhigh eliminated over 13,000 lines of code across older projects.

Key points

  1. Mistele paired Dillon Mulroy's de-slop skill with his own Effect skill when running gpt-5.6-sol-xhigh.
  2. The automated run generated a Pull Request adding 503 lines while removing 13,682 lines.
  3. The author notes that this effectively cleared out substantial bloat from older projects.

Why it matters

Using specialised agent skills alongside advanced models can dramatically simplify legacy codebases. Significant net reductions in line count highlight how AI tooling can assist in decluttering and modernising software architectures.

Analysis

This brief social post provides practical anecdotal evidence rather than a deep technical breakdown. Nevertheless, it demonstrates how composing targeted skills—specifically for removing redundant boilerplate and applying Effect patterns—can steer high-reasoning models like gpt-5.6-sol-xhigh toward aggressive, automated codebase compaction.

Original post

Kyle Mistele 🏴‍☠️

@0xblacklight · 15 August 2026

handed gpt-5.6-sol-xhigh @dillon_mulroy's de-slop skill + my effect skill and came back to a +503/-13,682 PR absolutely glassed a couple of old projects t.co/7nhg96rfug

956 likes18 replies1.6k bookmarks197.7k views

View on X

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:Peter Steinberger

    OpenClaw Deletes 400k Lines of Tests Using Dedicated Agent Skill

    Peter Steinberger reported that OpenClaw pruned around 400,000 lines of its own test code with minimal impact on code coverage. The cleanup was driven by an agent skill called 'test-audit', which targets low-value, redundant, or implementation-coupled tests.

    10.8kbookmarks1.3mviews

    AI & LLMs· News

  • X post:Connor Loi

    Code cleanup with /ponytail-review to counter AI code bloat

    Developer Connor Loi highlights the /ponytail-review skill, describing it as an anti-slop mechanism that removes unnecessary code generated by additive models like Codex.

    818bookmarks42.1kviews

    AI & LLMs· Tool

  • Link:Brian Lovin

    deslop: AI Code Cleanup Skill

    “deslop” is an agent skill created by Brian Lovin designed to remove AI-generated code slop from Git branches. It inspects branch diffs against the main branch to eliminate unnatural comments, redundant error handling, and improper type casts.

    AI & LLMs· Tool

  • X post:Miles Cranmer

    Ponytail: Agent Skill Against Overengineered AI Code

    Miles Cranmer highlights the open-source repository 'ponytail' as an effective prompt-based skill to prevent AI coding agents from generating bloated solutions. The project guides agents towards minimal code and native platform features instead of redundant dependencies.

    1.5kbookmarks47.5kviews

    AI & LLMs· Tool

  • X post:Meng To

    no-ai-slop: Skill removes repetitive AI writing patterns

    Meng To shares a workflow to counter generic AI writing, highlighting Peter Yang's open-source repository 'no-ai-slop', which strips more than 20 repetitive LLM clichés and robotic phrases from text.

    1.8kbookmarks126.6kviews

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.