Unslop Code

Roast and strip AI code slop: narrator comments, vacuous tests, over-abstraction

Tested · Works

Test report

Verdict
Tested · Works
Score
8.8/10
Tested
Jul 19, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · b978134

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 19, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran live against a 37-line Python file planted with six slop patterns and it caught every one: import-explainer comments, an assertion-free test, a single-implementation Factory, 'utilizes a sophisticated paradigm' jargon, an 'I hope this helps!' chatbot line, and a time.sleep(5) wait, all organized into a severity-ranked report with a numbered fix menu. The no-skill baseline flagged the obvious comment noise but did not name the chatbot-bleed or the sleep-wait as distinct issues. A tidy, self-contained prompt skill that is honest about ignoring security and performance.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 7/10
  • Docs & honesty 5/5

What Unslop Code does

A code-review skill that scans a diff, file, or pasted code for AI-generated slop and reports it as a severity-ranked, categorized roast with a numbered fix menu. Triggers on requests to clean up AI comments, detect slop, or de-clutter code. Covers narrator comments, assertion-free tests, needless abstraction, chatbot bleed, and sleep-based waits; explicitly ignores security and performance.

How to install Unslop Code

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Unslop Code

  • /unslop-code Roast and strip AI code slop: narrator comments, vacuous tests, over-abstraction

It also activates on plain-language prompts like these:

  • Review this file for AI slop and clean up the noisy comments.
  • Is this code full of AI slop? Give me a numbered fix menu.
  • Strip the narrator comments and vacuous tests from this diff.

Frequently asked questions

Is the Unslop Code skill free?
Yes. The skill itself is free from Erlemar/dswok. SkillProof publishes the install command and an independent test verdict at no cost.
Does Unslop Code work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 19, 2026. Verdict: Tested · Works. Ran live against a 37-line Python file planted with six slop patterns and it caught every one: import-explainer comments, an assertion-free test, a single-implementation Factory, 'utilizes a sophisticated paradigm' jargon, an 'I hope this helps!' chatbot line, and a time.sleep(5) wait, all organized into a severity-ranked report with a numbered fix menu. The no-skill baseline flagged the obvious comment noise but did not name the chatbot-bleed or the sleep-wait as distinct issues. A tidy, self-contained prompt skill that is honest about ignoring security and performance.
What is the Unslop Code SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Unslop Code?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Unslop Code with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.