Index of every page on this site: llms.txt
All skills
brianlovin avatar

/deslop

@1a9819e official
by Brian Lovinbrianlovin/agent-config377 stars
33
Run it yourself

Remove AI-generated code slop from the current branch. Use after writing code to clean up unnecessary comments, defensive checks, and inconsistent style.

Use this Skill: https://skilld.dev/gh/brianlovin/agent-config/deslop

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈40 tokens for metadata: the name and description. ≈133 when used: this file.

Description uses 2.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈162 characters, or 2.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Remove AI code slop

Check the diff against main, and remove all AI generated slop introduced in this branch.

This includes:

  • Extra comments that a human wouldn't add or is inconsistent with the rest of the file
  • Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted / validated codepaths)
  • Casts to any to get around type issues
  • Any other style that is inconsistent with the file

Report at the end with only a 1-3 sentence summary of what you changed

Source: SKILL.md on GitHub

Skill behaviors

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No alerts1mo5 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    This skill is designed to clean up AI-generated code by removing unnecessary comments and defensive checks. It processes code diffs, which could potentially contain malicious instructions if the code being reviewed was created by an untrusted source. This is a common attack surface for skills that process external text or code.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

  • Runlayer7mo

    1/1 file flagged

  • ZeroLeaks6mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 1a9819e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Dormantupdated 9 months ago

Topics

README badge

README badge for brianlovin/agent-config/deslop

What it does

Removes unnecessary comments, defensive checks, type casts, and style inconsistencies from the current Git branch by diffing against main. Targets cleanup of AI-generated code patterns that deviate from the repository's existing conventions.

Generated from the current SKILL.md.

Frequently asked

What counts as AI slop that this skill removes?
The skill targets extra comments inconsistent with the file style, over-defensive try/catch blocks and validation checks on trusted code paths, type casts to any, and other style inconsistencies introduced by AI generation.
Does this skill modify files or just report what could be changed?
The SKILL.md does not specify whether changes are applied automatically or shown for review before commit.
How does this skill determine what's slop versus legitimate code?
It compares the diff against main and relies on the AI agent to identify patterns that deviate from the existing codebase style and safety practices.

Generated from the current SKILL.md. These answers refresh after source changes.