slop
Skill127 starsChanged 27 days agoMITView on GitHub
Remove AI-generated code slop from git diffs to maintain code quality
1 other project uses a version of this.
Adopted by
Most recently taken up by
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- davidanthonyn/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository38 other files it gives its agents.
- AGENTS.mdAGENTS.md
- wiki/AGENTS.mdAGENTS.md
- wiki/CLAUDE.mdCLAUDE.md
- accountable-engineeringSkill
- adrSkill
- babysit-prSkill
- blindspot-passSkill
- capability-experimentsSkill
- codemapSkill
- code-quality-reviewSkill
- code-reviewSkill
- commit-atomicSkill
- context-discoverySkill
- diagnosing-bugsSkill
- doc-searchSkill
- docs-updateSkill
- draft-pull-requestSkill
- git-contextSkill
- handoffsSkill
- implementation-loggerSkill
- implement-specSkill
- llm-wikiSkill
- orchestrating-fusionSkill
- pickupSkill
- plannotator-setup-goalSkill
- portless-localSkill
- prdSkill
- pr-reviewSkill
- prSkill
- qmd-knowledgeSkill
- quiz-meSkill
- ralphSkill
- retroSkill
- security-auditSkill
- spec-interviewSkill
- tddSkill
- tmuxSkill
- visual-prSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. About 0 are common, 20 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈20
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Check the diff against a branch and remove all AI-generated slop introduced in this branch.
- Very specific: line 21
If no branch is provided, compare against main: /slop main
- Distinctive: line 36
Never change what the code does - only how it does it.
- Very specific: line 40
Follow the established coding standards from @CLAUDE.md or conventions:
- Distinctive: line 42
Use proper import sorting and file organization
- Distinctive: line 43
Follow language-specific patterns (ES modules, proper TypeScript types, etc.)
- Distinctive: line 45
Use proper error handling patterns
- Distinctive: line 56
IMPORTANT: Use switch statements or if/else chains over nested ternary operators
- Distinctive: line 64
Create overly clever solutions that are hard to understand
- Distinctive: line 66
Remove helpful abstractions that improve code organization
- Distinctive: line 85
Read the current content
- Distinctive: line 88
Check for opportunities to improve elegance and consistency
- Very specific: line 94
Remove any casts where possible
- Distinctive: line 97
Ensure all functionality remains unchanged
- Distinctive: line 123
Identify the modified sections: - Only refine code that changed in the diff
- Distinctive: line 124
Analyze for improvement opportunities: - Look for ways to enhance elegance and consistency
- Distinctive: line 125
Apply project standards: - Follow established conventions and patterns
- Distinctive: line 126
Preserve functionality: - Ensure behavior remains unchanged
- Distinctive: line 128
Document significant changes: - Only document changes that affect understanding
- Distinctive: line 132
Prefer explicit over compact - readable code beats clever code
- Distinctive: line 133
Use descriptive names - clarity over brevity
- Distinctive: line 135
Remove redundant code - eliminate duplicates
- Distinctive: line 136
Use language-appropriate patterns - follow idiomatic practices
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Remove AI Code Slop
Check the diff against a branch and remove all AI-generated slop introduced in this branch. Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.
Usage
/slop [branch-name]
- If no branch is provided, compare against main:
/slop main
What is AI Code Slop?
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
- Casts to
anyto get around type issues - Any other style that is inconsistent with the file
Core Principles
1. Preserve Functionality
Never change what the code does - only how it does it. All original features, outputs, and behaviors must remain intact.
2. Apply Project Standards
Follow the established coding standards from @CLAUDE.md or conventions:
- Use proper import sorting and file organization
- Follow language-specific patterns (ES modules, proper TypeScript types, etc.)
- Maintain consistent naming conventions
- Use proper error handling patterns
3. Enhance Clarity
Simplify code structure by:
- Reducing unnecessary complexity and nesting
- Eliminating redundant code and abstractions
- Improving readability through clear variable and function names
- Consolidating related logic
- Removing unnecessary comments that describe obvious code
- IMPORTANT: Use switch statements or if/else chains over nested ternary operators
- Choose clarity over brevity - explicit code is often better than overly compact code
4. Maintain Balance
Preserve necessary complexity — over-simplification can:
- Reduce code clarity or maintainability
- Create overly clever solutions that are hard to understand
- Combine too many concerns into single functions
- Remove helpful abstractions that improve code organization
- Prioritize "fewer lines" over readability
Process
1. Get the diff
# Compare against main branch
git diff main...HEAD --stat
# Or against specific branch
git diff $1 --stat2. Review each changed file
For each changed file:
- Read the current content
- Compare with original (before changes)
- Identify AI-generated slop patterns
- Check for opportunities to improve elegance and consistency
3. Remove slop and refine
- Remove unnecessary comments
- Simplify overly defensive code
- Remove
anycasts where possible - Restore natural code style
- Apply project-specific best practices
- Ensure all functionality remains unchanged
4. Verify
# Show remaining changes
git diff --stat
# Check tests still pass
npm testCommon Slop Patterns
- Over-commenting: Comments explaining obvious code
- Verbose error handling: Try/catch blocks where not needed
- Unnecessary type casts:
x as anyto bypass TypeScript - Defensive programming: Checks for already-validated inputs
- Redundant validation: Duplicate null/undefined checks
- Nested ternaries: Complex nested ternary operators
- Overly compact code: Dense one-liners that sacrifice readability
Refinement Guidelines
When refining code:
- Identify the modified sections - Only refine code that changed in the diff
- Analyze for improvement opportunities - Look for ways to enhance elegance and consistency
- Apply project standards - Follow established conventions and patterns
- Preserve functionality - Ensure behavior remains unchanged
- Verify improvements - The refined code should be simpler and more maintainable
- Document significant changes - Only document changes that affect understanding
Code Style Preferences
- Prefer explicit over compact - readable code beats clever code
- Use descriptive names - clarity over brevity
- Flatten deep nesting with early returns and guard clauses
- Remove redundant code - eliminate duplicates
- Use language-appropriate patterns - follow idiomatic practices
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

