code-simplifier
Skill43 starsChanged 6 months agoMITView on GitHub
simplifies and refines code for clarity, consistency, and maintainability while preserving exact functionality. use when chatgpt needs to review, clean up, or simplify recently modified code, align code with project conventions, reduce unnecessary complexity, improve readability, or make implementation details more explicit without changing behavior.
59 other projects use a version of this.
Adopted by
Most recently taken up by
- euxx/claude-skills-for-copilottheir own version, first seen Nov 8, 2026
- aktsmm/Agent-Skillstheir own version, first seen Nov 8, 2026
- ValorVie/custom-skillstheir own version, first seen Nov 8, 2026
- ZhouYinLong-lab/Dog-Skillstheir own version, first seen Nov 8, 2026
- simonwong/skillstheir own version, first seen Nov 6, 2026
- islandhopper81/claude-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use tdd-rust, type-design-analyzer and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
FlorianBruniauxSkilltdd-rust
Also in 3 projects that use this
PaulKinlanSkilltype-design-analyzer
Analyzes type design quality focusing on encapsulation, invariant expression, usefulness, and enforcement. Provides quantitative ratings (1-10) for each dimension.
Also in 3 projects that use this
PaulKinlanSkillcomment-analyzer
Analyzes code comments for accuracy, completeness, and long-term maintainability. Identifies misleading comments, comment rot, and documentation gaps.
Also in 4 projects that use this
ufodev-ioSkillsecurity-guardian
Comprehensive security layer for all interactions with Claude: audits code, dependencies, commands, configs, and AI-generated output for vulnerabilities. Protects against prompt injection, data leaks, unsafe advice, and social engineering. Works in Cursor, Claude Code, claude.ai, and API contexts. Use always as a background security protocol in any Claude-powered environment.
Also in 3 projects that use this
SentrySkillfind-bugs
Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
Also in 3 projects that use this
tossSkillpr-triage
Classify and summarize a PR for efficient review
Also in 3 projects that use this
- +1 more from PaulKinlan
Other versions59 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 59
- rtk-ai/rtk★ 86ksame name
- tisfeng/Easydict★ 15ksame name
- elie222/inbox-zero★ 13ksame name
- getsentry/skills★ 1.1ksame name
- Azure/azqr★ 799same name
- DoubleML/doubleml-for-py★ 798same name
- deadlock-mod-manager/deadlock-mod-manager★ 584same name
- microsoft/ghqr★ 528same name
- feiskyer/codex-settings★ 248same name
- wesm/middleman★ 198same name
49 more not listed
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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bubbletea-code-reviewSkill
- bubbleteaSkill
- golang-patternsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
24 rules. 0 are common, 20 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 54 edited versions we read keep these.
20
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Do not change features, outputs, side effects, or observable behavior.
- Distinctive: line 14
Do not broaden scope unless the user explicitly asks for a wider review.
- Distinctive: line 18
Prefer refining the code that was just written or edited.
- Distinctive: line 19
Avoid unrelated cleanup in untouched areas.
- Distinctive: line 21
Prefer explicit, readable code over compact code.
- Distinctive: line 24
Avoid clever one-liners when a straightforward structure is easier to read.
- Very specific: line 25
Avoid nested ternary operators.
- Distinctive: line 29
When the repository or provided guidance includes project standards such as CLAUDE.md, follow them closely.
- Distinctive: line 33
Use ES modules with proper import sorting and explicit extensions where required.
- Very specific: line 34
Prefer the function keyword over arrow functions when that is the project standard.
- Distinctive: line 35
Add explicit return type annotations for top-level functions when the project expects them.
- Very specific: line 36
Follow established React component patterns with explicit Props types.
- Very specific: line 37
Use the repository’s preferred error-handling patterns and avoid introducing unnecessary try/catch.
- Distinctive: line 40
If no project standard is available, preserve the local style of the surrounding code while still simplifying it.
- Distinctive: line 44
Look for opportunities to:
- Distinctive: line 51
remove comments that only restate obvious code behavior
- Distinctive: line 53
keep helpful abstractions that improve organization
- Distinctive: line 55
Do not simplify in ways that:
- Distinctive: line 61
remove abstractions that help structure the codebase
- Distinctive: line 68
Check for project-specific conventions from repository guidance and nearby code.
- Distinctive: line 78
keep edits scoped and intentional
- Distinctive: line 80
avoid noisy reformatting unrelated to the simplification
- Distinctive: line 81
prefer a few high-confidence improvements over broad cosmetic churn
- Distinctive: line 83
When summarizing your work:
“Common” is measured: kept by at least 6 in 10 of the 54 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Refine recently modified code for clarity, consistency, and maintainability while preserving exact functionality.
Core behavior
Preserve behavior exactly.
- Do not change features, outputs, side effects, or observable behavior.
- Change how the code is written, not what it does.
- Do not broaden scope unless the user explicitly asks for a wider review.
Focus on code that was recently modified or touched in the current session.
- Prefer refining the code that was just written or edited.
- Avoid unrelated cleanup in untouched areas.
Prefer explicit, readable code over compact code.
- Choose clarity over brevity.
- Avoid clever one-liners when a straightforward structure is easier to read.
- Avoid nested ternary operators. Use
if/elsechains orswitchstatements for multiple conditions.
Apply project conventions
When the repository or provided guidance includes project standards such as CLAUDE.md, follow them closely.
Common conventions to apply when present:
- Use ES modules with proper import sorting and explicit extensions where required.
- Prefer the
functionkeyword over arrow functions when that is the project standard. - Add explicit return type annotations for top-level functions when the project expects them.
- Follow established React component patterns with explicit
Propstypes. - Use the repository’s preferred error-handling patterns and avoid introducing unnecessary
try/catch. - Preserve existing naming conventions unless renaming clearly improves consistency and does not increase scope.
If no project standard is available, preserve the local style of the surrounding code while still simplifying it.
What to improve
Look for opportunities to:
- reduce unnecessary nesting
- remove redundant abstractions
- eliminate duplicated logic when the result is clearer
- consolidate closely related logic
- improve variable, function, and component names when that materially improves readability
- remove comments that only restate obvious code behavior
- make control flow easier to follow
- keep helpful abstractions that improve organization
Do not simplify in ways that:
- reduce clarity
- make debugging harder
- combine too many concerns into one function or component
- replace readable code with dense shorthand
- remove abstractions that help structure the codebase
Review process
Use this workflow:
- Identify the code that was recently modified.
- Check for project-specific conventions from repository guidance and nearby code.
- Find the highest-value simplifications that preserve behavior.
- Apply small, clear refinements.
- Re-check that functionality remains unchanged.
- Report only meaningful changes that affect readability, structure, or maintainability.
Output expectations
When making changes:
- keep edits scoped and intentional
- preserve public interfaces unless the same interface can be expressed more clearly without behavioral change
- avoid noisy reformatting unrelated to the simplification
- prefer a few high-confidence improvements over broad cosmetic churn
When summarizing your work:
- briefly explain the significant simplifications
- mention any project conventions you applied
- note any areas you intentionally left unchanged to avoid altering behavior
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.

