review-readability
Skill0 starsChanged 45 days agoMITView on GitHub
Review code for readability — refactor, rename, clarify and
2 other projects use a version of this.
Adopted by
Most recently taken up by
- desbma/agent-skillstheir own version, first seen Oct 27, 2026
- moiznoorani/skillstheir own version, first seen Oct 11, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- desbma/agent-skills★ 1same name
- moiznoorani/skills★ 1same 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 repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- align-withSkill
- discussSkill
- github-prSkill
- review-modernizeSkill
- review-releaseSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Check all references, such as call-sites, and numbers, such as line counts, before making claims.
- Distinctive: line 27
If the code is already in good shape, say so instead of wasting our time with superficial improvements just to think you did your job.
≈ “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
Scope: $ARGUMENTS — if that's empty, the whole codebase.
You're looking for opportunities to improve the readability of code in scope. This is a quest to refactor, rename, clarify and simplify the codebase structure and execution flow. Nothing about the implementation is sacred, you can freely suggest major changes. Raising versions of dependencies is possible as well, but you need to justify that, You're not looking for bugs. You're not looking to add features. Rather make the code shorter than longer if you can.
First read everything in scope end-to-end before forming any opinion. Check all references, such as call-sites, and numbers, such as line counts, before making claims. You need to be sure that the changes you suggest don't introduce any relevant changes in behaviour. Some changes in corner cases can be fine, but state it clearly and let me approve it. If the code is already in good shape, say so instead of wasting our time with superficial improvements just to think you did your job.
Examples of what to look for:
- Abstractions with a single user
- Comments that restate the code or contradict it
- Data converted back and forth between representations
- Dead code and write-only state
- Defensive checks for things that can't happen
- Hand-rolled versions of what the standard library provides
- Helpers and constants extracted but used once
- Inconsistent data structures passed around
- Inconsistent function order
- Names that mislead
- One feature scattered across files
- One thing kept in several variables
- Overlong functions and deep nesting
- Parameters, options and branches that always take the same value
- Same concept under different names
- The same logic in >2 places
- Using outdated language or library features
Report your findings ordered by payoff. Classify payoff as "low", "medium" or "high". Only include "optional" suggestions if there's nothing you recommend applying. Propose a series of commits to fix the findings. For clarity, list your findings lettered A, B, etc. and commits numbered 1, 2, etc. One concern per commit, ordered so that each builds on the last: mechanical renames and single extractions first, structural splits after, pure moves last. Wait for user input. If given the go-ahead, do the commits one-by-one reporting your progress clearly as for example "Next commit 5/7". Follow the repo's and user's commit rules exactly. If they require approval per commit, show the full message and wait each time, however many that is.
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.