Skills
code-humanizer
by LeonardNJU
humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions.
Our verdict
We have not reviewed code-humanizer yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About code-humanizer
code-humanizer is an agent skill that cleans AI-generated code by removing duplicated helpers, try-import fallbacks, broad excepts, and speculative abstractions. It is test-gated and behavior-preserving, ensuring changes do not alter functionality.
Best for
Developers using AI coding assistants who want cleaner, more maintainable code without manual cleanup.
Use cases
- Refactor AI-generated code to reduce redundancy
- Remove unnecessary fallback patterns and broad exception handling
- Simplify speculative abstractions while keeping tests passing
Notes
94 stars on GitHub. Last updated 2026-07-26. Licensed MIT.
Pros
- Test-gated, reducing risk of breaking behavior
- Targets common AI code patterns specifically
- Lightweight skill, easy to integrate into agent workflows
Cons
- Requires existing tests to validate changes
- May not handle all code styles or languages
- Limited to the patterns it is designed to detect
Key facts
What we have checked
- Days since the last commit
- 111
- GitHub forks
- 4
- GitHub stars
- 95
- Open issues
- 0
- Releases in the last 90 days
- 0
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How code-humanizer is growing
90 to 95
Health and security
Is code-humanizer looked after, and what do its setup files show
Health score
38 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 22.7 of 30 | Last push 111 days ago |
| Releases | 0 of 15 | 0 releases in 90 days |
| Issue replies | Not counted | The latest check has no issue response reading (fewer than 3 measured issues, or issues switched off) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | Not counted | MCP servers only |
Security check static checks
100 out of 100
- Note 1 of 1 packages are not pinned to one version, so only the malicious packages list was checked for them, not version advisories.
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
code-simplification
addyosmani
Production-grade engineering skills for AI coding agents.
safe-refactor
JuliusBrussee
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
surgical-patch
JuliusBrussee
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
tdd
mattpocock
Skills for Real Engineers. Straight from my .agents directory.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.