code-degunker
code-degunker is a Refactoring & code quality skill for AI agents, published by zocomputer in the skills repository on GitHub. Skillspace rates code-degunker F (42/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Identify and fix AI-generated code anti-patterns: incomplete implementations, TODO placeholders, over-engineering, hallucinated APIs, missing error handling, over-defensive code, security vulnerabilities, performance anti-patterns, code bloat, type workarounds, dead code, magic numbers, inconsistent patterns, and poor architecture. Use when asked to "clean up", "degunk", "deslop", review, audit, or harden code. Also triggers on "is this code any good", "make this production-ready", "this feels AI-generated", "fix the code smell", "remove the slop", or "this code is a mess". Covers 27 anti-patterns across architecture, logic, security, performance, completeness, style, and reliability. Supports full file review and branch diff review modes.
- Grade
- F
- Quality
- 42 / 100
- Safety
- Risky
- GitHub stars
- 44
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 52 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- references sensitive credential env
- dynamic code execution (eval/exec)
- reads environment variables
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.