multiAI Summary Pending
code-analysis
Check if code is readable by non-developers - clear names, plain English comments, no jargon
231 stars
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/code-analysis/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/abejitsu/code-analysis/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/code-analysis/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How code-analysis Compares
| Feature / Agent | code-analysis | Standard Approach |
|---|---|---|
| Platform Support | multi | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Check if code is readable by non-developers - clear names, plain English comments, no jargon
Which AI agents support this skill?
This skill is compatible with multi.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Code Readability Checker
Analyzes code to ensure non-developers (managers, stakeholders, new team members) can understand it.
## What It Checks
- **Clear naming**: No cryptic abbreviations (usr_tkn → userToken)
- **Plain comments**: Everyday language, not technical jargon
- **Documentation**: What/Why/How for major sections
- **Comment ratio**: At least 20% of lines should be comments
## Usage
```bash
python3 analyze.py --path your-file.py --strictness lenient
```
## Example
**Bad Code** (score: 71/100):
```python
def proc(usr, tkn):
tmp = usr + tkn
return tmp * 2
```
Issues: Cryptic names, no comments, unclear purpose.
**Good Code** (score: 95/100):
```python
def process_user_authentication(username, auth_token):
"""Validate user credentials and return auth score"""
combined_credential = username + auth_token
return combined_credential * 2
```
## Known Issues
- May flag false positives in documentation files
- Works best on actual production code
- Use `--strictness lenient` to reduce noise