Skip to content
Agentmart
Submit a tool

code-smells

Analyze code for smells, anti-patterns, and refactoring opportunities.

Skill by Hbin77

IndexedMIT
Write a review

Chalk Labs

Need help deploying code-smells?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hbin77-code-smells

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Analyze code for smells, anti-patterns, and refactoring opportunities. Read-only analysis, no code changes.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/code-smells

What's inside

Skill name
code-smells
Description
Analyze code for smells, anti-patterns, and refactoring opportunities. Read-only analysis, no code changes.
License
MIT
Instructions
109 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Code Smells Detection Skill

Analyze code for smells, anti-patterns, and refactoring opportunities. Read-only analysis — no code changes.

## When to Use
- Before starting a refactoring effort
- During code review to identify structural issues
- When a module "feels wrong" but you can't pinpoint why
- To assess technical debt in a specific area

## Process

1. **Determine scope**: Use `$ARGUMENTS` as target path. Default to current project root.

2. **Automated scan**: Run available tools based on project type:

   **JavaScript/TypeScript:**
   ```
   npx knip --reporter compact 2>/dev/null          # unused exports/deps
   npx depcheck 2>/dev/null                           # unused packages
   wc -l $(find <scope> -name '*.ts' -o -name '*.tsx' -o -name '*.js' -o -name '*.jsx') | sort -rn | head -20
   ```

   **Python:**
   ```
   pylint --disable=all --enable=R,C <scope> 2>/dev/null | head -30
   wc -l $(find <scope> -name '*.py') | sort -rn | head -20
   ```

   **General (any language):**
   ```
   # Largest files (complexity indicator)
   wc -l <files> | sort -rn | head -20

   # Deep nesting
   grep -rn '^\s\{12,\}' <scope> --include='*.ts' --include='*.py' | head -20

   # Magic numbers
   grep -rn '[^a-zA-Z0-9_]\([0-9]\{3,\}\)[^a-zA-Z0-9_]' <scope> | head -20

   # TODO/FIXME/HACK markers
   grep -rn 'TODO\|FIXME\|HACK\|XXX\|WORKAROUND' <scope> | head -30
   ```

3. **Manual inspection**: Read the top 5 largest files. Look for:
   - Functions > 40 lines
   - Classes > 300 lines or 10+ methods
   - Parameter lists > 5 params
   - Nested conditions > 3 levels deep
   - Duplicated code blocks (similar structure in multiple places)
   - God objects (one module importing/used by everything)

4. **Dependency check**: Grep for circular imports:
   ```
   # Map imports to find circular references
   grep -rn "import.*from\|require(" <scope> --include='*.ts' --include='*.js'
   ```

## Severity Classification

| Severity | Criteria | Action |
|----------|----------|--------|
| **Critical** | Bugs likely, blocking testability, circular deps | Fix immediately |
| **Major** | Maintainability risk, high complexity, large duplication | Plan refactoring |
| **Minor** | Style issues, small duplication, naming inconsistency | Fix opportunistically |
| **Info** | Suggestions, potential improvements | Track for later |

## Output Format

```
## Code Smell Report: [scope]

### Quick Stats
- Files scanned: N
- Largest file: [path] (N lines)
- Deepest nesting: [path:line] (N levels)
- TODO/FIXME count: N

### Findings

#### Critical (N)
- **[Smell Type]** `path/file.ts:L` — [description]
  → Suggested: [refactoring pattern]

#### Major (N)
- **[Smell Type]** `path/file.ts:L` — [description]
  → Suggested: [refactoring pattern]

#### Minor (N)
- **[Smell Type]** `path/file.ts:L` — [description]

### Hotspot Files (most smells concentrated)
1. `path/file.ts` — N findings
2. `path/file.ts` — N findings

### Recommended Next Steps
1. [Most impactful action]
2. [Second priority]
3. Run `/refactor <scope>` to execute automated refactoring
```

## Rules
- Read-only. Never modify code.
- Verify every finding with Grep before reporting — no false positives.
- If automated tools aren't available, rely on manual inspection.
- Always include file:line references for every finding.
- Sort findings by severity, then by file (group related smells together).

From Hbin77/codex-kit, MIT.

More from Hbin77/codex-kit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 7, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Hbin77

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get code-smells running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying code-smells?

CallGet help
Cite this page

code-smells skill. Agent Mart. https://agentmart.dev/skills/hbin77-code-smells (last updated 2026-10-24)