code-smells
Analyze code for smells, anti-patterns, and refactoring opportunities.
Skill by Hbin77
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.
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.
About
Reviews
Write a reviewNo 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
- 0.518score
qa
Hbin77
Browser QA — automation, accessibility audit, user flow verification
SkillBFreshness: BClaude Code +9 - 0.518score
refactor
Hbin77
Safe, systematic refactoring workflow — same behavior, better structure
SkillBFreshness: BClaude Code +9 - 0.518score
retro
Hbin77
Run a sprint/session retrospective to capture what worked, what didn't, and what to improve.
SkillBFreshness: BClaude Code +9 - 0.518score
design-audit
Hbin77
Audit UI code against ui-ux-pro-max UX guidelines; report by severity
SkillBFreshness: BClaude Code +9 - 0.518score
guard
Hbin77
Activate safety guard mode — restrict edit scope, confirm destructive ops
SkillBFreshness: BClaude Code +9 - 0.518score
design-system
Hbin77
Generate a MASTER design system using the ui-ux-pro-max skill
SkillBFreshness: BClaude Code +9 - 0.518score
dev
Hbin77
Full sequential dev pipeline — understand, plan, implement, verify, review
SkillBFreshness: BClaude Code +9 - 0.518score
explore
Hbin77
Explore and explain the project's architecture and structure
SkillBFreshness: BClaude Code +9 - 0.518score
extract-errors
Hbin77
Parse and analyze error logs, stack traces, and build output to identify and fix issues.
SkillBFreshness: BClaude Code +9 - 0.518score
investigate
Hbin77
Systematically diagnose a bug via structured root cause analysis
SkillBFreshness: BClaude Code +9 - 0.518score
plan
Hbin77
Analyze the project and produce a detailed implementation plan
SkillBFreshness: BClaude Code +9 - 0.515score
browse
Hbin77
Open a URL in a headless browser, screenshot, and report
SkillBFreshness: BClaude Code +9
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
- Repository
- github.com/Hbin77/codex-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Hbin77
- 0.518score
investigate
Hbin77
Systematically diagnose a bug via structured root cause analysis
SkillBFreshness: BClaude Code +9 - 0.518score
dev
Hbin77
Full sequential dev pipeline — understand, plan, implement, verify, review
SkillBFreshness: BClaude Code +9 - 0.518score
explore
Hbin77
Explore and explain the project's architecture and structure
SkillBFreshness: BClaude Code +9 - 0.518score
extract-errors
Hbin77
Parse and analyze error logs, stack traces, and build output to identify and fix issues.
SkillBFreshness: BClaude Code +9 - 0.518score
design-system
Hbin77
Generate a MASTER design system using the ui-ux-pro-max skill
SkillBFreshness: BClaude Code +9 - 0.518score
plan
Hbin77
Analyze the project and produce a detailed implementation plan
SkillBFreshness: BClaude Code +9
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.
Cite this page
code-smells skill. Agent Mart. https://agentmart.dev/skills/hbin77-code-smells (last updated 2026-10-24)