
code-quality
Review, refactor, and debug code with verification before claiming done. Use when responding to review feedback, requesting a review, refactoring or reducing technical debt, root-causing a bug or failing test, or checking work before a merge, commit, or completion claim.
- Installs
- 291
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/samhvw8/dotfiles --skill code-quality- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads code-quality automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Code Quality
Systematic code improvement through review, refactoring, and debugging with verification gates.
Module Selection
| Need | Module | Reference |
|---|---|---|
| Receive Feedback | Review | references/code-review-reception.md |
| Request Review | Review | references/requesting-code-review.md |
| Verify Before Claim | Review | references/verification-before-completion.md |
| Reduce Complexity | Refactoring | references/oop-refactoring-catalog.md |
| Functional Patterns | Refactoring | references/functional-refactoring-patterns.md |
| Find Code Smells | Refactoring | references/code-smells-reference.md |
| Test Strategies | Refactoring | references/testing-strategies.md |
| Investigate Bugs | Debugging | references/systematic-debugging.md |
| Trace Root Cause | Debugging | references/root-cause-tracing.md |
| Add Validation | Debugging | references/defense-in-depth.md |
| Verify Fix | Debugging | references/verification.md |
Core Principles
YAGNI, KISS, DRY - Always honor these.
Be honest, be brutal, straight to the point, and be concise.
Technical correctness over social comfort. Verify before implementing. Ask before assuming. Evidence before claims.
Code Review
Receiving Feedback
Pattern: READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT
Rules:
- ❌ No performative agreement ("You're right!", "Great point!")
- ❌ No implementation before verification
- ✅ Restate requirement, ask questions, push back with reasoning
- ✅ YAGNI check: grep for usage before implementing suggestions
Sources:
- Human partner → Implement after understanding
- External reviewer → Verify technically before implementing
Requesting Review
When: After major features, before merge, after complex fixes
Process:
- Get SHAs:
BASE_SHA=$(git rev-parse HEAD~1),HEAD_SHA=$(git rev-parse HEAD) - Run
/code-review, passing: WHAT, PLAN, SHAs, DESCRIPTION - Fix Critical immediately, Important before proceeding, note Minor
Verification Gates
Claim a result only after running the command that proves it in this session and reading its output — a claim without that evidence is a guess.
Gate: IDENTIFY → RUN → READ → VERIFY → THEN claim
Review findings (yours or a subagent's) need four more checks before you report them:
- Guard: Name the guard you searched for on the same path, and say why it does not stop the bug.
- Intent: Search
.okf/and other project docs for the behavior. Documented as intended → a policy question, not a bug. - Origin: Before you blame a commit, run
git log -Sorgit show <sha>^:<file>. Do not infer old behavior from a commit message. - Lines: Cite line numbers you read from the file, not from an agent summary.
Refactoring
Mindset
Simplify relentlessly. Preserve behavior religiously. Measure everything.
Every refactoring: small and safe, tested immediately, measurably better.
Protocol
- Assessment - Baseline metrics, identify smells, classify debt
- Safety Net - Verify test coverage, add characterization tests
- Red-Green-Refactor - Write failing test, minimal pass, improve design
- Pattern Application - SOLID, design patterns, functional transforms
- Validation - Measure improvements, verify behavior preserved
Code Smells (5 Categories)
- Bloaters: Long Method, Large Class, Long Parameter List
- OO Abusers: Switch Statements, Temporary Field
- Change Preventers: Divergent Change, Shotgun Surgery
- Dispensables: Duplicate Code, Dead Code, Lazy Class
- Couplers: Feature Envy, Inappropriate Intimacy
Quick Patterns
OOP: Extract Method, Inline, Replace Temp with Query, Guard Clauses Functional: Map/Filter/Reduce, Pure Functions, Composition, Immutability
Debugging
Core Principle
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
Random fixes waste time and create new bugs.
The Four Techniques
1. Systematic Debugging (references/systematic-debugging.md)
- Phase 1: Root Cause Investigation
- Phase 2: Pattern Analysis
- Phase 3: Hypothesis Testing
- Phase 4: Implementation
2. Root Cause Tracing (references/root-cause-tracing.md)
Trace backward through call stack to find original trigger.
3. Defense-in-Depth (references/defense-in-depth.md)
Validate at every layer: Entry → Business logic → Environment → Debug
4. Verification (references/verification.md)
Run command. Read output. Then claim result.
Quick Reference
Bug → systematic-debugging.md (Phase 1-4)
Error deep in stack? → root-cause-tracing.md
Found root cause? → defense-in-depth.md
About to claim success? → verification.md
Red Flags
Stop if thinking:
- "Quick fix for now, investigate later"
- "Just try changing X and see"
- "It's probably X, let me fix that"
- "Should work now" / "Seems fixed"
References
Code Review
references/code-review-reception.md- Response protocolsreferences/requesting-code-review.md- Request processreferences/verification-before-completion.md- Verification gates
Refactoring
references/oop-refactoring-catalog.md- Martin Fowler's patternsreferences/functional-refactoring-patterns.md- FP transformationsreferences/code-smells-reference.md- 23 smells, 5 categoriesreferences/testing-strategies.md- Characterization tests, TDD
Debugging
references/systematic-debugging.md- Four-phase frameworkreferences/root-cause-tracing.md- Call stack analysisreferences/defense-in-depth.md- Multi-layer validationreferences/verification.md- Verification protocols
Bottom Line
- Review: Technical rigor over social performance
- Refactor: Small, safe, tested, measurable
- Debug: Root cause first, fix once
- Always: Evidence before claims
Verify. Question. Then implement. Evidence. Then claim.
FAQ
What does the code-quality skill do?
Review, refactor, and debug code with verification before claiming done. Use when responding to review feedback, requesting a review, refactoring or reducing technical debt, root-causing a bug or failing test, or checking work before a merge, commit, or completion claim.
How do I install code-quality?
Run npx skills add https://github.com/samhvw8/dotfiles --skill code-quality in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/code-quality/ (personal) or .claude/skills/code-quality/ (project).
Which AI agents can use code-quality?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is code-quality safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains code-quality?
It is published by samhvw8 in samhvw8/dotfiles. It has 291 recorded installs.
More from samhvw8/dotfiles
frontend-development
samhvw8/dotfiles
Open the skill to read its SKILL.md instructions.
3d-graphics
samhvw8/dotfiles
Open the skill to read its SKILL.md instructions.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.