Systematic Code Refactoring
luongnv89/claude-howto
Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
$ npx skills add nyldn/claude-octopus --skill skill-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nyldn/claude-octopus skill-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-audit .claude/skills/skill-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skill-audit" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-audit into .claude/skills/skill-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nyldn/claude-octopus/tree/main/skills/skill-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nyldn/claude-octopus --skill skill-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nyldn/claude-octopus skill-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-audit .agents/skills/skill-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-audit" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-audit into .agents/skills/skill-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nyldn/claude-octopus --skill skill-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nyldn/claude-octopus skill-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-audit .cursor/skills/skill-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skill-audit" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-audit into .cursor/skills/skill-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nyldn/claude-octopus.git --path skills/skill-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nyldn/claude-octopus --skill skill-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nyldn/claude-octopus skill-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-audit .gemini/skills/skill-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skill-audit" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-audit into .gemini/skills/skill-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nyldn/claude-octopus skill-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nyldn/claude-octopus --skill skill-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-audit .github/skills/skill-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skill-audit" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-audit into .github/skills/skill-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nyldn/claude-octopus --skill skill-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nyldn/claude-octopus skill-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nyldn/claude-octopus.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-audit .opencode/skills/skill-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skill-audit" agent skill from https://github.com/nyldn/claude-octopus/tree/main/skills/skill-audit into .opencode/skills/skill-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skill-auditAudit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
Skill Audit is an agent skill from nyldn/claude-octopus. Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Development, covering Technical debt. The repository describes itself as: Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship. The licence is MIT.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4d152db. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Skill Audit loads about 3.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 547 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from nyldn/claude-octopus at commit 4d152db, republished under its MIT licence (© nyldn). 547 words, ~3,174 tokens.
.claude/skills/skill-audit/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than
/octo:*slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, seeskills/blocks/codex-host-adapter.md.
Load skills/blocks/engineering-method-selection.md from the installed plugin
and apply only the methods relevant to this task. Preserve this entry point's
execution contract and output format. Read referenced skills as instructions;
do not invoke the current command recursively or add provider calls from a seat.
Comprehensive, methodical auditing to find issues, inconsistencies, and broken features across a codebase.
Core principle: Define scope → Create checklist → Execute systematically → Report findings → Prioritize fixes.
For architecture simplification, load
skills/blocks/architecture-simplification.md. Pin the revision, inspect recent
churn and representative callers, then apply the deletion test. Do not recommend
removing a small wrapper when it centralizes a security, cleanup, precedence, or
failure invariant. A simplify verdict needs source evidence, a concrete caller,
and migration and rollback steps.
Use this skill when user wants to:
Do NOT use for:
**Audit Objectives:**
What to audit: [app features, code patterns, specific issues]
Why auditing: [what prompted this, what problem are we solving]
Scope: [entire app, specific module, particular feature set]
Depth: [surface-level or deep inspection]Use AskUserQuestion if needed:
**Audit Focus:**
Which aspects should I audit?
1. Functional - Do features work as expected?
2. Consistency - Are patterns applied uniformly?
3. Completeness - Are implementations finished?
4. Quality - Is code maintainable?
5. User-facing - Does UI/UX work correctly?
6. Integration - Do components work together?**Audit Plan**
**Areas to Cover:**
1. [Area 1: e.g., All form submissions]
2. [Area 2: e.g., All API endpoints]
3. [Area 3: e.g., All button states]
4. [Area 4: e.g., All error handling]
**Methodology:**
- [ ] Identify all instances
- [ ] Test each systematically
- [ ] Document findings
- [ ] Categorize by severity
- [ ] Propose fixes
**Estimated Coverage:** [X components, Y files, Z features]Use Glob and Grep to find all relevant code:
**Finding Audit Targets:**
Searching for: [pattern/feature]
Method: [glob pattern or grep query]
**Found:**
1. [File 1:line]
2. [File 2:line]
3. [File 3:line]
...
N. [File N:line]
Total instances: [N]**Audit Checklist:**
- [ ] Item 1: [component/feature to check]
- Location: [file:line]
- Expected: [what should happen]
- Test: [how to verify]
- [ ] Item 2: [component/feature to check]
- Location: [file:line]
- Expected: [what should happen]
- Test: [how to verify]
...
Total items to audit: [N]Use task plan tool to track audit progress.
For each item:
**Auditing Item [N]/[Total]: [Description]**
**Location:** [file:line]
**Check 1: [Test name]**
- Expected: [what should happen]
- Method: [how to test - code review, runtime check, etc.]
- Result: ✓ Pass / ❌ Fail
- Evidence: [what you observed]
**Check 2: [Test name]**
- Expected: [what should happen]
- Method: [how to test]
- Result: ✓ Pass / ❌ Fail
- Evidence: [what you observed]
**Overall Status:** ✓ Pass / ⚠️ Issues Found / ❌ Broken
**Issues:**
[If any issues, list them here]
Audit Progress:
✓ [1/50] User login form
✓ [2/50] Password reset form
⚠️ [3/50] Registration form (issues found)
❌ [4/50] Contact form (broken)
⚙️ [5/50] Newsletter signup (in progress)
- [6/50] Survey form
...**Audit Findings Summary**
**Critical Issues (Broken Functionality):**
1. [Issue 1]
- Location: [file:line]
- Impact: [what's broken]
- Severity: Critical
2. [Issue 2]
- Location: [file:line]
- Impact: [what's broken]
- Severity: Critical
**Major Issues (Degraded Functionality):**
1. [Issue 1]
- Location: [file:line]
- Impact: [what's wrong]
- Severity: Major
**Minor Issues (Inconsistencies/Polish):**
1. [Issue 1]
- Location: [file:line]
- Impact: [what's inconsistent]
- Severity: Minor
**Passed Checks:**
- [N] items fully functional
- [List if relevant]**Audit Statistics**
Total Items Audited: [N]
✓ Passed: [N] ([X%])
⚠️ Issues Found: [N] ([X%])
❌ Broken: [N] ([X%])
**By Category:**
- Critical: [N]
- Major: [N]
- Minor: [N]
**Coverage:**
- Files reviewed: [N]
- Components tested: [N]
- Code paths verified: [N]**Recommended Fix Priority:**
**Phase 1: Critical Fixes (Do First)**
1. [Issue - file:line]
- Why critical: [reason]
- Estimated effort: [time]
2. [Issue - file:line]
- Why critical: [reason]
- Estimated effort: [time]
**Phase 2: Major Fixes (Do Next)**
1. [Issue - file:line]
- Impact: [description]
- Estimated effort: [time]
**Phase 3: Minor Fixes (Nice to Have)**
1. [Issue - file:line]
- Impact: [description]
- Estimated effort: [time]
**Total Estimated Effort:** [sum of all fixes]**Next Steps:**
I found [N] issues during the audit.
Would you like me to:
1. Fix all critical issues now (estimated [time])
2. Fix issues one category at a time (critical → major → minor)
3. Let you review findings first, then decide what to fix
4. Create detailed tickets/todos for each issue
What's your preference?User: "Create a process to audit and check the entire app for things that might be broken"
Implementation:
**Phase 1: Scope**
- Audit all user-facing features
- Check for runtime errors
- Verify expected behavior
**Phase 2: Discovery**
- List all features (from routes, components, docs)
- Create comprehensive checklist
**Phase 3: Execute**
- Test each feature systematically
- Document working vs broken
**Phase 4: Report**
- Critical: Features that crash
- Major: Features that work incorrectly
- Minor: Features with UX issues
**Phase 5: Fix**
- Prioritized remediation planUser: "Find all instances of direct DOM manipulation and check if they should use React state"
Implementation:
**Phase 1: Scope**
- Audit: Direct DOM manipulation patterns
- Goal: Identify React anti-patterns
**Phase 2: Discovery**
- Grep for: document.querySelector, getElementById, etc.
- Found: [N] instances
**Phase 3: Execute**
- Check each instance:
- Is there a good reason for direct DOM?
- Should it use React state instead?
- Is it causing bugs?
**Phase 4: Report**
- List instances that should migrate to React
- List instances that are fine as-is
**Phase 5: Fix**
- Refactor problematic instancesUser: "Audit the app for button style consistency"
Implementation:
**Phase 1: Scope**
- Audit: All button elements
- Goal: Ensure consistent styling
**Phase 2: Discovery**
- Find all buttons in codebase
- Identify button component(s)
**Phase 3: Execute**
- Check each button against style guide
- Document inconsistencies
**Phase 4: Report**
- Buttons using correct component: [N]
- Buttons with inconsistent styles: [N]
- Buttons using deprecated patterns: [N]
**Phase 5: Fix**
- Standardize all buttons to design systemAudit found a broken feature?
→ Use skill-debug to investigate root cause
→ Use systematic debugging to fixAudit found UI inconsistencies?
→ Use skill-visual-feedback to fix visual issues
→ Ensure consistency across appLarge audit with many items?
→ Use skill-iterative-loop to process in batches
→ Loop through sections of the appAudit includes security concerns?
→ Delegate security-specific checks to skill-security-audit
→ Use skill-audit for functional checksGood:
Auditing all form submissions:
1. Login form
2. Registration form
3. Password reset form
4. Contact form
5. Newsletter signup
...
(Methodical, complete)Poor:
Checking some forms:
- Login form
- Maybe that contact thing
- Whatever else I find
(Random, incomplete)For each audit item, record:
Group findings into meaningful categories:
Good:
Issue: Registration form submit button doesn't work
Location: src/components/RegisterForm.tsx:45
Root cause: onClick handler missing
Fix: Add onClick={handleSubmit}
Effort: 5 minutesPoor:
Issue: Some button broken somewhere
Fix: Fix it| Action | Why It's Wrong |
|---|---|
| Skip creating checklist | Will miss things, duplicate work |
| Test randomly without system | Incomplete coverage |
| Not documenting findings | Can't prioritize or fix later |
| Audit without clear criteria | Don't know what "pass" means |
| Fix while auditing | Confuses audit with remediation |
| Ignore patterns | Miss systemic issues |
**Feature:** [Name]
**Location:** [file:line]
**Tests:**
- [ ] Feature loads without errors
- [ ] Feature responds to user input
- [ ] Feature displays correct data
- [ ] Feature handles errors gracefully
- [ ] Feature works on mobile
- [ ] Feature is accessible
**Result:** ✓ Pass / ⚠️ Issues / ❌ Broken
**Issues:** [if any]**Pattern:** [What to check]
**Instance:** [file:line]
**Checks:**
- [ ] Follows current best practices
- [ ] Consistent with codebase
- [ ] No deprecated APIs used
- [ ] Properly typed/documented
- [ ] No obvious bugs
**Result:** ✓ Good / ⚠️ Needs update / ❌ Problematic
**Notes:** [any observations]**Component:** [Name]
**Location:** [file:line]
**Checks:**
- [ ] Uses design system components
- [ ] Follows spacing guidelines
- [ ] Uses correct colors
- [ ] Typography consistent
- [ ] Responsive design works
- [ ] States handled (hover, active, disabled)
**Result:** ✓ Consistent / ⚠️ Minor issues / ❌ Inconsistent
**Issues:** [if any]| Audit Type | Discovery Method | Check Method | Output |
|---|---|---|---|
| Functional | List features | Test each | Pass/fail report |
| Pattern | Grep for code | Review each instance | Compliant/non-compliant |
| Consistency | Find all instances | Compare to standard | Consistent/inconsistent |
| Completeness | List requirements | Verify each exists | Complete/incomplete |
Systematic audit → Complete checklist + Methodical execution + Prioritized findings
Otherwise → Missed issues + Duplicate work + No clear action planDefine scope. Create checklist. Execute systematically. Report findings. Prioritize fixes.
© nyldn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/skill-audit of nyldn/claude-octopus.
Open the folder on GitHubat commit 4d152db
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in nyldn/claude-octopus, which our catalogue first saw on October 7, 2026.
Skill Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skill Audit this skillnyldn/claude-octopus | 4.2k | 1 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Systematic Code Refactoringluongnv89/claude-howto | 42k | — | ~3k | Automated safety check: Pass | MIT | |
| Code Simplification for ego-litecitrolabs/ego-lite | 17k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Code Refactoring Workflowluongnv89/claude-howto | 42k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Cto AdvisorIbrahim-3d/orchestrator-supaconductor | 380 | 4 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Tech Debt Analyzerailabs-393/ai-labs-claude-skills | 454 | 2 repos | ~3.9k | Automated safety check: Pass | MIT |
luongnv89/claude-howto
Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.
citrolabs/ego-lite
Finds and implements evidence-backed simplifications in the ego-lite repository, such as dead code, duplicated state and speculative abstractions, without hiding behavior changes.
luongnv89/claude-howto
Guides systematic, test-backed refactoring in the style of Martin Fowler, moving through research, planning and small incremental changes with your approval at each phase.
Ibrahim-3d/orchestrator-supaconductor
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.
ailabs-393/ai-labs-claude-skills
This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability.
tailcallhq/forgecode
Finds every FIXME comment in a codebase, groups related ones across files into one task, implements the work they describe and removes the comments once it is done.
nyldn/claude-octopus
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
nyldn/claude-octopus
Thorough research across multiple sources — use for complex topics needing broad synthesis
nyldn/claude-octopus
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
nyldn/claude-octopus
Extract patterns and anatomy from URLs — use to reverse-engineer content strategies from live pages
nyldn/claude-octopus
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
nyldn/claude-octopus
Present options with trade-offs for informed decision-making — use when choosing between approaches
Categories
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review. Skill Audit is an agent skill from nyldn/claude-octopus.
Skill Audit fits situations like: tech debt review; tasks that involve Technical debt.
Run `npx skills add nyldn/claude-octopus --skill skill-audit -a claude-code`. Or copy the skill folder (skills/skill-audit in nyldn/claude-octopus) into .claude/skills/skill-audit in your project. Claude Code loads it when a task matches its description.
Run `npx skills add nyldn/claude-octopus --skill skill-audit -a codex`. Or copy the skill folder (skills/skill-audit in nyldn/claude-octopus) into .agents/skills/skill-audit in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nyldn/claude-octopus --skill skill-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-audit, .gemini/skills/skill-audit, .github/skills/skill-audit and .opencode/skills/skill-audit in your project.
SKILL.md names no scripts, command-line tools or credentials: Skill Audit is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Skill Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Skill Audit: Systematic Code Refactoring (luongnv89/claude-howto, 42k stars), Code Simplification for ego-lite (citrolabs/ego-lite, 17k stars), Code Refactoring Workflow (luongnv89/claude-howto, 42k stars) and Cto Advisor (Ibrahim-3d/orchestrator-supaconductor, 380 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
nyldn (a GitHub user) maintains it in nyldn/claude-octopus, which has 4,182 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 7, 2026.
Source: nyldn/claude-octopus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.