refactor
Skill157 starsChanged 33 days agoMITView on GitHub
Safely restructures existing code while preserving behavior through impact analysis and TDD. User-invoked entry point via /refactor; not for autonomous or subagent use.
195 other projects use a version of this.
Adopted by
Most recently taken up by
- mannobeats/hyper-tastetheir own version, first seen Nov 16, 2026
- GoBeromsu/craft-skillstheir own version, first seen Nov 16, 2026
- erikperttu/steering-coding-agentstheir own version, first seen Nov 16, 2026
- chuckplayer/claude-agent-packtheir own version, first seen Nov 16, 2026
- Archont561/skillstheir own version, first seen Nov 15, 2026
- nazmirket/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use ascii-diagram, debug-fix and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SethGammonSkillascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
Also in 4 projects that use this
zebbernSkilldebug-fix
Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)
Also in 4 projects that use this
parcadeiSkillagent-context-isolation
Agent Context Isolation
Also in 3 projects that use this
parcadeiSkillagentica-infrastructure
Reference guide for Agentica multi-agent infrastructure APIs
Also in 3 projects that use this
- +8 more from parcadei
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- github/awesome-copilot★ 41ksame name
- unkeyed/unkey★ 5.5ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- adobe/S3Mock★ 1.2ksame name
- SethGammon/Citadel★ 927same name
- poshan0126/dotclaude★ 871same name
- JordanCoin/codemap★ 715same name
- membrane/api-gateway★ 658same name
185 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository68 other files it gives its agents.
- github-pages/agents.mdAGENTS.md
- adrSkill
- agent-protocolsSkill
- angular-idiomsSkill
- api-documentationSkill
- auditSkill
- axum-idiomsSkill
- browser-automationSkill
- bugfixSkill
- chaos-testingSkill
- ci-cdSkill
- cli-developmentSkill
- code-reviewSkill
- cpp-idiomsSkill
- csharp-idiomsSkill
- data-engineeringSkill
- debugging-protocolSkill
- django-idiomsSkill
- dotnet-idiomsSkill
- elixir-idiomsSkill
- embedded-systemsSkill
- feature-flagsSkill
- flutter-idiomsSkill
- frontend-designSkill
- git-commit-integritySkill
- go-idiomsSkill
- guardrailsSkill
- hono-idiomsSkill
- incident-responseSkill
- java-idiomsSkill
- javascript-idiomsSkill
- kotlin-idiomsSkill
- laravel-idiomsSkill
- logging-implementationSkill
- ml-engineeringSkill
- mobile-designSkill
- mobile-testingSkill
- nextjs-idiomsSkill
- parallel-dispatchSkill
- payment-integrationSkill
- perf-optimizationSkill
- perf-optimizeSkill
- php-idiomsSkill
- postgres-idiomsSkill
- python-idiomsSkill
- rails-idiomsSkill
- react-idiomsSkill
- refactoring-patternsSkill
- research-methodologySkill
- ruby-idiomsSkill
- rust-idiomsSkill
- security-auditSkill
- sequential-thinkingSkill
- spring-boot-idiomsSkill
- sql-idiomsSkill
- structured-specSkill
- supply-chain-securitySkill
- swift-idiomsSkill
- testability-patternsSkill
- test-e2eSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 0 are common, 6 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 68
Before starting, you MUST:
- Very specific: line 70
Read architectural-pattern.md and project-structure.md
- Very specific: line 71
Read rule-priority.md for conflict resolution
- Very specific: line 76
Set Mode: Use task_boundary to set mode to PLANNING
- Distinctive: line 82
If decision involves trade-offs, create an ADR using the ADR Skill
- Very specific: line 88
Set Mode: Use task_boundary to set mode to EXECUTION
- Distinctive: line 91
Ensure existing tests pass: before making any change
- Distinctive: line 94
Add new tests: if the refactoring exposes untested behavior
- Distinctive: line 99
Key principle: Never break the build for more than one step at a time.
- Very specific: line 102
Set Mode: Use task_boundary to set mode to VERIFICATION
- Distinctive: line 104
Run the full validation suite: quality checks per idiom skill, all tests, build check
- Very specific: line 107
If applicable, run E2E tests per browser-automation skill
- Very specific: line 110
Commit with type refactor(<scope>): <description> per @git-workflow-principles.md
“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Refactor Skill
Entry-point guard: This is a user-invoked command skill (
/refactor). If you are a spawned subagent, do NOT execute this skill — return to your assigned scope card.
Purpose
Safely restructure existing code while preserving behavior. Uses a different mindset than greenfield feature development: understand first, then change structure.
Requirement Elicitation
Determine refactoring source before proceeding:
Path A — Human-Specified
User provides a specific, actionable target:
- ✅
/refactor extract storage interface in task feature - ✅
/refactor split user handler into separate auth handler - ✅
/refactor migrate callbacks to async/await in notification service→ Proceed directly to Phase 1
Path B — Tool-Driven
User references a static analysis tool as the requirement source:
- ✅
/refactor from-deepsource— read DeepSource MCP findings - ✅
/refactor from-clippy— parsecargo clippyoutput - ✅
/refactor from-lint— parse linter output (ESLint, golangci-lint, ruff) → Parse tool findings → present summary → user approves scope → proceed to Phase 1
Supported tools:
| Tool | Integration |
| DeepSource MCP | Read findings via deepsource MCP tools |
| cargo clippy | Parse cargo clippy --message-format json |
| golangci-lint | Parse golangci-lint run --out-format json |
| ESLint | Parse npx eslint . --format json |
| ruff | Parse ruff check . --output-format json |
| SonarQube | Read via API if available |
Path C — Discovery
User doesn't know what to refactor, or provides vague request:
- ✅
/refactor discover— audit first, then refactor - ❌
/refactor apps/backend— too vague - ❌
/refactor improve code quality— what specific issue? → Multi-agent mode (/workflow-team): Dispatch SCOUT(@scout + @reviewer, code smell audit) → Single-agent mode: Run/auditon the target area first, then use findings as input → Present findings → user approves scope → proceed to Phase 1
Vague request without path → "Run /refactor discover to find issues, or specify a target like /refactor extract storage interface in task feature."
When to Use
- Code restructuring (moving, renaming, splitting modules)
- Pattern migration (e.g., switching from callbacks to async/await)
- Dependency upgrades with breaking changes
- Addressing tech debt or architectural improvements
- Tool-driven cleanup from static analysis findings
When NOT to Use
- New features (use
/workflow-solo) - Small bug fixes (use
/bugfix) - "Find what to improve" without
/refactor discover(use/auditfirst)
Pre-Implementation Checklist
Before starting, you MUST:
- Scan
.agents/rules/directory for applicable rules - Read
architectural-pattern.mdandproject-structure.md - Read
rule-priority.mdfor conflict resolution
Phases
Phase 1: Impact Analysis
Set Mode: Use task_boundary to set mode to PLANNING
- Map the blast radius — what files, modules, and tests are affected?
- Document existing behavior — what tests currently pass? what contracts exist?
- Identify risks — can this be done incrementally or is a big-bang needed?
- Create refactoring plan in
task.mdwith incremental steps - If decision involves trade-offs, create an ADR using the ADR Skill
Skills to consider:
- Sequential Thinking — for multi-step refactoring with interdependencies
Phase 2: Incremental Change (TDD)
Set Mode: Use task_boundary to set mode to EXECUTION
For each step in the refactoring plan:
- Ensure existing tests pass before making any change
- Make one incremental change — move, rename, or restructure
- Run tests after each change — behavior must be preserved
- Add new tests if the refactoring exposes untested behavior
- Follow applicable rules:
- Architectural Patterns @architectural-pattern.md
- Code Organization Principles @code-organization-principles.md (includes circular dependency guidance)
Key principle: Never break the build for more than one step at a time.
Phase 3: Parity Verification
Set Mode: Use task_boundary to set mode to VERIFICATION
- Run the full validation suite: quality checks per idiom skill, all tests, build check
- Compare test coverage — coverage should be equal to or better than before
- Verify no behavior changes — same inputs produce same outputs
- If applicable, run E2E tests per
browser-automationskill
Phase 4: Ship
Commit with type refactor(<scope>): <description> per @git-workflow-principles.md
Completion Criteria
- Requirement source identified (Path A, B, or C)
- Impact analysis documented
- All changes made incrementally with tests passing at each step
- Full verification suite passes
- Test coverage is equal to or better than before
- Committed with
refactortype
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

