en un clic
refactor
Safely refactor code with test-driven approach.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Menu
Safely refactor code with test-driven approach.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Write a structured handoff at session end. Preserves context so the next agent can resume without human briefing. Invoke before ending any feature session longer than 30 minutes.
Multi-perspective code review against project standards with P1/P2/P3 severity classification. Works in Claude Code (Agent + optional GitHub MCP) and Cursor (Task subagents + gh/git). Use when the user invokes /review, asks for a PR or diff review, or wants a standards-aligned review with severity tags.
Multi-perspective code review (P1/P2/P3) for Cursor: inline checklists plus three parallel Task subagents (perf-auditor, security-reviewer, simplicity-reviewer with combined data-integrity prompt). Use when the user invokes /review, asks for a PR review, or wants repo-standard findings with severity.
Create well-formatted git commits following conventional commit standards.
Red→green→refactor discipline for new behavior — forces a failing test before implementation and a passing test before any claim of done.
Create or manage a git worktree for isolated parallel development — lets multiple agents work in the repo simultaneously without branch collisions.
| name | refactor |
| description | Safely refactor code with test-driven approach. |
Safely refactor code with test-driven approach.
/refactor <target> [--scope <scope>] [--dry-run]
target: File, function, or pattern to refactor--scope: Limit refactoring scope (function, file, module)--dry-run: Show planned changes without executingWhen this skill is invoked:
Autonomy:
Safety:
Quality:
Verify tests exist:
{test_command} tests/ --collect-only
If tests don't exist for the target:
Run tests to establish baseline:
{test_coverage_command}
Record:
Plan the refactoring:
--dry-run, present plan and stopExecute refactoring in small steps: For each change:
Verify final state:
{test_coverage_command}
Ensure:
Present changes:
Extract Function/Method:
# Before
def process():
# 50 lines of code
# After
def process():
step1()
step2()
step3()
Remove Duplication:
# Before: Same code in 3 places
# After: Single shared function
Simplify Conditionals:
# Before
if x and y and z:
if a or b:
...
# After
if should_process(x, y, z, a, b):
...
Rename for Clarity:
# Before
def proc(d):
# After
def process_user_data(user_data):
$ /refactor src/{project}/services/user --scope module
🔄 Refactoring: src/{project}/services/user
📋 Pre-refactor state:
- Tests: 24 passing
- Coverage: 95%
- Duration: 1.2s
📝 Planned changes:
1. Extract duplicate validation logic → shared validator
2. Rename process() → process_user_request()
3. Simplify nested conditionals in update()
🔧 Executing refactoring...
Step 1: Extract validation logic
✅ Tests pass (24/24)
Step 2: Rename process()
✅ Tests pass (24/24)
Step 3: Simplify conditionals
✅ Tests pass (24/24)
📋 Post-refactor state:
- Tests: 24 passing
- Coverage: 96% (+1%)
- Duration: 1.1s (-0.1s)
✅ Refactoring complete!
Changes made:
- src/{project}/services/user: Simplified, renamed functions
- src/{project}/utils/validators: New shared validation module
- tests/unit/test_user: Updated imports
Commit suggestion:
git commit -m "refactor(user): extract validation, improve naming"