oprogramadorreal/optimus-claude / skills/refactor
refactor
VerifiedRefactors code toward project-guideline compliance and testability (so /optimus:unit-test can safely increase coverage) across four analysis lenses, fanned out to parallel agents when the scope warrants it. Supports "testability" or "guidelines" focus plus flexible scoping. Read-only until the user approves the plan; applied changes stay local. Use after /optimus:init, before /optimus:unit-test; for an iterative loop, use /optimus:deep refactor.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 4.8 KB |
| SKILL.md | skill md | 10.7 KB |
| agents/code-simplifier.md | markdown | 1.1 KB |
| agents/consistency-analyzer.md | markdown | 1.4 KB |
| agents/guideline-reviewer.md | markdown | 926 B |
| agents/openai.yaml | config | 198 B |
| agents/shared-constraints.md | markdown | 1016 B |
| agents/testability-analyzer.md | markdown | 1.3 KB |
agents/shared-constraints.md
View on GitHub# Refactor Agent Constraints
Read `$CLAUDE_PLUGIN_ROOT/references/shared-agent-constraints.md` first — it applies in full. Refactor addendums:
- Analyze the provided files, or the source files in the provided areas.
- Scope-expansion carve-out: cross-file consistency findings are a primary goal of refactor — report them even when the related file lies outside the original scope (the base rule's 3-extra-files-per-finding limit still applies).
## Output format
Report each finding in this exact format. Your agent prompt defines the **Category** values and any fields it adds or replaces.
- **File:** file:line
- **Category:** [per agent prompt]
- **Confidence:** High | Medium | Low — report a Low as Low; never round it up to Medium or drop the finding.
- **Guideline:** [which project guideline this addresses]
- **Issue:** [what is wrong and why it matters]
- **Current:**
```
[relevant snippet — max 5 lines]
```
- **Suggested:**
```
[fix or refactoring approach — max 5 lines]
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |