ai-output-validation
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and…
Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.
$ npx -y skills add DevelopersGlobal/ai-agent-skills --skill refactoring --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/refactoringContext preview
The summary Claude sees to decide when to auto-load this skill.
Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct.
name: refactoring description: Safe, behavior-preserving code transformation backed by tests. Refactor with evidence, not instinct. category: review applies-to: [claude, gemini, cursor, copilot, any] version: 1.0.0
Refactoring changes the internal structure of code without changing its external behavior. The keyword is "without" — if behavior changes, it's not refactoring, it's modification. This skill enforces safe refactoring with tests as the safety net.
1. Before touching a single line: ensure there are tests covering the code to be refactored. 2. If tests are missing: add characterization tests first. These capture current behavior, not desired behavior. 3. Run the tests. They should all pass. This is your baseline.
**Verify:** Tests pass. They cover the code being refactored.
4. Make the smallest meaningful change. 5. Run tests after EVERY change — not after 10 changes. 6. If tests break: revert immediately and take a smaller step. 7. Never batch multiple refactoring changes together.
**Verify:** Tests pass after every individual change.
8. Refactoring types cannot be mixed in one step:
9. "Refactor and also fix this" is not refactoring — it's two PRs.
**Verify:** This commit does exactly one type of refactoring.
10. Run the full test suite. 11. If integration/E2E tests exist: run them too. 12. Compare external API responses before and after (if applicable).
**Verify:** All tests pass. No observable behavior change.
| Excuse | Rebuttal | |--------|----------| | "I'll add tests after refactoring" | You can't verify a behavior-preserving refactor without tests before the refactor. | | "This change is obviously safe" | Obvious safety is how production incidents happen. Run the tests. | | "I'll just do a quick cleanup" | "Quick cleanup" that changes behavior is a bug, not a refactor. |
AI agent skills for production grade applications
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and…
Design stable, versioned, self-documenting APIs. Easy to use correctly, hard to use incorrectly. Apply Hyrum's Law from day one.
Automated quality gates from commit to production. Every merge to main is potentially shippable. No manual steps in the deployment path.
Get layered, context-aware explanations of unfamiliar code. Understand what it does, why it was written that way, and how to work with it safely.
Structured code review focusing on correctness, security, and maintainability. Correctness before style. Every reviewer comment must be actionable.
Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.