Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vibeeval/refactor
Code refactoring workflow - analyze → plan → implement → review → validate
Passed 19 of 21 test cases with the skill, and 10 of 21 without it.
and 10 more in the full report
10 fixed10 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are modifying `src/db/connection.ts` and want to ensure human oversight between individual edits using the pause flag. Which flag controls this behavior and what does it do?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies --step-by-step as the flag that pauses after each change for human approval. | Missed | Passed |
The instructions your model reads when the skill loads.
Safe refactoring with review gates.
┌──────────┐ ┌────────────┐ ┌──────────┐ ┌──────────┐ ┌───────────┐
│ phoenix │───▶│ plan- │───▶│ kraken │───▶│plan-reviewer│───▶│ arbiter │
│ │ │ agent │ │ │ │ │ │ │
└──────────┘ └────────────┘ └──────────┘ └──────────┘ └───────────┘
Analyze Plan Implement Review Verify
current changes refactor changes tests pass
| # | Agent | Role | Output |
|---|---|---|---|
| 1 | phoenix | Analyze current code, identify improvement areas | Analysis report |
| 2 | plan-agent | Create safe refactoring plan | Step-by-step plan |
| 3 | kraken | Implement the refactoring | Code changes |
| 4 | plan-reviewer | Review changes for correctness | Review report |
| 5 | arbiter | Verify all tests still pass | Test report |
test cases passed, vs 10 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.