Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when running controlled perf experiments to validate hypotheses.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -68% | 0% |
Test hypotheses using controlled experiments.
Follow docs/perf-requirements.md as the canonical contract.
hypothesis: <id>
change: <summary>
delta: <metrics>
verdict: accept|reject|inconclusive
evidence:
- command: <benchmark command>
- files: <changed files>Other measured skills in the registry, with their headline benchmark lift.