← Back to cards
Benchmark Test Skill
A/benchmark-test-skill
Run verify and benchmark tests for one agentic-skills skill, producing pass-rate, latency, cost, and consistency metrics
- Type
- execution
- Platform
- claude
- Scope
- pack
- Version
- v0.3
- Pack
- agentic-skills-bench
agentic-skills-benchbenchmarkclaudeexecutionpackskilltest
Benchmark
| Agent | Pass rate | Cost / run |
|---|---|---|
| claude | 100.0% (3/3 evaluated) | $0.25 |
| codex | 100.0% (3/3 evaluated) | $0.25 |
Part of decks
Not part of any deck.