10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 892 ms

1. 1agent-performance-benchmarkerdemo or tutorialno passport yet

   skillruvnet/ruflorecord

   • agent-performance-benchmarker

     Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker

2. 2perf-benchmarkerverified and signedpassport

   skillcomposio-community/awesome-claude-pluginsrecord

   • perf-benchmarker

     Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.

3. 3agent-v3-performance-engineerverified and signedpassport

   skillruvnet/ruflorecord

   • agent-v3-performance-engineer

     Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

4. 4agent-benchmark-suiteverified and signedpassport

   skillruvnet/ruflorecord

   • agent-benchmark-suite

     Agent skill for benchmark-suite - invoke with $agent-benchmark-suite

5. 5agentdbverified and signedpassport

   MCP servergit+https://github.com/ruvnet/agentdbnpmrecord510,961 downloads/month

   • agentdb_attention_benchmark

     Benchmark attention mechanism performance

6. 6agent-performance-monitordemo or tutorialno passport yet

   skillruvnet/ruflorecord

   • agent-performance-monitor

     Agent skill for performance-monitor - invoke with $agent-performance-monitor

7. 7agent-performance-analyzerdemo or tutorialno passport yet

   skillruvnet/ruflorecord

   • agent-performance-analyzer

     Agent skill for performance-analyzer - invoke with $agent-performance-analyzer

8. 8agentic-perffound in code, not yet checkedno passport yet

   MCP serveratheurer/agentic-perf

   • execute_benchmark

     Execute a previously validated benchmark configuration.

9. 9agent-evaluationverified and signedpassport

   skilldavila7/claude-code-templatesrecord

   • agent-evaluation

     Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

10. 10agent-performance-optimizerdemo or tutorialno passport yet

    skillruvnet/ruflorecord

    • agent-performance-optimizer

      Agent skill for performance-optimizer - invoke with $agent-performance-optimizer