run-benchmarks
INSTRUCTIONS: 1. Output the COMPLETE function including the signature and docstring shown above 2. Fill in the implementation after the docstring 3. Use proper 4-space indentation for the function body 4. Output ONLY the Python code - no…
- Skills
- AI research
- 2
What it does and how to use it
A skill that teaches Claude Code to do ai research tasks well. It is packaged knowledge the model uses whenever it is relevant.
- Install the skill (command above).
- In Claude Code, describe what you need - the skill turns on by itself when the context fits.
- No commands to memorize: you talk in plain language and the skill does the rest.
Install (Claude Code)
mkdir -p .claude/skills/run-benchmarks && curl -fsSL https://doutorai.pt/data/lib/skills__run-benchmarks.md -o .claude/skills/run-benchmarks/SKILL.mdPaste this command into the terminal, in your project folder, and the component installs automatically.
Content
#!/bin/bash
#===============================================================================
# Loki Mode Benchmark Runner
# Run HumanEval and SWE-bench benchmarks to validate multi-agent performance
#
# Usage:
# ./benchmarks/run-benchmarks.sh [benchmark] [options]
# ./benchmarks/run-benchmarks.sh humaneval # Setup only
# ./benchmarks/run-benchmarks.sh humaneval --execute # Direct Claude (baseline)
# ./benchmarks/run-benchmarks.sh humaneval --execute --loki # Multi-agent Loki Mode
# ./benchmarks/run-benchmarks.sh humaneval --execute --limit 10 # First 10 problems
#
- 🔒 Full content on the Pro plan (€7.99/month) -Need help with Claude Code?
Ask Dr AI - it explains things simply.
Need a tailor-made solution?
Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.
Save hours every week with AI, no hassle
Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.