aws-solutions-library-samples

Run Benchmarks — Development skill for Claude Code

Development community

Run Benchmarks — GenAIIDP empirical config/scaling suite.

How to install Run Benchmarks

Installs to ~/.claude/skills/aws-solutions-library-samples-accelerated-intelligent-document-processing-on-aws-run-benchmarks/SKILL.md

Terminal

mkdir -p ~/.claude/skills/aws-solutions-library-samples-accelerated-intelligent-document-processing-on-aws-run-benchmarks && curl -fsSL https://raw.githubusercontent.com/aws-solutions-library-samples/accelerated-intelligent-document-processing-on-aws/HEAD/.claude/skills/run-benchmarks.md -o ~/.claude/skills/aws-solutions-library-samples-accelerated-intelligent-document-processing-on-aws-run-benchmarks/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Run Benchmarks does

Run Benchmarks — GenAIIDP empirical config/scaling suite

Use this skill to run the benchmark suite in `benchmarks/` — an end-to-end, ground-truth study across document types/sizes × configuration options that quantifies success/completeness/accuracy/calibration/latency/tokens/cost. Use it to (a) regenerate the results paper for a release, or (b) gate a code change by comparing against the committed baseline.

Read `benchmarks/matrices/METHODOLOGY.md` first — it defines the matrices, scori

Alternatives in Development

Engage.Crash — Crash → root cause → reachability → empirical exploitability verdict (native bugs) 348 ★
Scaling Prompts — Scaling Prompts — Road to 1M+ Users & Beyond CoinGecko 313 ★
Contract Review Skill — Review legal contracts for risks, extract key terms, and suggest redlines 192 ★