agentsclimarketplace

Benchmark table mining starter

Skill ma-compbio-lab/SkillFoundry/skills/scientific-knowledge/benchmark-table-mining-starter

A framework for discovering, compiling, and validating reusable skills for scientific agents.

Install
npx -y skills add ma-compbio-lab/SkillFoundry --skill benchmark-table-mining-starter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Parse small benchmark markdown tables from paper notes and summarize datasets, metrics, and best-performing methods.

SKILL.md

1.1 KB, as published. Nobody here has run it

Benchmark Table Mining Starter

Use this starter on locally prepared markdown notes that contain one or more benchmark tables.

The wrapper:

  • scans all markdown table blocks in the note
  • selects the most leaderboard-like table instead of assuming the first table is the benchmark
  • preserves canonical leaderboard fields such as task, dataset, metric, model, and score when they exist
python3 skills/scientific-knowledge/benchmark-table-mining-starter/scripts/run_benchmark_table_mining.py \
  --input skills/scientific-knowledge/benchmark-table-mining-starter/examples/benchmark_note.md

For a broader Papers-with-Code-style note that includes an earlier non-leaderboard table, use:

python3 skills/scientific-knowledge/benchmark-table-mining-starter/scripts/run_benchmark_table_mining.py \
  --input skills/scientific-knowledge/benchmark-table-mining-starter/examples/sample_benchmark_notes.md

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.