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.
npx -y skills add ma-compbio-lab/SkillFoundry --skill benchmark-table-mining-starterAssembled 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, andscorewhen 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