Scans notebooks for data file references and verifies each file exists on disk. Use when checking for broken data paths.
Audit Data References Scan all notebooks for data file references and verify they exist on disk. Steps 1. Scan all files in for data loading patterns: Python: , , , , , R: , , , , , Stata: , , , Also check the Jupytext pairs for the same patterns 2. Extract every referenced file path and normalize it: Resolve relative paths from the notebook's directory ( ) Resolve paths using , from / 3. Check that each referenced file exists in or 4. Scan and for all data files present on disk 5. Report three…
Full body not shown for this license – view the source on GitHub →Copy a source-pinned command for your client. You run it yourself.
Destination: .claude/skills/data-audit · pinned to the source commit
# Run from your project root
git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 692e9fa3fea40bbdf614584d461851f8fb968ac2
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/skills/29-quarcs-lab-project20XXy/dot-claude/skills/data-audit" ".claude/skills/"
rm -rf .skillboard-tmpReview the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.
sudo apt update && sudo apt install -y gitnpm install -g @anthropic-ai/claude-code# Run from your project root
git clone https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 692e9fa3fea40bbdf614584d461851f8fb968ac2
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/skills/29-quarcs-lab-project20XXy/dot-claude/skills/data-audit" ".claude/skills/"
rm -rf .skillboard-tmpDestination: .claude/skills/data-audit
Scanner static-checks@0.1.0 · commit 692e9fa3fea4. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.
Declares shell/exec-level tools that grant wide host access.
Evidence: Bash· fingerprint d1e9567da9a8a4b0