← ClaudeAtlas

kg-debuglisted

Diagnose a CV-LB disagreement, a suspicious score jump, or a failed/odd submission using the systematic CV-LB debugging procedure and the validation auditor.
TranBaDat2607/claude-code-kaggle-grandmaster · ★ 2 · AI & Automation · score 76
Install: claude install-skill TranBaDat2607/claude-code-kaggle-grandmaster
# /kg-debug Run kgkit with the Bash tool, as `PYTHONPATH="${CLAUDE_PLUGIN_ROOT}" python -m kgkit <command>`: this command pre-approves that form for the kgkit calls it makes. Submitting, pushing or publishing still asks (so does a PowerShell `$env:` assignment). Symptom: `$ARGUMENTS` Follow the `cv-lb-debugging` skill: 1. Classify the symptom with its table and list the likely causes in order. 2. Run the cheap checks yourself: submission validation and distribution comparison, re-scoring the inference path on a validation fold (parity with OOF), CV-LB correlation from the ledger, public LB noise estimate. 3. In parallel, launch the `validation-auditor` agent on the relevant code and folds. 4. If shift is suspected: `python -m kgkit adv` and drop/transform tests. 5. Conclude with the root cause (or ranked hypotheses with the experiment that would distinguish them), the fix, and how it changes trust in CV vs LB going forward. Record it in `reports/journal.md` (or a `studies/<name>/README.md` when a script decided it), and one line in CLAUDE.md `## Current state` when it changes how CV or the LB is trusted from now on.