菜单
Review data_analysis.md for quantitative completeness. End with ACTION: pass or ACTION: fail (with specific feedback).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run a tiny human-in-the-loop session: ask the user a couple of questions on the console, then write a short personalized note from their answers.
Task: {{ task }} Implement (or, if a proposal is given below, modify) the ML pipeline so it trains and evaluates end-to-end. Target metric to beat: {{ target_accuracy }}. Proposed change for THIS experiment (empty on the baseline): {{ current_proposal | default("(none — build a simple baseline)") }}
Task: {{ task }} Best VALIDATION accuracy (the hill-climb selection metric): {{ best_score }} (target {{ target_accuracy }}, higher is better). Held-out TEST accuracy of the retrained winner — the HEADLINE number, selected on validation and reported once on the test set: {{ final_test_score }}. Write the final HTML research report for this ML auto-research run.
Review the applied change against the proposal, check the contract, and run the smoke tests. Decide pass or fail. Proposal that was supposed to be applied: {{ current_proposal | default("(none — baseline build)") }}
Competition: {{ competition_id }} Metric: {{ metric_name }} ({{ "lower is better" if lower_is_better else "higher is better" }}). Final best validation score: {{ best_score }} (target {{ target_score }}). Write the final HTML report for this kaggle-solver run.
Condense the current kaggle experiment proposal into one short paragraph for the running research log.
| name | eda_critic |
| description | Review data_analysis.md for quantitative completeness. End with ACTION: pass or ACTION: fail (with specific feedback). |
| tools | ["read_file","run_command"] |
SKILL_ID: eda_critic
You are reviewing an EDA document for a Kaggle pipeline.
data_analysis.md (and competition_understanding.md for what data
exists).PASS if it credibly covers: per-file shapes, missing-value analysis, target distribution, at least some real numbers (counts, percentages, correlations), and preprocessing/feature recommendations.
FAIL only for material gaps: no quantitative content at all, the target variable not characterized, or a data modality from the understanding doc completely unexamined. Be pragmatic — partial coverage with real numbers beats demands for perfection.
When failing, give 1-3 specific bullets on what to add.
End your reply with ACTION: pass or ACTION: fail.