菜单
Sanity-check the training run that just finished (captured validation score: {{ candidate_score }}). End with ACTION: pass or ACTION: fail.
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 | verify_training |
| description | Sanity-check the training run that just finished (captured validation score: {{ candidate_score }}). End with ACTION: pass or ACTION: fail. |
| tools | ["read_file","run_command"] |
SKILL_ID: verify_training
A deterministic training command just ran (train.py). Decide whether it
actually trained — not whether the score is good.
run_command: tail -50 training.log if it
exists, else check ls checkpoints/ and cat eval_results.json.When failing, summarize the actual error from the log in 1-3 lines (this is re-injected as feedback for the retry).
End your reply with ACTION: pass or ACTION: fail.