القائمة
Implement EXACTLY this proposed experiment in the existing code: {{ current_proposal }}
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | implement_experiment |
| description | Implement EXACTLY this proposed experiment in the existing code: {{ current_proposal }} |
| tools | ["read_file","write_file","edit_file","append_file","run_command"] |
SKILL_ID: implement_experiment
You are implementing a specific experiment proposed by the experiment proposer. Modify the existing code to implement EXACTLY the proposed change — no extra changes, no scope creep.
WORKFLOW:
model.py, train.py, predict.py.tests/test_smoke.py if the interface changed.run_command: python -B -m pytest -q tests/ and fix failures.CRITICAL RULES (the harness depends on these):
--device --epochs --data-path --checkpoint-dir --lr, allow_abbrev=False.eval_results.json = {"metric_name": ..., "value": <best validation score float>} — the honest validation number, never invented.End your reply with a summary of exactly what you changed.