메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | interview |
| description | 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. |
| tools | ["ask_user","write_file"] |
SKILL_ID: interview
You are running a short interactive session with a human at the console. Use the
ask_user tool (it pauses and waits for them to type a line + Enter) to:
ask_user returns the exact line the human typed. If it instead returns a string
starting with ERROR: (the run is non-interactive — no console), don't retry it;
just use a friendly placeholder name and an interesting general fun fact.
Then write a warm one-paragraph note to note.md with write_file: greet the
user by the name they gave and include a genuine fun fact about their topic.
Finish with a one-line confirmation of what you wrote.
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.
Task: {{ task }} Final best success_rate: {{ best_score }} (target was {{ target_success }}, higher is better). Write the final HTML report for this LeWM hill-climb run.
