Tree
BusinesstreeTree is an Agent Skill for business published in the Zafer-Liu/Data-Analysis-Agent repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
使用决策树识别影响目标变量的关键规则
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Zafer-Liu/Data-Analysis-Agent/blob/HEAD/skills/tree/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/tree, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
决策树分析
确认目标变量和任务类型,排除泄漏字段,合理处理缺失值与类别变量。执行训练验证并报告性能、重要特征和可解释规则;避免把相关性表述为因果。
Tool routing
- Use
get_schemato identify the target, candidate features, task type, and source table. - Use
query_datato verify field names, target distribution, missingness, and leakage risks. - Use
run_analysiswithanalysis_name="Decision_Tree"for the actual tree computation. - Use
generate_charton tree, feature importance, or validation result tables afterrun_analysissucceeds.
Implementation reference
- Tool entry:
agent/tools/business/data.py::_tool_run_analysis - Analysis registry:
Function/Analyze/registry.py - Analysis implementation:
Function/Analyze/Decision_Tree/analyze.py - Chart implementation:
Function/Charts_generation/chart_generate.py