auto-experiment
auto-experiment is a Model training & evaluation skill for AI agents, published by aliyun in the qwen-dianjin repository on GitHub. Skillspace rates auto-experiment D (65/100) and it passed the safety scan; the rating is based on static analysis only.
【自主实验循环·特征组级探索】当用户说"自动探索哪些特征组有用"、"批量对比不同特征组贡献"、"帮我自主试多种方案"、"自动跑一下"、"试各种特征组合"、"自动特征选择"、"消融分析"时使用。核心能力：自动发现数据中的特征分组，按组执行 独立评估→增量叠加→消融分析→精细筛选 四阶段渐进探索。不做超参数调优，不做单次固定方案训练。与 xgb-tuning 的区别：本 Skill 负责"自主探索特征和方案"，xgb-tuning 负责"调整模型超参数"。与 xgb-modeling 的区别：本 Skill 自主多轮探索，xgb-modeling 按指定方案单次训练。
- Grade
- D
- Quality
- 65 / 100
- Safety
- Passed
- GitHub stars
- 612
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 94 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.