Feature Engineering Advisor
Use when designing, reviewing, or selecting features for machine learning models. Advises on feature types, missing value treatment, encoding, interaction terms, time-series features, leakage risks, and feature importance evaluation strategies. 中文触发词:特征工程、特征设计、特征选择、数据泄漏。
Install
npx skills add shisuidata/ss-data-skills --skill feature-engineering-advisorgit clone --depth 1 https://github.com/shisuidata/ss-data-skills.git /tmp/ss-data-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ss-data-skills/skills/feature-engineering-advisor ~/.claude/skills/feature-engineering-advisorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Feature Engineering Advisor ## 目标 帮助数据科学家和算法工程师设计、评估和审查模型特征,减少数据泄露、无效特征和工程实现风险。 这个 Skill 不直接输出可运行的训练代码,而是负责特征方案决策:选什么、怎么处理、有什么风险。 ## 使用场景 使用这个 Skill,当用户需要: - 为分类、回归、排序或推荐模型设计原始特征 - 审查现有特征方案是否存在数据泄露 - 判断缺失值、离群值和高基数字段的处理方式 - 设计时序特征、行为序列特征或用户画像聚合特征 - 判断哪些特征最值得优先纳入,哪些应该剔除 典型输入: ```text 我要为 SaaS 客户流失预测模型设计特征,目前有用户行为日志、订阅表和支持工单表,请帮我设计特征方案。 ``` ## 不适用场景 不要用这个 Skill 直接完成: - 模型结构选择或超参调优(本库暂无对应 Skill) - 模型评估方案和上线判断,应使用 `model-evaluation-reviewer` - 原始数据摸底,应使用 `exploratory-data-analysis` - 指标口径审查,应使用 `metric-definition-reviewer` - SQL 审查,应使用 `sql-reviewer` 如果用户没有提供数据结构或业务目标,先列出需要确认的问题,不要直接生成特征方案。 ## 输入信息 最少输入: - 建模目标:预测什么,对谁预测 - 可用数据表或字段说明 可选输入: - 目标变量定义 - 预测时间点(样本截止时间) - 预测时间范围(预测未来多久) - 特征工程平台:Spark、Python/Pandas、Flink 实时特征 - 已有特征版本或基线模型 - 业务约束:禁用字段、隐私限制、合规要求 ## 上下文建议 推荐使用 [机器学习上下文模板](../../context/templates/ml-context.md) 补充建模目标、样本定义和数据来源。 最有价值的上下文是:预测目标、样本构造时间点、可用表结构和已知高价值信号。缺少真实数据样例时,先设计特征框架和待确认清单。 ## 设计框架 1. 明确预测目标和时间点,确定样本构造方式。 2. 识别特征来源:行为特征、属性特征、关系特征、时序特征。 3. 逐类设计特征方案:原始值、聚合统计、差分、比率、桶分类、Embedding。 4. 检查数据泄露:特征是否使用了预测时间点之后的数据。 5. 检查高基数字段:是否需要编码或降维。 6. 检查缺失值:是否与业务含义有关(缺失本身即为信号)。 7. 给出特征优先级:预期影响力、工程成本、稳定性。 8. 标记监控建议:特征分布漂移、上线后稳定性检查。 ## 可用脚本 有特征表时,先做泄漏筛查: ```bash python3 scripts/leakage_check.py check --csv features.csv --label churned --asof-col snapshot_time \ --feature-time logins_30d=last_login_time --exclude customer_id ``` 示例见 `assets/example_features.csv`,全部参数见 [命令行参数](references/cli.md)。
Details
- Skill name
feature-engineering-advisor- Repository
- shisuidata/ss-data-skills
- Path
skills/feature-engineering-advisor/SKILL.md- License
- MIT
- Repo updated
- 8 November 2026
FAQ
What does the Feature Engineering Advisor skill do?
Use when designing, reviewing, or selecting features for machine learning models. Advises on feature types, missing value treatment, encoding, interaction terms, time-series features, leakage risks, and feature importance evaluation strategies. 中文触发词:特征工程、特征设计、特征选择、数据泄漏。
How do I install the Feature Engineering Advisor skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add shisuidata/ss-data-skills --skill feature-engineering-advisor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Feature Engineering Advisor popular?
It lives in shisuidata/ss-data-skills, which has 9 GitHub stars and 0 forks.
Related skills
Ab Test Analysis
9shisuidata/ss-data-skills
Use when designing, checking, or interpreting A/B tests and experiments. Computes significance, confidence intervals, sample ratio mismatch, power, CUPED, and sample size with a bundled zero-dependency script, then judges validity risks, guardrails, and ship/iterate/rollback decisions and renders an HTML experiment report. 中文触发词:A/B 实验、AB 测试、实验解读、显著性、样本量计算、能不能全量。
Business Root Cause Analysis
9shisuidata/ss-data-skills
Use when diagnosing business metric changes or anomalies such as GMV decline, conversion drop, retention loss, churn increase, revenue change, lead decline, or active user fluctuation with a structured root cause analysis plan. 中文触发词:指标归因、为什么下降、异常排查、GMV 下滑、指标波动原因。
Daily Report Writer
9shisuidata/ss-data-skills
Use when writing a concise daily report, daily worklog, standup update, shift handoff, or end-of-day summary for data analysis, data development, BI, governance, or operations work. 中文触发词:日报、日终同步、站会发言、值班交接。
Model Evaluation Reviewer
9shisuidata/ss-data-skills
Use when reviewing or designing the evaluation framework for a machine learning model. Checks metric selection, train-test split, offline-online gap, cold start, business translation of model scores, and monitoring strategy. 中文触发词:模型评估、AUC、模型能不能上线、模型效果审查。
Appdeploy
3AppDeploy-AI/skills
Deploy web apps with backend APIs, database, file storage, AI operations, authentication, realtime, and cron jobs. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses HTTP API via curl.
Patterns
9zllovesuki/cloudflare-agent-skills
Apply Cloudflare reference architecture patterns for CRUD SaaS, collaboration, async exports, AI assistants, RAG, media, webhook ingestion, and migration. Use to turn requirements into an implementation pattern and primitive map.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.