| name | r00-BehiSecc-awesome-claude-skills--datascience |
| description | ๐ค Data Science & AI/ML skill suite derived from BehiSecc/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.
|
| version | 1.0.0 |
| domain | datascience |
| tags | ["data-science","machine-learning","analytics","pandas","mlops"] |
| source | https://github.com/BehiSecc/awesome-claude-skills |
| license | MIT |
๐ค Data Science & AI/ML Skill Suite
Derived from BehiSecc/awesome-claude-skills ยท Focus: curated list of Claude Skills
Overview
This skill provides 10 production-ready commands tailored for
Data Science & AI/ML workflows. All commands follow a consistent
interaction pattern with structured output, progress tracking and
actionable recommendations.
Available Commands
/data-profiling โ Automated EDA report: distributions, nulls, outliers, correlations and drift/feature-engineer โ Feature importance analysis with SHAP values and automated encoding recipes/model-evaluate โ Model performance dashboard: ROC, PR curves, confusion matrix and bias check/pipeline-scaffold โ Modular ML pipeline scaffold with versioning, logging and registry hooks/ab-test-design โ Statistical A/B test design: sample size, power, MDE and sequential testing/sql-optimize โ Query plan analysis, index recommendations and cost estimation/dashboard-spec โ BI dashboard specification from KPI list with chart types and data sources/data-contract โ Schema validation, SLA definition and data quality contract generation/llm-eval โ LLM output evaluation harness: hallucination rate, faithfulness and latency/anomaly-detect โ Time-series anomaly detection with root-cause attribution and alert tuning
Interaction Pattern
Every command follows this structured response format:
1. CONTEXT CHECK โ Verify inputs and confirm scope with user
2. ANALYSIS โ Deep analysis with live progress display
3. FINDINGS TABLE โ Structured results with severity / priority
4. RECOMMENDATIONS โ Prioritised action list (quick wins first)
5. NEXT STEPS โ Suggested follow-up commands
UI Conventions
| Symbol | Meaning |
|---|
| โ | Passed / complete |
| โ | Failed / critical |
| โ | Warning / review |
| โณ | In progress |
| โ | Pending |
| ๐ด | Critical severity |
| ๐ | High severity |
| ๐ก | Medium severity |
| ๐ข | Low / informational |
Progress bars use block characters:
[โโโโโโโโโโ] 80%
Quick Start
cp -r . ~/.claude/skills/r00-BehiSecc-awesome-claude-skills--datascience/
/read ~/.claude/skills/r00-BehiSecc-awesome-claude-skills--datascience/SKILL.md
Then simply describe your task and Claude will route to the
appropriate command automatically.
