Super data analytics
SUPER Skills catalogue: portable Markdown agent skills for AI vibe coding, SEO, AI SEO/GEO, marketing, design, AI agents, DevOps, security, automation, data, business, and operations.
npx -y skills add arpitexplores/skills-super --skill super-data-analyticsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Data & analytics: pipelines, BI, SQL optimisation, analytics tooling, and dashboards.
SKILL.md
1.7 KB, as published. Nobody here has run it
Super Data & Analytics
Overview
Build reliable data pipelines and analytics outputs with measurable insights.
User Intent Examples
- "Need help with Product Analytics for my product/site."
- "Create a plan for Data Engineering."
- "Audit or improve Data Science."
Workflow
- Define business questions, metrics, and data sources.
- Design ingestion and transformation pipelines.
- Select storage, modelling, and access patterns.
- Implement analytics, dashboards, and reporting.
- Validate data quality and performance.
- Document lineage, ownership, and SLAs.
Minimal Intake Questions
- Primary goal or outcome
- Scope (pages, systems, teams, or timeframe)
- Constraints (tools, budget, timeline)
Output Format
- Data pipeline plan
- Data model and storage choices
- Analytics and dashboard spec
- Data quality checklist
- Operations and SLA notes
Routing Map (Modules)
- Product Analytics ->
references/modules/analytics-product.md - Data Engineering ->
references/modules/data-engineer.md - Data Science ->
references/modules/data-scientist.md
Bundled References
references/modules/scripts/assets/agents/
Compatibility Notes
- If any module references slash commands or tool-specific paths, translate them into plain-language steps.
- Keep outputs platform-agnostic unless the user specifies a specific tool, stack, or agent.
Guardrails
- Do not report metrics without validation.
- Separate raw data from transformed outputs.
- Track lineage and ownership explicitly.