Skills Guide

Structured Clustering Analysis

VerifiedSafe

Produce a professional clustering analysis with a structured process, quality checks, and actionable recommendations.

Sby Skills Guide Bot
Data & AIIntermediate
108/9/2026
Claude CodeCursorWindsurfCopilotCodex
#clustering#data-analysis#framework#quality-validation#recommendations

Recommended for

Claude CodeCursorCopilotWindsurfData scientistCodex

Our review

This skill guides the production of a complete, structured clustering analysis, incorporating quality validation steps and actionable recommendations.

Strengths

  • Structured four-step process from research to quality checks
  • Uses recognized frameworks (CRISP-DM, Kimball, Data Mesh) to tailor the approach
  • Detailed output template covering success metrics, risks, and implementation plan
  • Integrates with project context via memory.md and knowledge-base.md

Limitations

  • Requires existing data and context to be fully effective
  • Process may feel heavyweight for simple analyses
  • Focuses on structure and methodology, without providing specific clustering algorithms
When to use it

Use this skill when asked for a professional clustering analysis with measurable recommendations and system integration.

When not to use it

Avoid this skill for quick data exploration or purely exploratory clustering where no structured deliverable is needed.

Security analysis

Safe
Quality score85/100

The skill is a template for generating a clustering analysis report. It does not instruct any destructive, exfiltrating, or obfuscated actions. It only involves reading and updating project files, which are standard agent operations.

No concerns found

Examples

Customer segmentation clustering
Perform a clustering analysis to segment our customers based on purchasing behavior. Use the structured process with quality checks and provide an executive summary, recommendations, and success metrics.
Data quality clustering review
Analyze our existing customer data for clustering potential. Apply CRISP-DM and include risks, mitigations, and a metrics table with current vs target for Data Quality Score.
Dashboard clustering optimization
Produce a clustering analysis to optimize dashboard load time and query performance. Follow the full output format including implementation table and next steps.

description: Analyze and produce a clustering analysis with structured process, quality checks, and system integration

Clustering Analysis

Purpose

Analyze and produce a comprehensive clustering analysis that delivers actionable, measurable results. This skill provides a structured process with quality validation, ensuring professional-grade output every time.

Category: Data & Analytics

Inputs

Required

  • Objective: What you want to achieve with this deliverable
  • Context: Relevant background information

Optional

  • Constraints: Any limitations or requirements to consider
  • Existing Work: Previous documents or data to build on

System Context

Before starting:

  • Read memory.md for current project context and priorities
  • Check knowledge-base.md for relevant learned rules or constraints
  • Review any existing related documents in the project
  • Note any active tasks in Task Board.md that relate to this deliverable

Process

Step 1: Context & Research

  • Review any existing clustering analysis documents in the project
  • Check knowledge-base.md for relevant learned rules or constraints
  • Check memory.md for current project context and priorities
  • Identify key stakeholders and their requirements
  • Select the most appropriate framework: CRISP-DM, Kimball Dimensional Modeling, Data Mesh

Step 2: Analysis & Framework Application

  • Apply the selected framework to structure the clustering analysis
  • Identify gaps, opportunities, and risks
  • Define success metrics: Data Quality Score, Query Performance, Dashboard Load Time, Data Freshness
  • Document assumptions and dependencies
  • Validate approach against industry best practices

Step 3: Build the Deliverable

  • Structure the clustering analysis using the output format below
  • Include specific, actionable recommendations — not generic advice
  • Add concrete numbers, timelines, and benchmarks where applicable
  • Cross-reference with existing project documents for consistency
  • Ensure every section adds value — remove filler

Step 4: Quality Validation

  • [ ] All required inputs have been addressed
  • [ ] Recommendations are specific and actionable (not vague)
  • [ ] Numbers and benchmarks are realistic and sourced
  • [ ] Output format matches the specification below
  • [ ] No contradictions with knowledge-base rules
  • [ ] Follows best practice: Define metrics before building dashboards

Output Format

# Clustering Analysis

## Executive Summary
[2-3 sentence overview of the deliverable and key recommendations]

## Context & Objectives
- **Objective**: [What this achieves]
- **Audience**: [Who this is for]
- **Timeline**: [When this applies]

## Analysis
[Structured analysis using the selected framework]

## Recommendations
1. [Specific, actionable recommendation with expected impact]
2. [Specific, actionable recommendation with expected impact]
3. [Specific, actionable recommendation with expected impact]

## Implementation
| Action | Owner | Timeline | Priority |
|--------|-------|----------|----------|
| [Action item] | [Who] | [When] | [High/Medium/Low] |

## Success Metrics
| Metric | Current | Target | Measurement Method |
|--------|---------|--------|-------------------|
| [KPI] | [Baseline] | [Goal] | [How to measure] |

## Risks & Mitigations
| Risk | Likelihood | Impact | Mitigation |
|------|-----------|--------|------------|
| [Risk] | [H/M/L] | [H/M/L] | [Action] |

## Next Steps
- [ ] [Immediate next action]
- [ ] [Follow-up action]
- [ ] [Review date]

Applicable Frameworks

  • CRISP-DM
  • Kimball Dimensional Modeling
  • Data Mesh
  • Data Vault
  • Metrics Layer

Key Metrics

  • Data Quality Score
  • Query Performance
  • Dashboard Load Time
  • Data Freshness
  • Coverage Rate
  • Anomaly Detection Rate

Best Practices

  • Define metrics before building dashboards
  • One source of truth per metric
  • Document all transformations and business logic
  • Test data pipelines like you test code
  • Archive raw data, transform in layers

After Completion

  • Update memory.md if this deliverable changes project context or priorities
  • Add any reusable learnings to knowledge-nominations.md
  • If follow-up actions were identified, add them to Task Board.md
  • Recommend related skills if additional work is needed
Related skills

Prompt Engineering

Data & AI

Prompt engineering best practices and templates to maximize AI outputs.

claudeCursorWindsurf+1beginner
289
78
911
Admin

Data Visualization

Data & AI

Generates data visualizations and charts tailored to your data.

claudeCursorWindsurfintermediate
198
56
744
Admin

RAG Architecture Setup

Data & AI

Setup guide for RAG (Retrieval-Augmented Generation) architectures.

claudeCursorWindsurfadvanced
167
51
703
Admin