MAGIC Agent Skills is now open source! Star on GitHub
MAGIC Agent SkillsMAGIC Agent Skills
Guides

Skill Interaction Matrix

Skills are designed to chain together. The agent automatically transitions between skills based on your prompt — you don't need to name skills explicitly.

Common Chains

ChainSkillsWhen to Use
Load → Profilemagic-data-loadingmagic-data-profilingAssess quality of a new dataset
Load → Profile → Reportmagic-data-loadingmagic-data-profilingmagic-report-generationFull quality audit with documentation
Load → Clean → Validatemagic-data-loadingmagic-data-cleaningmagic-data-validationFix and verify data quality
Load → Explore → Visualizemagic-data-loadingmagic-data-explorationmagic-data-visualizationUnderstand and visualize patterns
Load → Transform → Exportmagic-data-loadingmagic-data-transformationmagic-data-loadingReshape and export data

Skill Dependency Graph

graph LR
    load[magic-data-loading] --> profile[magic-data-profiling]
    profile --> clean[magic-data-cleaning]
    clean --> validate[magic-data-validation]
    validate --> transform[magic-data-transformation]
    transform --> viz[magic-data-visualization]
    transform --> report[magic-report-generation]
    load -.-> explore[magic-data-exploration]
    explore -.-> stats[magic-statistical-analysis]
    explore -.-> viz
    stats -.-> report
    synth[magic-data-synthesis] -.-> validate

    style load fill:#dbeafe,stroke:#3b82f6
    style profile fill:#d1fae5,stroke:#10b981
    style clean fill:#d1fae5,stroke:#10b981
    style validate fill:#d1fae5,stroke:#10b981
    style transform fill:#fef3c7,stroke:#f59e0b
    style viz fill:#fce7f3,stroke:#ec4899
    style report fill:#fce7f3,stroke:#ec4899
    style explore fill:#e0e7ff,stroke:#6366f1
    style stats fill:#e0e7ff,stroke:#6366f1
    style synth fill:#f3e8ff,stroke:#a855f7

Solid arrows = common chains (agent transitions automatically). Dashed arrows = alternative paths.

Data Flow Between Skills

Each skill consumes and produces specific data formats:

SkillConsumesProduces
magic-data-loadingRaw files (CSV, Excel, Parquet, JSON)pandas DataFrame + checkpoint
magic-data-profilingDataFrameQuality score, issue list, statistics
magic-data-cleaningDataFrame + issue listCleaned DataFrame + change log
magic-data-validationDataFrameValidation report (pass/fail per rule)
magic-data-transformationDataFrameTransformed DataFrame + checkpoint
magic-data-explorationDataFrameSummary statistics, correlations, patterns
magic-data-visualizationDataFramePNG charts + generation script
magic-report-generationProfiling/analysis resultsMarkdown report + validation
magic-statistical-analysisDataFrameTest results, models, interpretations
magic-data-synthesisSchema or existing dataSynthetic DataFrame
Was this page helpful?
Edit on GitHub

Last updated on

On this page