---

name: data-fetch description: Fetch and aggregate data from 17 external APIs including Census, arXiv, NASA, Wikipedia, PubMed, and GitHub. version: 1.0.0

Data Fetch

You are fetching and aggregating data from multiple external sources using the shared library's DataFetchingFactory. This skill provides access to 17 structured API clients.

Available Data Sources

Execution Strategy

Single Source Query

Copyfrom data_fetching import DataFetchingFactory
factory = DataFetchingFactory()
client = factory.create_client('arxiv')
results = await client.search("quantum computing", max_results=10)

Multi-Source Aggregation (PARALLEL)

Copyimport asyncio
sources = ['arxiv', 'wikipedia', 'news']
tasks = [factory.create_client(s).search(query) for s in sources]
results = await asyncio.gather(*tasks)

Source Selection Guide

Output Format

Copy📊 DATA FETCH RESULTS

Query: {query}
Sources: {sources_used}
Date: {timestamp}

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
          SOURCE: {source_name}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Results: {count}

1. {title}
   - {metadata}
   - URL: {url}

2. {title}
   ...

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
           AGGREGATED INSIGHTS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Cross-Source Themes:
1. {theme} - Found in: {sources}
2. {theme} - Found in: {sources}

Conflicts/Discrepancies:
- {source1} says X, {source2} says Y

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
              CITATIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

[1] {citation}
[2] {citation}

Integration with Orchestrators

For complex research, combine with orchestration:

Copy/data-fetch → provides raw data
    ↓
DreamCascade → synthesizes findings
    ↓
/data-artist → visualizes results

Key Principles

1. Parallel fetching - Query multiple sources simultaneously
2. Source attribution - Always cite data origins
3. Deduplication - Merge overlapping results
4. Rate limiting - Respect API limits per client
5. Caching - Use MCP cache for repeated queries

Common Workflows

Copy# Census demographics
/data-fetch census "housing prices by county"

# Academic research
/data-fetch arxiv,pubmed "CRISPR gene editing"

# Tech exploration
/data-fetch github "machine learning frameworks" --stars >1000

# Current events
/data-fetch news,wikipedia "climate summit 2026"

Related Skills

• /data-artist - Visualize fetched data beautifully
• /quality-audit - Verify data quality and validate findings