/datasource
SkillDev toolsCreate a DataSource note documenting a specific database, table, API endpoint, dataset, or data entity with schema, quality metrics, and access information.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the /datasource skill
About this capability
A comprehensive knowledge management system for Solutions Architects using AI
What this skill tells your AI
The instructions your AI receives, as published by davidroliverba/architectkb in .claude/skills/datasource/SKILL.md and read by ahel’s review.
Create a DataSource note documenting a specific database, table, API endpoint, dataset, or data entity with schema, quality metrics, and access information.
Usage
/datasource <name>
/datasource "SAP Invoices"
/datasource "DataPlatform Revenue Fact Table"
/datasource "Snowflake Customers"
Instructions
Phase 1: Parse Input & Link to System
- Extract data source name
- Ask which system owns this data:
Which system owns this data source? Search: [user searches for System] Or create new System? (Y/n) - Confirm link: "Link to [[System - {{system}}]]? (Y/n)"
Phase 2: Essential Information
Creating DataSource: {{name}} (owned by {{system}})
1️⃣ Data Type:
- database-table (relational table)
- database-view (virtual table)
- api-endpoint (REST/GraphQL data)
- kafka-topic (event stream)
- data-warehouse-table (Snowflake/BigQuery)
- data-lake (file-based storage)
- cache (Redis/Memcached)
Default: database-table
User input: [selection]
2️⃣ Record Count (approximate):
Default: null
User input: [number, e.g., 5000000]
3️⃣ Data Volume per Day:
Default: null
User input: [e.g., "2.5GB", "500K records"]
4️⃣ Refresh Frequency:
- real-time
- hourly
- daily
- weekly
- on-demand
Default: daily
User input: [selection]
5️⃣ Classification:
- public
- internal
- confidential
- secret
Default: internal
User input: [selection]
Phase 3: Data Quality (Optional)
Ask: "Add data quality metrics? (Y/n)"
If YES:
- Completeness (%): 98.5
- Uniqueness (%): 99.9
- Accuracy: high | medium | low
- Timeliness: how fresh (< 5 minutes, < 1 hour, etc.)
Phase 4: Schema & Key Fields
Key Fields (comma-separated):
invoice_id, vendor_id, amount
Then ask:
Schema details needed? (Y/n)
- Parent entities (sources of this data)
- Child entities (what feeds from this)
- Related tables
Phase 5: Access & Consumers
How is this data accessed?
- REST API
- GraphQL
- Direct database query
- Kafka topic
- Batch export / S3
- Other
Default: [based on data type]
Which systems consume this data?
Search: [[System - DataPlatform]]
Add: [[System - Analytics]]
Phase 6: Generate Frontmatter
type: DataSource
title: "{{name}}"
sourceId: "{{sourceId}}"
sourceSystem: "[[System - {{system}}]]"
owner: "[[{{person}}]]"
dataType: {{type}}
recordCount: {{count}}
volumePerDay: "{{volume}}"
refreshFrequency: {{frequency}}
classification: {{classification}}
gdprApplicable: {{gdpr}}
piiFields: [{{pii}}]
completeness: {{completeness}}
uniqueness: {{uniqueness}}
accuracy: {{accuracy}}
timeliness: {{timeliness}}
exposedVia: [rest-api, kafka-topic]
consumerCount: {{consumer_count}}
criticalConsumers: [{{critical_systems}}]
confidence: medium
freshness: current
verified: false
created: 2026-01-14
tags: [type/data-source, {{sourceSystem|lower}}]
Phase 7: Generate Body Content
- Overview: What data this contains
- Data Volume & Performance: Size, growth, refresh
- Data Schema: Sample table structure
- Field Mapping: Key fields explained
- Data Quality: Completeness, accuracy metrics
- Access & Integration: How systems access it
- Security & Governance: Classification, PII, GDPR
- Related Integration Notes: What uses this data
Phase 8: Create File
Filename: DataSource - {{name}}.md
Location: Vault root
Output:
✅ Created: DataSource - {{name}}.md
Linked to:
- [[System - {{owning system}}]]
Next steps:
1. Create integration: /integration {{source}} {{target}}
2. Document consumer systems
3. Add to architecture diagram
Example Interaction
User: /datasource "SAP Invoices"
System: Which system owns this data?
> SAP S/4HANA
Data Type:
> database-table
Record Count:
> 200000000
Volume per Day:
> 5GB
Refresh Frequency:
> hourly
Classification:
> confidential
Data Quality:
Completeness: 98.5
Uniqueness: 99.9
Accuracy: high
Timeliness: < 5 minutes
Key Fields:
> invoice_id, vendor_id, company_code, amount, invoice_date
Consumers (search for Systems):
> DataPlatform
> Snowflake
> Analytics
✅ Created: DataSource - SAP Invoices.md
Updated:
- [[System - SAP S/4HANA]] added to owns/exposes
- [[System - DataPlatform]] added to consumers
- [[System - Snowflake]] added to consumers
Signals
- GitHub stars
- 52
- Forks
- 12
- Last commit
- Mar 2026
Advanced
- Catalog kind
- skill
- Gateway key
datasource- Source
- github.com/davidroliverba/architectkb