mikevan666/OpenDataWorks Platform
skills/platform/opendataworks-platform/SKILL.md
Use this built-in skill for OpenDataWorks platform metadata, lineage, datasource resolution, and DDL lookup. This skill does not execute SQL for data analysis.
$ install --global
skillsauthnpx skillsauth add mikevan666/opendataworks OpenDataWorks PlatformInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 5:58 AM8.1s3 files scanned
SKILL.md
- name:
- OpenDataWorks Platform
- description:
- Use this built-in skill for OpenDataWorks platform metadata, lineage, datasource resolution, and DDL lookup. This skill does not execute SQL for data analysis.
- category:
- Platform
- version:
- v1
OpenDataWorks Platform Skill
Use this skill when the user asks about OpenDataWorks platform objects or needs platform context before any analysis.
Scope:
- metadata inspect
- lineage lookup
- datasource resolution
- DDL lookup
Do not use this skill to execute analytical SQL. SQL execution belongs to OpenDataWorks Readonly SQL Skill.
Execution contract:
- Always call the local shared
odw-cli. - Prefer the helper scripts in
scripts/. - Do not call
portal-mcpfor OpenDataWorks platform capabilities.
Preferred scripts:
python3 scripts/inspect_metadata.py --keyword "<keyword>"python3 scripts/query_lineage.py --table "<table>" --db-name "<db>"
Working rules:
- If the user asks about tables, fields, databases, or datasource ownership, start with metadata inspect or datasource resolve.
- If the user asks about upstream/downstream relationships, lineage impact, or where a table comes from, use lineage lookup.
- If SQL is needed to answer the question, hand off to the readonly SQL skill instead of embedding execution logic here.
Related Skills
mikevan666/OpenDataWorks Readonly SQL
tools
VerifiedTrustedCommunity
Use this built-in skill to execute readonly SQL through the OpenDataWorks agent API and shared odw-cli. Guardrails such as readonly checks, datasource scope, default limit, and timeout are enforced by CLI and API.
17SKILL.mdUpdated Apr 16, 2026
mikevan666/Smoke
testing
VerifiedTrustedCommunity
A minimal smoke skill used to verify that opendataagent can load bundled skills and surface them during chat.
17SKILL.mdUpdated Apr 16, 2026
mikevan666/Python Analysis
development
VerifiedTrustedCommunity
Use this built-in skill for lightweight Python-based data exploration, profiling, aggregation, and file-based analysis. It does not fetch OpenDataWorks metadata on its own.
17SKILL.mdUpdated Apr 16, 2026
mikevan666/Chart Visualization
data-ai
VerifiedTrustedCommunity
Use this built-in skill for chart construction and data storytelling from structured tabular results. The workflow is organized from the AntV chart-visualization playbook, but current default output is ECharts-compatible option JSON for local rendering.
17SKILL.mdUpdated Apr 16, 2026