lineage-analysis — Claude Code skill: what it does, how to install
lineage-analysis finds every Power BI report tied to a semantic model across Fabric workspaces, without needing admin rights.
GPL-3.0 ★ 1,104 updated 2026-10-28
/plugin marketplace add data-goblin/power-bi-agentic-development
/plugin install semantic-models@power-bi-agentic-developmentWhat lineage-analysis does
The skill runs scripts/get-downstream-reports.py, which walks the workspaces a user can reach and checks each report's datasetId, using 8 parallel workers. You can target it by workspace and model name or by a dataset GUID directly, with plain or JSON output. It needs the azure-identity and requests packages, and authenticates through DefaultAzureCredential, so az login, a managed identity, or env variables all work.
Workspace contributor rights are enough, but then only workspaces you can access show up in results. Covering the whole tenant means passing --dataset-id with an admin token against the admin/reports endpoint instead.
The scan only catches Power BI reports. Excel workbooks with live connections, composite models, explorations, Fabric notebooks, data agents, paginated .rdl reports, dataflows, and third-party XMLA clients fall outside its reach, so a full dependency picture requires Fabric's own lineage endpoints via fab api or checking connections directly inside the Power BI service. It also isn't built for scanning dozens of models in a row: each run re-scans every reachable workspace, and looping it risks hitting API throttling.
What it helps with
- check which reports break if a model changes
- spot reports sitting in unexpected workspaces, copies or forks
- map dependencies between a model and its reports before deleting it
- tell PBIR reports apart from legacy ones that need converting
Example prompts for the agent
- Find every report that depends on Model Name in Workspace Name
- Show downstream dependencies for the dataset with GUID <guid>
- Output the model's lineage as JSON for further processing
How to install lineage-analysis
1Plugin marketplace
/plugin marketplace add data-goblin/power-bi-agentic-development/plugin install semantic-models@power-bi-agentic-developmentThis installs the whole semantic-models plugin with all its skills
2Skills CLI (Vercel)
npx skills add data-goblin/power-bi-agentic-development --skill lineage-analysis -a claude-code3Manually: put the files in place
~/.claude/skills/lineage-analysis/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/lineage-analysis/
1Skills CLI (Vercel)
npx skills add data-goblin/power-bi-agentic-development --skill lineage-analysis -a codex2Manually: put the files in place
.agents/skills/lineage-analysis/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add data-goblin/power-bi-agentic-development --skill lineage-analysis -a cursor2Manually: put the files in place
.cursor/skills/lineage-analysis/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install data-goblin/power-bi-agentic-development plugins/semantic-models/skills/lineage-analysis2Manually: put the files in place
.github/skills/lineage-analysis/SKILL.md1Skills CLI (Vercel)
npx skills add data-goblin/power-bi-agentic-development --skill lineage-analysis -a gemini-cli2Platform CLI
gemini skills install https://github.com/data-goblin/power-bi-agentic-development --path plugins/semantic-models/skills/lineage-analysisManually: put the files in place
.devin/skills/lineage-analysis/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about lineage-analysis
How do I install lineage-analysis in Claude Code?
Run /plugin marketplace add data-goblin/power-bi-agentic-development, then /plugin install semantic-models@power-bi-agentic-development.
What does lineage-analysis do?
It scans Fabric workspaces for Power BI reports bound to a given semantic model, checking each report's datasetId to build a dependency list.
What dependencies does the skill miss?
It only picks up Power BI reports. Excel live-connection workbooks, composite models, explorations, Fabric notebooks, data agents, paginated reports, and dataflows aren't covered.