agentleFS
santoshkanthetysantoshkanthety/powerbi-agent/skills/powerbi-lineage-analysis/SKILL.md

powerbi-lineage-analysis

Skill3 starsChanged 7 months agoMITView on GitHub

Trace relationships between semantic models and downstream reports across Fabric workspaces. Automatically invoke when the user asks to "find downstream reports", "show report lineage", "impact analysis", "what depends on this dataset", "cross-workspace lineage", "which reports are connected", "get model dependencies", or mentions model-to-report dependency tracing.

  • Installs packages

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before modifying or deleting a semantic model, to understand impact

    line 13
  2. Very specific:

    Run scripts/get-downstream-reports.py to find all reports bound to a semantic model.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Lineage Analysis

Trace downstream dependencies from a semantic model to all connected reports across the tenant. No admin permissions required -- workspace contributor access is sufficient.

When to Use

  • Before modifying or deleting a semantic model, to understand impact
  • Auditing which reports are connected to a model and where they live
  • Identifying orphaned or test reports connected to production models
  • Cross-workspace dependency mapping

Downstream Reports

Run scripts/get-downstream-reports.py to find all reports bound to a semantic model.

# By workspace and model name
python3 scripts/get-downstream-reports.py "Workspace Name" "Model Name"

# By dataset GUID directly
python3 scripts/get-downstream-reports.py --dataset-id <guid>

# JSON output for further processing
python3 scripts/get-downstream-reports.py "Workspace" "Model" --json

Requirements: azure-identity, requests (pip install azure-identity requests). Authenticated via DefaultAzureCredential (works with az login, managed identity, or environment variables).

How it works: Lists all workspaces the user can access, then queries each workspace's reports in parallel (8 workers) checking datasetId. Groups results by workspace. Typically completes in under 10 seconds for ~100 workspaces.

Permissions: Workspace contributor or higher on any workspace to be scanned. Reports in workspaces without access will not appear. For full tenant coverage, use the --dataset-id flag with a tenant admin token and the admin/reports API instead.

Limitations

Reports are not the only consumers. A semantic model can also be consumed by:

  • Analyze in Excel workbooks (.xlsx live connections)
  • Composite models (other semantic models chaining via DirectQuery)
  • Explorations (ad-hoc visual explorations in the Power BI service)
  • Fabric notebooks (connecting via Spark or sempy)
  • Fabric data agents
  • Paginated reports (.rdl)
  • Dataflows referencing the model
  • Third-party tools connecting via XMLA

The script only discovers Power BI reports. For full dependency mapping including these other item types, use the Fabric lineage APIs (fab api "admin/groups/{id}/lineage") or the lineage view in the Power BI service UI.

Not appropriate for many models at once. The script scans all accessible workspaces per invocation. Running it in a loop over dozens of semantic models will generate excessive API calls and risk throttling. For bulk lineage analysis across many models, use the admin scan APIs (admin/workspaces/getInfo) or the DataHub search script instead.

Interpreting Results

FieldMeaning
Report format PBIRModern format, editable as JSON
Report format PBIRLegacyLegacy format, needs conversion to PBIR for direct editing
Reports in unexpected workspacesMay indicate copies, forks, or thin reports pointing at a shared model
Many downstream reportsHigh-impact model -- changes require coordination

Related Skills

  • review-semantic-model -- Audit model quality, memory, DAX, design
  • refresh-semantic-model -- Trigger and monitor model refreshes
  • fabric-cli (fabric-cli plugin) -- Workspace and item management via fab CLI

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.