Weekly Performance Review BI
Chain dashboard generation, QA gating, and executive narrative writing for deterministic weekly BI reporting.
DocumentationRequirements & limits
Use when weekly BI reporting needs deterministic orchestration across dashboard generation, QA, and narrative drafting.
Inputs
- normalized_performance_table with standardized marketing metrics.
- source_totals and data timestamps for QA.
- metric_dictionary and QA rule thresholds.
- audience profile for executive summary tone.
- reporting windows: current period and comparison period.
Outputs
- Publish decision
- QA package
- Narrative package
Before you begin
- Reading and copying the procedure require no terminal setup. Check requirements for any packaged programs separately.
Try this first
Read the procedure and supply its documented inputs. Use the full text in an agent app or chat that supports pasted instructions, following that host's guidance.
Limits for this step
- Instruction package only; it does not provide or authorize an executable runtime capability.
- Safe for orchestrating read-only reporting steps; require human approval before external publication.
Read full instructionsHide full instructions
Weekly Performance Review BI
When to use
- Use for recurring weekly performance marketing reporting with BI publish gates.
- Use when output must follow a fixed structure across runs.
- Use when reporting must stop automatically on critical data-quality failures.
Inputs required
- normalized_performance_table with standardized marketing metrics.
- source_totals and data timestamps for QA.
- metric_dictionary and QA rule thresholds.
- audience profile for executive summary tone.
- reporting windows: current period and comparison period.
Workflow
- Run
dashboard-generatoron normalized data. - Validate
dashboard-generatoroutput schema and required sections. - Run
dashboard-qa-checkeragainst source totals, freshness, completeness, reconciliation, anomaly rules, and schema drift. - If QA result is
blocked, stop workflow and return QA package plus alert payload. - If QA result is
approved, runexecutive-narrative-writerwith QA-approved dashboard output. - Return consolidated package with publish decision, dashboard sections, and executive narrative.
Output format
- Run Metadata: run_id, reporting windows, execution timestamp.
- Publish Decision: approved or blocked with reasons.
- Dashboard Package: executive summary, channel table, anomaly panel, action panel, publish payload.
- QA Package: summary, check results, blocking reasons, alert payload.
- Executive Narrative: headline, concise summary, driver breakdown, risks, next actions.
Guardrails
- Never run executive narrative step when QA status is blocked.
- Never override a critical QA failure without explicit user approval.
- Preserve metric definitions and output schema contracts across all steps.
- Keep section order stable so BI consumers receive deterministic outputs.
View file metadata
---
name: weekly-performance-review-bi
description: Orchestrate end-to-end weekly BI performance reporting by chaining dashboard generation, QA validation, and executive narrative writing. Use when teams need a deterministic weekly workflow that blocks publish on critical data-quality failures and only produces leadership summaries after QA approval.
---Install instruction files
These commands copy guidance into the selected runtime directories. Confirm that your agent app discovers it. Any packaged programs need separate setup and verification.
Install (Codex)
./bin/skills-hub install adtech/[email protected] --runtime codex
Install (Claude)
./bin/skills-hub install adtech/[email protected] --runtime claude
Install (Generic)
./bin/skills-hub install adtech/[email protected] --runtime generic --target ./my-agent/skills