Dashboard Generator
Generate deterministic weekly marketing dashboard outputs from normalized performance tables for BI publishing.
DocumentationRequirements & limits
Use when normalized performance tables need to be turned into deterministic weekly dashboard sections.
Inputs
- normalized_performance_table with date, channel, campaign, spend, clicks, impressions, conversions, revenue.
- date_window_current and date_window_previous.
- output_contract (default): executive summary, channel table, anomaly panel, action panel.
- optional thresholds for highlighting changes.
Outputs
- Dashboard package
- KPI table
- Action panel
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 report generation from validated inputs; require human approval before publishing external dashboard outputs.
Read full instructionsHide full instructions
Dashboard Generator
When to use
- Use for recurring dashboard builds from cleaned performance datasets.
- Use when stakeholders require the same weekly panel order and structure.
- Use when asked to output both machine-ready dataset slices and human-readable dashboard sections.
Inputs required
- normalized_performance_table with date, channel, campaign, spend, clicks, impressions, conversions, revenue.
- date_window_current and date_window_previous.
- output_contract (default): executive summary, channel table, anomaly panel, action panel.
- optional thresholds for highlighting changes.
Workflow
- Validate required columns before any transformation.
- Aggregate by requested grain: channel first, then campaign when requested.
- Compute canonical metrics: CTR, CPC, CVR, CPA, ROAS.
- Compute period deltas using the same grain and metric definitions.
- Build deterministic dashboard payload sections in fixed order.
- Return both section content and a compact publish-ready data object.
Output format
- Executive Summary: 3 to 5 bullets with largest business-impact changes.
- Channel Table: channel, spend, conversions, CPA, ROAS, week-over-week deltas.
- Anomaly Panel: metric, segment, observed delta, threshold, severity, likely cause hypothesis.
- Action Panel: ranked actions with expected impact and confidence.
- Publish Payload: stable JSON keys for BI layer ingestion.
Guardrails
- Never fabricate data for missing channels or campaigns.
- Preserve metric definitions exactly as provided by upstream dictionary.
- Keep section order deterministic across runs.
- Flag low confidence when previous period volume is below threshold.
View file metadata
---
name: dashboard-generator
description: Build or refresh deterministic weekly performance dashboard outputs from standardized marketing tables for BI tools like Looker, Power BI, or Tableau. Use when asked to generate channel summaries, anomaly panels, action panels, or a fixed reporting layout for recurring performance reviews.
---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