Plan Bi Roadmap

Prioritizes BI initiatives with impact, effort, and governance alignment.

Published by @gtmagents·0 agent reads / 30d·0 saves·Updated June 14, 2026

Command: plan-bi-roadmap

Inputs

inputs – backlog source (csv, notion, jira board, spreadsheet).
capacity – number of initiatives supportable next cycle.
themes – comma-separated strategic themes (revenue, success, marketing, product).
audience – exec | bi-lead | revops | async.
constraints – optional notes on tooling, compliance, or dependency limits.

Workflow

Backlog Normalization – ingest initiatives, tag by theme, align to OKRs.
Scoring Engine – calculate impact, effort, risk, and sponsor readiness.
Roadmap Draft – allocate capacity, stage workstreams, and highlight dependencies.
Governance Layer – attach owners, status checkpoints, and success metrics.
Packaging – tailor roadmap deck/memo with decisions + asks for audience.

Outputs

Prioritized roadmap with scoring table + swimlane view.
Governance tracker with owners, milestones, and KPI definitions.
Decision log capturing trade-offs and follow-up actions.

Agent/Skill Invocations

insights-program-director – orchestrates prioritization + stakeholder alignment.
data-architecture-lead – validates feasibility and data contract implications.
metric-governance-kit skill – ensures KPI definitions are locked.
dashboard-playbook skill – provides adoption considerations for planning.

More on the bench

Statistical Analysis

Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.

data-science-ml+2

Postgres

Execute read-only SQL queries against multiple PostgreSQL databases. Use when: (1) querying PostgreSQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.

software-engineering+2

Interactive Dashboard Builder

Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.

data-science-ml+2

Sharebench · Public bench

Connect via MCP.

Add the public bench to any AI tool. Your agents read every artifact you see — no signup needed.

1Pick your tool

# Add the public bench as an MCP server
claude mcp add --transport http sharebench-public https://mcp-public.sharebench.ai

# Settings → MCP → Add new MCP server
{
  "mcpServers": {
    "sharebench-public": {
      "url": "https://mcp-public.sharebench.ai"
    }
  }
}

# Custom GPT or Developer Mode
# Add a remote MCP connector with this URL:
https://mcp-public.sharebench.ai

# Append to ~/.codex/config.toml
[mcp_servers.sharebench_public]
url = "https://mcp-public.sharebench.ai"

2Ask your agent for an artifact

Once connected, just ask in plain language — your agent searches the bench and pulls in what it needs.“Pull the brand voice from sharebench and rewrite this draft.”