Dashboard Specification
Writes the brief a dashboard needs before a developer touches it: audience, metric hierarchy, layout, and what success looks like.
Overview
Dashboard Specification runs before a new dashboard is built, when an existing one is confusing and needs a redesign, or when stakeholders and the data team disagree on what it should even show.
What it covers
- States the dashboard's purpose in one sentence: the question, the audience, and the decision it enables.
- Profiles each target audience by visit frequency, primary question, and technical comfort, since different needs usually mean different dashboards, not more filters.
- Defines a metric hierarchy: hero KPIs, secondary metrics, and detail breakdowns, capped near 10 to 12 metrics total.
- Designs the layout using a hero, trends, breakdowns, details pattern, and specifies every filter and drill-down deliberately.
- Documents the data source and refresh frequency for each metric, and defines how success will be measured.
Part of Data Analytics Skills
This is one of 31 skills in the Data Analytics Skills library, in the Data Storytelling & Visualization group.
Installation
- Clone the repo once:
git clone https://github.com/nimrodfisher/data-analytics-skills.git - Copy just this skill:
cp -r data-analytics-skills/04-data-storytelling-visualization/dashboard-specification ~/.claude/skills/(or~/.agents/skills/for Codex) - Ask your agent something like "write the spec for a new retention dashboard before we build it" and it activates on its own.
See the Data Analytics Skills entry for the full library.
Related assets
Frontend Design
Generates distinctive, production-grade UI that avoids generic "AI slop," with bold typography, cohesive color, and precise motion, implemented as real code.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Caveman
Makes your coding agent answer in a stripped down, high signal style that keeps every technical fact and cuts filler, saving output tokens on chat style questions.