Agent skill · Data & Analytics

kpi-tracker-design

Design a KPI tracker that drives decisions instead of decorating them — the few-metrics discipline (5–9, each with an owner and a so-what), targets with honest baselines, the trend-first layout, and the review ritual where the tracker actually gets used. Use when asked set up KPI tracking for the team, build a metrics dashboard in sheets, which numbers should we track, or our dashboard exists but nobody acts on it. Produces the metric selection with kill-list, the tracker structure, the target-setting notes, and the review ritual.

mohitagw15856github.com/mohitagw15856GitHub ↗
claude-codecursorMIT
Install
npx skills add mohitagw15856/pm-claude-skills --skill kpi-tracker-design --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 5 KB
Bundled scripts: none
Path: skills/kpi-tracker-design/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,255
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# KPI Tracker Design Skill KPI trackers fail by addition: every meeting adds a metric, none subtracts, and within two quarters the tracker is a wall of numbers nobody reads — motion without instrumentation. The working tracker is small (5–9 metrics, each with an owner and a written so-what), trend-first (a number without its history is a Rorschach test), honestly baselined before targets exist, and — the part that decides everything — *attached to a ritual* where someone reads it aloud and decisions reference it. The tracker is the artifact; the ritual is the product. ## What This Skill Produces - **The metric selection** — 5–9 survivors of the so-what test, each: definition, source, owner, cadence — plus the kill-list of metrics deliberately not tracked, with reasons - **The tracker structure** — metric × period grid, trend columns/sparklines, target and threshold lines - **The target notes** — baseline-first discipline: track before targeting; targets with owners and reasons, not round numbers - **The review ritual** — where, when, who reads it, and the metric-in-every-decision norm ## Required Inputs Ask for these if not provided: - **The decisions the tracker should feed** — me

What's inside
Steps it walks through
  1. What This Skill Produces
  2. Required Inputs
  3. Framework: The Design Rules
  4. Output Format
  5. The Metrics (5–9)
  6. The Kill-List
  7. Structure & Targets
  8. The Ritual
  9. Quality Checks
  10. Anti-Patterns
More from pm-claude-skills
All skills →
About this skill
What does the kpi-tracker-design skill do?

Design a KPI tracker that drives decisions instead of decorating them — the few-metrics discipline (5–9, each with an owner and a so-what), targets with honest baselines, the trend-first layout, and the review ritual where the tracker actually gets used. Use when asked set up KPI tracking for the team, build a metrics dashboard in sheets, which numbers should we track, or our dashboard exists but nobody acts on it. Produces the metric selection with kill-list, the tracker structure, the target-setting notes, and the review ritual.

How do I install it?

Run `npx skills add mohitagw15856/pm-claude-skills --skill kpi-tracker-design --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From mohitagw15856/pm-claude-skills, a repository with 1,255 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going