What do I need to use KPI Tracker Design?

The decisions the tracker should feed; The candidate metrics and their sources; The audience and cadence; Existing baselines.

Is KPI Tracker Design free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

KPI Tracker Design

Q: How do I know the KPI Tracker Design output is good?

The skill verifies itself against its own quality checks: Every metric passed the so-what test against a real decision; Count is 5–9; the kill-list exists with reasons; Definitions settle the numerator/denominator argument in writing; Trends are visible per metric — no naked current-values.

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 pm-cowork

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.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The decisions the tracker should feed — metrics follow decisions; "what would we do differently if this number moved?" is the selection filter, and it needs the team's real decision list

▸The candidate metrics and their sources — what's measurable today vs. requiring new instrumentation (day-one tracker uses today's sources; the wishlist is a separate roadmap)

▸The audience and cadence — team-weekly vs. leadership-monthly are different trackers (grain, commentary, tone) — pick one; hybrids serve neither

▸Existing baselines — history where it exists; where it doesn't, the no-targets-for-a-month rule applies

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Every metric passed the so-what test against a real decision

✓Count is 5–9; the kill-list exists with reasons

✓Definitions settle the numerator/denominator argument in writing

✓Trends are visible per metric — no naked current-values

✓The ritual has a slot, a reader, and the decision-linkage norm

⚠️ What it refuses to do

Do not track what you can't act on — interesting is not a criterion; decidable is

Do not exceed nine — the tenth metric costs attention from the first nine

Do not set targets on unbaselined metrics — round-number targets on unknown behavior are theater

Do not show numbers without trends — a value with no history is a mood

Do not build the tracker without booking the ritual — undecorated walls beat decorated ones

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="kpi-tracker-design"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

KPI Tracker Design is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog