GE
Growth Experiment Backlog
🔵 Stable🕐 updated 2026-06-24
🔷 SkillSpec L3
pm-growth
Build and prioritise a growth experiment backlog. Use when asked to plan growth experiments, prioritise growth ideas, set up a test backlog, or run a growth process/sprint. Produces a prioritised backlog — each experiment as a hypothesis with the metric it moves, an ICE/PXL score, the minimum test design, and a definition of done; plus the cadence to run it.
What to give it
▸The metric to move — the one growth metric this cycle (activation, conversion, retention, referral).
▸The funnel stage / leak — where the opportunity is (pair with [`marketing-funnel-plan`](../marketing-funnel-plan/SKILL.md)).
▸Raw ideas — any experiment ideas already on the table.
▸Constraints — eng/design bandwidth and traffic volume (which caps how many tests can reach significance).
✅ 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 item is a falsifiable hypothesis with the metric it moves and a "because" — not a vague idea
✓Scoring (ICE/PXL) is applied consistently so the backlog is sortable, not cherry-picked
✓Top experiments specify sample size/duration to actually detect the expected effect
✓Each test has guardrail metrics so a "win" can't quietly harm something else
✓There's a cadence that captures the learning from losers, not just winners
⚠️ What it refuses to do
Do not run experiments without a hypothesis and a target metric — that's just shipping changes and hoping
Do not call a test before it reaches the planned sample size — peeking and stopping early manufactures fake wins
Do not chase many tiny tests when traffic is low — you'll never reach significance; pick fewer, bigger bets
Do not ignore guardrail metrics — a conversion win that tanks refunds or retention is a loss
Do not discard losing experiments silently — the learning is the asset; record why it failed
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-mcpRelated skills
🔌 Embed this skill
Drop this on your blog, docs, or site — it renders a "Run this skill" card:
<div data-pm-skill="growth-experiment-backlog"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>💬 Discussion
Growth Experiment Backlog is one of 625 open-source professional AI agent skills — all SkillSpec L3.
Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog