chanl-ai

13 Experiment Review — Testing skill for Claude Code

Testing community

Analyze a finished growth experiment — win or lose — update the pipeline, push next ideas to the backlog, systemize winners into playbooks, and refresh plan macro stats.

How to install 13 Experiment Review

Installs to ~/.claude/skills/chanl-ai-marketing-os-13-experiment-review/SKILL.md

Terminal

mkdir -p ~/.claude/skills/chanl-ai-marketing-os-13-experiment-review && curl -fsSL https://raw.githubusercontent.com/chanl-ai/marketing-os/HEAD/skills/13-experiment-review.md -o ~/.claude/skills/chanl-ai-marketing-os-13-experiment-review/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What 13 Experiment Review does

name: experiment-review description: Analyze a finished growth experiment — win or lose — update the pipeline, push next ideas to the backlog, systemize winners into playbooks, and refresh plan macro stats. Use when a test ends, when results are in, or in the Monday growth meeting.

Experiment Review

Required after every run. Blindly starting the next test without asking *why* is not a growth machine — it's busywork.

When to use

When an experiment status is `running` and results

Alternatives in Testing

Claude Code Spec Workflow — Automated Kiro-style Spec workflow for Claude Code 3.6k ★
Create Test Repo — Create a new ArcKit test repo with full scaffolding, auto-detecting the next version number 2.2k ★
Next Evals OSS — Evals for Next.js up to 15.5.6 to test AI model competency at Next.js 310 ★