ali-demirbas/ab-test-playbook
A/B Test Builder: turn a screenshot into single-variable test plans with a primary KPI and guardrail, reviewed by two agents and shown side by side in HTML.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit ali-demirbas/ab-test-playbook/agents ./rig-ab-test-playbook/agents $ npx degit ali-demirbas/ab-test-playbook/skills ./rig-ab-test-playbook/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit ali-demirbas/ab-test-playbook/skills/ab-test-audit .claude/skills/ab-test-audit $ npx degit ali-demirbas/ab-test-playbook/skills/ab-test-card .claude/skills/ab-test-card $ npx degit ali-demirbas/ab-test-playbook/skills/ab-test-design .claude/skills/ab-test-design $ npx degit ali-demirbas/ab-test-playbook/skills/ab-test-suggest .claude/skills/ab-test-suggest $ npx degit ali-demirbas/ab-test-playbook/skills/ab-test .claude/skills/ab-test
$ curl -fsSL --create-dirs -o .claude/agents/mockup-reviewer.md https://raw.githubusercontent.com/ali-demirbas/ab-test-playbook/main/agents/mockup-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/scenario-critic.md https://raw.githubusercontent.com/ali-demirbas/ab-test-playbook/main/agents/scenario-critic.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (5)
Subagents (2)
| mockup-reviewer model: sonnet | Mandatory adversarial review of scenario cards for the single-variable rule, ring placement, readability, accessibility, personal data and visual realism before the cards are delivered. Spawned once p |
| scenario-critic model: sonnet | Mandatory adversarial review of every proposed A/B test scenario record against CLAUDE.md's binding rules and knowledge/methodology.md. Spawned by ab-test-suggest, ab-test-design and ab-test-card befo |
Similar rigs
shakhruz/mila
Mila — open-source digital employee in Telegram, built on Claude Code. Bring your own Claude account or API key; she remembers your business and acts in your name only with your consent.
Skill Collector 4.1k tok · · Q15
anomalyco/opencode
The open source coding agent.
Pragmatist 14.3k tok · · Q8
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok · · Q0
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok · · Q18