Ad Tests — Development skill for Claude Code
Champion vs challenger - read the pair on click-through, rank lines on their lifetime record within pin buckets, promote proportionally, rotate the challenger.
How to install Ad Tests
Installs to ~/.claude/commands/automatable-skool-ads-blueprint-day7-ad-tests.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/automatable-skool/ads-blueprint-day7/HEAD/.claude/commands/ad-tests.md -o ~/.claude/commands/automatable-skool-ads-blueprint-day7-ad-tests.md Restart Claude Code, or start a new session, for it to be picked up.
What Ad Tests does
description: Champion vs challenger - read the pair on click-through, rank lines on their lifetime record within pin buckets, promote proportionally, rotate the challenger. Fortnightly. argument-hint: [ad group ID or name, optional] [--pair-days N, default 14] [focus: read | swap | promote | log]
Run the fortnightly ad test read: $ARGUMENTS. Every ad group runs two responsive search ads - the champion (the service's best lines) and the challenger (the next untested batch from `ad-librar
Alternatives in Development
- Memory Gc — Inspect or rotate the autopilot ledger JSONL files (findings.jsonl, negatives.jsonl) 3.8k ★
- Nexting — Remote control for Claude Code, Codex, Grok, and Cursor on Mac or PC 1.3k ★
- Pool Compare — Compare all Meteora DLMM pools for a token pair by APR, fee/TVL ratio, and volume 722 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Agent Pair
A Claude Code / Codex skill that lets the two agents review each other's code. The peer session is resumed by
Join
Join your team's shared skills repository set up by a champion via /handbook:init
Q Reality Check
Challenger mode. Argue AGAINST current hypotheses and findings to find weak spots.
Auto Optimize
Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against bas
Ctxprof
Profile Claude Code JSONL sessions into six estimated token buckets, compare runs, and identify large context
Hunt Buckets
Enumerate cloud buckets for an ingested program (listing-only, no GetObject). Writes candidates to out/ /bucke
Related Agents
Gsc Ctr Curve
GSC click-through-rate auditor. Compares per-query observed CTR to the position-CTR curve and flags queries th
Sc Recon Expander
Task-less smart-contract recon expander — resolves proxies/diamonds/roles/linked addresses per chain and retur
Sector Analyst
Sector and industry analyst. Use to rank sectors and industries by relative strength and fundamental drivers,