Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TrueClicks/claude-plugins --skill skill-032-ad-copy-ab-testinggit clone --depth 1 https://github.com/TrueClicks/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/trueclicks/claude-plugins/skill-032-ad-copy-ab-testing)<a href="https://agentmods.dev/skills/trueclicks/claude-plugins/skill-032-ad-copy-ab-testing"><img src="https://agentmods.dev/badge/skills/trueclicks/claude-plugins/skill-032-ad-copy-ab-testing.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00706 |
| Opus 5 | $0.00011 | $0.00353 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
skill-032-ad-copy-ab-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 032: Ad Copy A/B Testing Program
Purpose
Continuous ad testing is essential for improving performance. Without active testing, accounts stagnate. This audit verifies each ad group has multiple RSAs for testing and identifies ad groups lacking adequate test coverage, especially high-traffic ones.
Data Requirements
Data Source: Standard
Standard Data:
data/account/campaigns/*/*/ads.md- All RSAs per ad groupdata/performance/campaigns/*/*/ads_metrics_30_days.md- Ad performance
Reference GAQL:
SELECT
campaign.name,
ad_group.name,
ad_group_ad.ad.id,
ad_group_ad.ad.type,
ad_group_ad.ad_strength,
ad_group_ad.status,
metrics.impressions,
metrics.clicks,
metrics.ctr,
metrics.conversions,
metrics.cost_micros
FROM ad_group_ad
WHERE ad_group_ad.ad.type = 'RESPONSIVE_SEARCH_AD'
AND ad_group_ad.status = 'ENABLED'
AND segments.date DURING LAST_30_DAYS
ORDER BY campaign.name, ad_group.name
Use /google-ads:get-custom for detailed ad-level performance.
Analysis Steps
- Count ads per ad group: Google recommends 1-3 RSAs per ad group for optimal testing
- Identify testing gaps: Ad groups with 0 RSAs (no ads), 1 RSA (no testing), 4+ RSAs (too many)
- Analyze test differentiation: Are RSAs actually different? Flag tests that are too similar
- Evaluate test performance: Impression distribution, statistical significance, identify winners/losers
- Prioritize by traffic: High-traffic ad groups without testing are highest priority
Thresholds
| Condition | Severity |
|---|---|
| Ad group with 0 RSAs | Critical |
| High-traffic ad group with 1 RSA | Critical |
| Ad group with 1 RSA | Warning |
| Ad group with 4+ RSAs | Warning |
| RSAs >80% similar in same ad group | Warning |
Output
Short (default):
## Ad Testing Audit
**Account:** [Name] | **Ad Groups:** [X] | **Without Testing:** [Y]%
### Critical ([Count])
- **[Campaign] / [Ad Group]**: [X] monthly clicks, only 1 RSA -> Add 1-2 test RSAs
### Warnings ([Count])
- **[Campaign] / [Ad Group]**: [Issue] -> [Fix]
### Testing Status
| Status | Ad Groups | % |
|--------|-----------|---|
| Active (2-3 RSAs) | X | X% |
| No testing (1 RSA) | X | X% |
| Over-testing (4+) | X | X% |
| No ads (0) | X | X% |
### Recommendations
1. [Priority action]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 89 lines · 22 tokens per session scan A 1f254c8cc5e5
skill-032-ad-copy-ab-testing is a skill published in the GitHub repository TrueClicks/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 706 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…