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 Ad-Superpowers/ad-superpowers-plugin --skill google-ads-performance-troubleshootergit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote 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/ad-superpowers/ad-superpowers-plugin/google-ads-performance-troubleshooter)<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-performance-troubleshooter"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-performance-troubleshooter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ad-superpowers/ad-superpowers-plugin/google-ads-performance-troubleshooter"><img src="https://agentmods.dev/badge/skills/ad-superpowers/ad-superpowers-plugin/google-ads-performance-troubleshooter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.01720 |
| Opus 5.5 | $0.00034 | $0.00688 |
| Sonnet 5.5 | $0.00017 | $0.00344 |
| Haiku 4.5 | $0.00009 | $0.00172 |
Grade A, and why
google-ads-performance-troubleshooter 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 1mo 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Troubleshooter
Systematic guide for diagnosing and resolving Google Ads performance problems. Start with the quick diagnosis below, then follow the detailed decision trees in references.
Quick Diagnosis Guide
WHAT PROBLEM DO YOU HAVE?
│
├─► CONVERSIONS DROPPED
│ ���── Check 1: Is tracking intact? (tag firing, consent mode)
│ ├── Check 2: Have clicks dropped? (traffic issue vs conversion rate)
│ ├── Check 3: Landing page changed? (speed, mobile, form broken)
│ ├── Check 4: Traffic quality changed? (search terms, device mix)
│ ├── Check 5: Competition/seasonality? (Auction Insights)
│ └── Detailed tree: See references/decision-trees.md "Conversion Drop Diagnosis"
│
├─► CPA INCREASED / ROAS DECREASED
│ ├── Check: Is conversion volume stable? (CPA up with same volume = bid issue)
│ ├── Check: New keywords/audiences? (lower intent traffic diluting efficiency)
│ ├── Check: Auction competition? (competitor CPCs rising)
│ ├── Check: Smart Bidding learning? (recent strategy change = 2-week volatility)
│ └── Detailed tree: See references/decision-trees.md "Efficiency Degradation"
│
├─► IMPRESSIONS / CLICKS DROPPED
│ ├── Check: Budget sufficient? (Limited by budget status)
│ ├── Check: Impression Share Lost (Budget vs Rank)
│ ├── Check: Ad disapprovals? (Policy violations)
│ ├── Check: Keyword status? (Low search volume, below first page bid)
│ └── Detailed tree: See references/decision-trees.md "Volume Decline"
│
├─► NO DELIVERY (0 impressions)
│ ├── Check: Campaign/ad group/ad enabled?
│ ├── Check: Budget > €0 and not exhausted?
│ ├── Check: Targeting not too narrow?
│ ├── Check: Negative keywords blocking all traffic?
│ └── Detailed tree: See references/decision-trees.md "Delivery Problems"
│
├─► QUALITY SCORE DROPPED
│ ├── Check: Expected CTR (ad relevance vs competition)
│ ├── Check: Ad Relevance (keyword-to-ad alignment)
│ ├── Check: Landing Page Experience (speed, relevance, mobile)
│ └── Detailed tree: See references/decision-trees.md "Quality Score"
│
└─► SMART BIDDING NOT WORKING
├── Check: Sufficient conversions? (Min 30/month for tCPA, 50 for tROAS)
├── Check: Learning period? (2 weeks after changes)
├── Check: Targets realistic? (not > 20% from actual performance)
├── Check: Conversion lag? (report may not yet show recent conversions)
└── Detailed tree: See references/decision-trees.md "Bidding Problems"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 199 lines · 86 tokens per session scan A eed002182f46
google-ads-performance-troubleshooter is a skill published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 29d ago), licensed MIT. It adds 86 tokens to every session and 1,720 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
traffic-diagnosis
Systematically diagnose why traffic changed — spike, drop, or shift in mix. Follow these steps in order. Each step narrows the hypothesis.
incident-postmortem
Close the learning loop after a rescue or incident — reconstruct the timeline from actionlog, run root-cause analysis (platform / site / measurement / external), produce a structured postmortem document, distill reusable insights via /learn, and propose preventive guardrails. Use after a /rescue, a CPA spike, a…
ai-hive-a2a-cancel-handoff-check
A verification workflow for tasks handed from one AI agent to another using A2A, a protocol for agent-to-agent communication. It checks remote status, task identifiers, handoff outputs, and cancellation results.
ai-hive-agents-api-session-recovery
A design guide for recovering long-running hosted-agent sessions, their execution events, and result files after interruptions.
sealeap-amazon-featured-offer-loss-triage
Triage loss of the Amazon Featured Offer by checking account health, order defect signals, price competitiveness, offer and fulfillment state, listing classification, unauthorized sellers, and external price evidence before escalating. Use when the Buy Box or purchase button disappears or repeatedly returns. Do not…
self-healing-agents
Self-Healing Agents are autonomous systems that detect their own failure modes and self-correct without human intervention.