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 swan-gtm/gtm-skills --skill meta-optimization-playbookgit clone --depth 1 https://github.com/swan-gtm/gtm-skillsWrote 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/swan-gtm/gtm-skills/meta-optimization-playbook)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/meta-optimization-playbook"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/meta-optimization-playbook/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/swan-gtm/gtm-skills/meta-optimization-playbook"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/meta-optimization-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.03268 |
| Opus 5.5 | $0.00015 | $0.01307 |
| Sonnet 5.5 | $0.00007 | $0.00654 |
| Haiku 4.5 | $0.00004 | $0.00327 |
Grade A, and why
meta-optimization-playbook 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Ads Optimization Playbook - B2B SaaS
What to do when things go right, wrong, or sideways. Decision trees, weekly cadence, thresholds, and benchmarks for managing B2B SaaS Meta accounts ($30K+ ACV).
Core Rule: Meta Thinks in Weeks, Not Days
Single-day or 3-day fluctuations are normal. Meta rotates audiences, tests delivery patterns, and adjusts. Never make decisions based on less than 7 days of data. Check results weekly, not daily.
The most common way to kill a winning campaign: Making changes every 2-4 days because a metric dipped. Let it run.
B2B SaaS Meta Benchmarks (2025-2026)
| Metric | Benchmark | Strong | Red Flag |
|---|---|---|---|
| CTR | 1.0-1.5% | 2.0%+ | < 0.8% |
| CPM | $10-20 | < $12 | > $25 |
| CPC (leads) | $1.50-2.50 | < $1.50 | > $3.50 |
| CPL (lead form) | $20-50 | < $25 | > $75 |
| Frequency (cold) | 1.5-3.0 | < 2.5 | > 4.0 |
| Frequency (retargeting) | 2.0-4.0 | < 3.0 | > 6.0 |
| MQL-to-SQL rate (Meta) | 5-10% | 15%+ | < 5% |
| Landing page CVR | 8-12% | 15%+ | < 5% |
Seasonal CPM swings:
- Q1 (Jan-Mar): Lowest CPMs - scale aggressively
- Q2 (Apr-Jun): Baseline (+10-20%)
- Q3 (Jul-Sep): Moderate increase (+15-25%)
- Q4 (Oct-Dec): Spike (+60-80%) - consider pausing or reducing B2B spend
Decision Tree 1: CPA Increasing
Trigger: CPA rises 20%+ above target for 2+ consecutive days.
CPA rising?
│
├─ Step 1: Check tracking
│ ├─ Pixel firing correctly? → If broken, fix immediately
│ ├─ CAPI sending events? → CAPI recovers 20-30% of lost conversions
│ └─ Attribution window correct? → B2B needs 7-day click minimum
│
├─ Step 2: Check frequency + creative fatigue
│ ├─ Frequency > 4.0? → Immediate creative refresh
│ ├─ CTR dropped 20%+ from baseline? → Creative fatigue, new concepts needed
│ └─ Frequency 3.0-4.0? → Warning zone, prepare replacement creative
│
├─ Step 3: Check learning phase
│ ├─ Made changes in last 7 days? → Learning phase reset. Wait.
│ ├─ Under 50 conversions this week? → Still in learning. Don't touch.
│ └─ Budget changed > 30%? → Learning phase reset. Roll back.
│
├─ Step 4: Check audience
│ ├─ Audience overlap between ad sets? → Consolidate or add exclusions
│ ├─ Audience saturated (small pool)? → Expand targeting or create lookalikes
│ └─ Irrelevant placements draining budget? → Check Audience Network, exclude if needed
│
├─ Step 5: Check landing page
│ ├─ Page load > 3 seconds? → 20% of clicks drop before page loads
│ ├─ Message mismatch between ad and LP? → Align copy
│ └─ Bounce rate spiked? → LP issue, not ad issue
│
└─ Step 6: External factors
├─ Q4 CPM spike? → Accept higher costs or reduce spend
├─ New competitor in auction? → CPM increase may be permanent
└─ Seasonal demand shift? → Adjust expectations
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 · 325 lines · 37 tokens per session scan A a7a64f72e36c
meta-optimization-playbook is a skill published in the GitHub repository swan-gtm/gtm-skills (221 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 3,268 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
paid-ad-copy-writer
Write paid ad copy for affiliate offers across ad platforms. Triggers on: "write ad copy", "Facebook ad for affiliate", "Google Ads copy", "TikTok ad script", "Pinterest ad", "paid traffic to affiliate", "create ad campaign", "ad headlines", "ad descriptions", "scale with paid ads", "run ads for my affiliate link"…
gooseworks
GooseWorks growth coworker and router for markets, competitors, audiences, creators, campaigns, ads, photos, graphics, video, content, email, SEO, social, leads and contacts. Use for brand facts or copy too, so offers, prices, rules, audience and bestsellers reach the brand's Marketing Brain.
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
yandex-direct
Skill "yandex-direct" from VKirill/claude-lane-stack, covering version requirements, usage, use this skill when, do not use this skill when and purpose.
yandex-direct-creatives
An advertising-writing guide for Yandex.Direct, a Russian online advertising platform. It turns keyword clusters from Key Collector, a keyword research tool, into campaigns, ad groups, and ads.