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 finsilabs/awesome-ecommerce-skills --skill meta-ads-integrationgit clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-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/finsilabs/awesome-ecommerce-skills/meta-ads-integration)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/meta-ads-integration"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/meta-ads-integration/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/finsilabs/awesome-ecommerce-skills/meta-ads-integration"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/meta-ads-integration.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 | $0.00035 | $0.02656 |
| Opus 5 | $0.00017 | $0.01328 |
| Sonnet 5 | $0.00007 | $0.00531 |
| Haiku 4.5 | $0.00003 | $0.00266 |
Grade A, and why
meta-ads-integration 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 9d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Ads Integration
Overview
Meta (Facebook/Instagram) is the dominant paid social channel for ecommerce, but reliable attribution requires pairing the browser-based Meta Pixel with server-side Conversions API (CAPI). Post-iOS 14, browser signals alone under-report 30–60% of conversions; CAPI restores signal fidelity by sending purchase events directly from your server. For Shopify, WooCommerce, and BigCommerce, official integrations handle both Pixel and CAPI automatically — no custom code required. Custom code only belongs in the Custom/Headless section.
When to Use This Skill
- When setting up Meta advertising for a new ecommerce store
- When conversion data in Ads Manager looks under-reported after iOS 14 rollout
- When launching Dynamic Product Ads (DPA) and needing catalog feed sync
- When ROAS is declining and you need to restore the signal quality Meta's algorithm relies on
- When adding retargeting audiences based on product viewers and add-to-cart events
Core Instructions
Step 1: Choose your integration approach
| Platform | Recommended Method | CAPI Support | Catalog Sync |
|---|---|---|---|
| Shopify | Native Meta Sales Channel | Yes (built-in) | Yes (automatic) |
| WooCommerce | Facebook for WooCommerce plugin | Yes (built-in) | Yes (automatic) |
| BigCommerce | Meta channel in Channel Manager | Yes (built-in) | Yes (automatic) |
| Custom / Headless | Meta Pixel + facebook-nodejs-business-sdk | Manual CAPI implementation | Manual feed generation |
All three major platforms have official Meta integrations that install both the Pixel and CAPI in a single setup — use these rather than manually pasting Pixel code.
Step 2: Connect your platform to Meta
Shopify
- Go to Shopify Admin → Sales Channels → + → Facebook & Instagram
- Install the Facebook & Instagram sales channel
- Connect your Meta Business Manager account and select your Facebook Page and Ad Account
- Under Data Sharing, select Maximum — this enables server-side CAPI in addition to the browser Pixel
- Shopify automatically:
- Installs the Meta Pixel on all pages
- Fires ViewContent, AddToCart, InitiateCheckout, and Purchase events
- Sends the same events via CAPI from Shopify's servers (deduplication handled automatically)
- Syncs your product catalog to Meta Commerce Manager for Dynamic Product Ads
- Go to Facebook & Instagram → Overview to verify pixel connection status
- In Meta Events Manager → Data Sources → [Your Pixel]: check Event Match Quality (EMQ) score — aim for 7+/10
What ships with it
7 files 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.
- evals/capi-server-side-event-tracking/criteria.json 2.4 KB
- evals/capi-server-side-event-tracking/task.md 2.3 KB
- evals/pixel-event-deduplication-and-pii-hashin/criteria.json 2.7 KB
- evals/pixel-event-deduplication-and-pii-hashin/task.md 2.7 KB
- evals/product-catalog-feed-generation/criteria.json 2.8 KB
- evals/product-catalog-feed-generation/task.md 3.8 KB
- tile.json 315 B
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.
- 9d ago First seen · 239 lines · 35 tokens per session scan A e4e6131fe955
meta-ads-integration is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (52 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 2,656 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
Facebook/Meta Ads
Automate Facebook and Instagram advertising campaigns, audience targeting, and performance optimization.
restaurant-ads
Facebook/Instagram ad copy variations — 10+ ad copy variants across happy hour, lunch, weekend brunch, catering, birthday/anniversary angles with A/B testing framework.
sealeap-amazon-apparel-lifecycle-ads
A playbook for planning advertising on Amazon US for clothing products, using an ASIN lifecycle. An ASIN is Amazon's product identifier; the lifecycle describes whether a product is new, growing, mature, declining, or seasonal.
sealeap-amazon-listing-optimizer
Audit, diagnose, rewrite, creatively brief, test, and safely prepare updates for Amazon product detail pages using live marketplace and product-type requirements, verified product facts, Brand Analytics, Search Query Performance, Ads search terms, customer feedback, competitor observations, and optional third-party…
sealeap-amazon-ca-apparel-ads
An Amazon Canada advertising planning guide for apparel products such as coats and underwear. It combines product life-cycle stages, seasonal timing, English and French search coverage, account evidence, profitability, and inventory considerations.
zernio
Schedule posts, manage inbox, broadcasts, sequences, and automations across 14 platforms from the CLI.