Ads Meta
Run a structured Meta (Facebook, Instagram, Threads) ads audit with 50 checks before scaling spend in the Andromeda + GEM + Lattice delivery era.
Overview
ads-meta is an agent skill most often used in Launch (also Grow distribution and analytics) that runs a 50-check Meta Ads deep analysis for Facebook, Instagram, and Threads in the Andromeda, GEM, and Lattice era.
Install
npx skills add https://github.com/agricidaniel/claude-ads --skill ads-metaWhat is this skill?
- 50-check deep analysis across Pixel/CAPI health, account structure, ASC/AAC defaults, and audience targeting
- Andromeda, GEM, and Lattice-era guidance: creative diversity, Entity-ID clustering risk, and creative-as-targeting scori
- Advantage+ assessment for Sales, Leads, and App optimization objectives
- Covers Facebook, Instagram, and Threads advertising in one Meta Ads workflow
- Agent-triggered when users mention Meta/Facebook/Instagram/Threads ads, Advantage+, ASC, AAC, or Entity-ID clustering
- 50 checks across Pixel/CAPI health, creative diversity, account structure, ASC/AAC defaults, and targeting
- Covers Facebook, Instagram, and Threads in one Meta Ads analysis workflow
- Andromeda-era context: retrieval layer scales to vastly higher model capacity than the prior funnel (per Meta engineerin
Adoption & trust: 986 installs on skills.sh; 5.8k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are spending on Meta but cannot tell if Pixel/CAPI, Advantage+ defaults, creative diversity, or Entity-ID clustering are quietly throttling delivery and ROAS.
Who is it for?
Solo builders and tiny teams running or planning Meta paid campaigns who need a systematic audit against current Andromeda/GEM/Lattice mechanics.
Skip if: Organic-only growth plans, non-Meta channels (search, TikTok, LinkedIn only), or teams that already have a signed-off media plan and only need generic copy brainstorming.
When should I use this skill?
User mentions Meta Ads, Facebook Ads, Instagram Ads, Threads ads, Advantage+, ASC, AAC, Andromeda, GEM, Lattice, Entity-ID clustering, creative diversity, Sales optimization, Leads optimization, App optimization, or Meta
What do I get? / Deliverables
You get a structured audit across fifty checks plus Advantage+ and creative-as-targeting scoring so you can prioritize fixes before scaling campaigns.
- Structured Meta Ads audit aligned to ~50 checks and Advantage+ / creative-as-targeting assessment
- Prioritized findings on CAPI health, creative diversity, Entity-ID clustering risk, and account structure
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Paid Meta campaigns are a primary distribution lever when a solo builder is launching or pushing offers; this skill shelves under Launch because that is when most indies first stand up Pixel/CAPI, ASC/AAC, and creative testing. Distribution is the canonical subphase for channel-specific paid social analysis rather than organic SEO or in-product lifecycle messaging.
Where it fits
Before your product launch week, you audit Pixel/CAPI and ASC defaults so prospecting campaigns can learn cleanly.
CPMs spike after a creative refresh—you use the fifty-check pass to see Entity-ID clustering or CAPI gaps.
You are testing a landing page with a small Meta leads budget and want structure and Advantage+ leads settings reviewed.
Monthly you re-run the checklist after creative rotations to keep GEM-aligned diversity scores honest.
How it compares
Use this as a procedural Meta ads audit skill—not a one-off chat tip sheet and not an MCP server that connects to ad APIs by itself.
Common Questions / FAQ
Who is ads-meta for?
ads-meta is for solo and indie builders (and small teams) who run Facebook, Instagram, or Threads ads and want agent-guided deep analysis of Pixel/CAPI, Advantage+, ASC/AAC, and creative diversity without hiring a full-time performance marketer.
When should I use ads-meta?
Use it at Launch when you are turning on paid distribution, during Grow when you are scaling spend or debugging performance, and anytime you mention Meta Ads, Advantage+, ASC, AAC, Andromeda, GEM, Lattice, Entity-ID clustering, or Sales/Leads/App optimization in chat.
Is ads-meta safe to install?
Treat it like any third-party agent skill: review the Security Audits panel on this Prism page and only share ad account details or tokens you are comfortable exposing to your coding agent’s environment.
SKILL.md
READMESKILL.md - Ads Meta
# Meta Ads Deep Analysis ## Andromeda + GEM + Lattice (2026) Meta's delivery stack was rebuilt across three releases: - **Andromeda** (Oct 2025) — ad-retrieval ranking model with 10,000× more model capacity than the previous funnel ([Meta Engineering, Dec 2024](https://engineering.fb.com/2024/12/02/production-engineering/meta-andromeda-advantage-automation-next-gen-personalized-ads-retrieval-engine/)). Filters the candidate creative set before the auction layer ever sees it. - **GEM** (Generative Embedding Model, late 2025) — replaces the feature pipeline. Creative *content* embeds directly into the targeting space, which is why "creative is the new targeting" is now mechanical truth not slogan. - **Lattice** (rolled out late 2025 / early 2026) — sequence-aware optimizer on top of GEM that uses user-action sequences to rank candidate ads. Net effect: creative diversity is now the #1 performance lever. Ads with Similarity Score >60% (per [Confect's measured threshold](https://confect.io/tactics/meta-andromeda-2026)) get retrieval suppression — the algorithm clusters near-identical creatives and silently limits their delivery. **100 minor variations perform no better than 10 genuinely distinct ones.** Prioritize concept / angle / format diversity over variant volume. ### Creative-as-targeting scoring rubric When auditing a creative library against Andromeda's retrieval logic, score across these 5 axes (each 0-2, total 0-10): | Axis | 0 (Risk) | 1 (OK) | 2 (Strong) | |------|----------|--------|------------| | Concept diversity | Single core message / value prop across all assets | 2 distinct messages | 3+ distinct angles (problem-led, social proof, comparison, …) | | Format diversity | One format (e.g. all static image) | 2 formats | 3+ (image, video, carousel, collection) | | Visual diversity | One palette / one model / one composition | 2 distinct visual treatments | 3+ visually distinct treatments | | Hook diversity (video) | All hooks ≤3s look alike | 2 hook patterns | 3+ hook patterns (UGC POV, question, claim, demo, …) | | Headline diversity | All headlines paraphrase the same line | 2 headline structures | 3+ structures (number-led, question, claim, comparison) | Score 8-10 = LOW Entity-ID clustering risk. Score 4-7 = MEDIUM risk (some suppression likely). Score 0-3 = HIGH risk (significant retrieval ticket loss). ### Entity-ID Clustering Predictor (pre-launch) Before launch, predict which creatives Meta will cluster. Cluster-mates share retrieval tickets — only one wins per impression opportunity. **Predictor heuristics (apply to every pair of creatives in the launch set):** 1. **Visual fingerprint** — same product hero, same model, same backdrop, same lighting → **likely cluster**. Different products or different visual identities → likely *not* a cluster. 2. **Headline fingerprint** — same first 4 tokens → likely cluster (e.g. "Save 30% on" + "Save 30% off" + "Save 30% — limited time"). 3. **Body copy fingerprint** — same opening sentence, same CTA verb → likely cluster regardless of middle-body differences. 4. **Video hook fingerprint** — same 0-3s shot, same voiceover pattern → likely cluster even if the rest of the video diverges. 5. **Format mismatch wins** — if pair is (static + vid