AGENT SKILL

foxwell-meta-creative

Build a Meta creative testing and scaling plan using Andrew Foxwell's public framework. Use when choosing tests by budget, creative volume, data density and risk, briefing Yappers, or diversifying winning angles.

License 许可
Apache-2.0
所属仓库
getedgehq/skills
最近更新
2026-11-12
Stars
★ 5
Forks
0

01 前言 Front Matter

name
foxwell-meta-creative
description
Build a Meta creative testing and scaling plan using Andrew Foxwell's public framework. Use when choosing tests by budget, creative volume, data density and risk, briefing Yappers, or diversifying winning angles.

02 资源文件 7

03 SKILL.md 正文

Foxwell Meta Creative Framework

Based on Andrew Foxwell's public method. Not affiliated with or endorsed by Andrew Foxwell.

When to use

Use this skill to turn an account's economics, production capacity and performance history into a practical Meta creative testing system. It supports framework selection, creative briefs, Yapper scripts, winner evaluation and controlled scaling. The deliverable is a decision-ready plan with assumptions, trade-offs, budgets, review criteria and the next production batch.

Use it when a team cannot decide between separate testing ad sets and testing alongside existing winners, when creative production has outgrown the account structure, or when a successful angle needs more formats to support acquisition. It also helps diagnose why tests produce attractive small samples but fail to become scalable ads.

This is a synthesis of publicly accessible Foxwell Digital and Foxwell Founders material, including named community contributors. Read the source ledger before attributing a rule to Andrew personally. Keep source-backed guidance distinct from the package's suggested operational safeguards. The method is conditional: the objective is repeatedly discovering and scaling useful creative within business constraints, rather than defending one permanent account structure.

Procedure

  1. Establish the assignment and baseline. Read the intake guidance. Capture daily spend, test allowance, target acquisition economics, account maturity, weekly concepts and variants, conversion delay and management capacity. Identify missing inputs explicitly. If information is unavailable, produce a conditional plan with stated assumptions rather than inventing account facts.

  2. Check the economics before increasing traffic. Use the economics rules to separate affordable acquisition cost from platform ROAS. Identify contribution margin, AOV and first-time buyer performance. A proposed budget increase needs an economic reason and evidence that the business can support it.

  3. Choose a framework by fit. Apply the decision table to compare ABO, CBO with minimum spends, direct competition and manual bid testing. Recommend one primary approach, explain its trade-off, and name the condition that would make another approach preferable. Use a hybrid only when the two lanes have distinct jobs.

  4. Make the test affordable. Follow budget and exposure planning. Set simultaneous batches, daily allocation, review window and maximum acceptable loss. Separate batch exposure from individual ad exposure. Reduce the batch count when the budget cannot support interpretable learning.

  5. Write an explicit creative hypothesis. Follow creative research and diversification. Distinguish an exploratory new angle from a controlled iteration. Preserve the effective customer psychology while changing the visual entry point. Explain what each test can teach and what it cannot establish.

  6. Build a diverse, credible production batch. Use the format guidance to select founder, employee, testimonial, demonstration, static, partnership or other appropriate formats. Apply the scale-potential quality gate. Do not count cosmetic variations as meaningful diversity or invent customer experiences to fill a brief.

  7. Brief Yappers when appropriate. Use the Yapper specification for a natural single-take delivery: unconventional hook, specific lived problem, product bridge and gentle invitation. Include speaker context, substantiated proof, hook variants and a recording note. Preserve conversational delivery without manufacturing testimonials.

  8. Define evaluation before launch. Use winner and iteration rules. Record economics, delivery, purchases, attribution and diagnostic video metrics. Distinguish insufficient exposure, a relative improvement and an economically qualified winner. Plan monitoring for sudden allocation to new ads in large campaigns.

  9. Specify the scaling path and fallback. Follow the scaling rules. Choose scale in place, graduate, or both, and explain how results will be checked at the destination. Watch concentration and acquisition performance. A winner in testing does not automatically retain delivery elsewhere.

  10. Produce the deliverable. Fill the output template, keeping sourced guidance separate from local assumptions. Use the worked examples to calibrate specificity and budget arithmetic. Include owners, review dates, decision triggers and a learning log so the next cycle can use the findings.

  11. Review and revise the system. Run the pass/fail checklist. Repair unsupported attribution, unfunded tests and unclear decisions. If discovery or scaling stalls, propose a bounded comparison of testing approaches. Treat changes to live campaigns or paid production as separate actions requiring the user's applicable authorization.

Files in this skill

04 同仓库更多 Skills

getedgehq
getedgehq/skills

zero-downtime-cloud-move

Runbook for moving a live app from one cloud to another (Google Cloud to AWS, AWS to Google Cloud, a PaaS to your own account, or one storage provider to another) without downtime. The agent inventories what is really running, builds the new stack next to the old one, keeps a one-line rollback for every phase, proves the new stack with real workloads before any traffic moves, cuts over with a checklist, watches a fixed window after the switch, copies data with an idempotent job whose second pass must report 0 left, and deletes the old cloud last. Use when someone asks to migrate, move or replatform a production app, switch cloud providers, move a backend, database files or object storage, plan a DNS cutover, or decommission an old cloud account.

★ 5
getedgehq
getedgehq/skills

zayats-ceo-branding

Build an evidence-based CEO positioning paper, Personal Branding Roadmap, and editorial workflow using Marina Zayats's public method. Use for executive branding, LinkedIn ghostwriting briefs, profile strategy, and recurring CEO-approved content planning.

★ 5
getedgehq
getedgehq/skills

yc-app-roast

YC App Roast: roast a YC or a16z Speedrun application. Use when a founder wants their YC or Speedrun answers scored, asks "what would a YC partner think", wants the weak answers found or rewritten, or wants their draft checked before they submit. Scores every answer 0-10 against public advice from YC and Speedrun partners, names the top issue with the exact words that cost points, and writes a rewrite from the founder's own facts. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.

★ 5
getedgehq
getedgehq/skills

yc-app-review

YC App Review: get a YC or a16z Speedrun application reviewed by people you trust. Use when a founder wants friends, mentors or alumni to review their YC or Speedrun application, or asks to share their draft for feedback. Builds a shareable review page (one HTML file, application-portal look) where reviewers leave notes per question and press "Send my notes" to send them back as text, then parses the notes into proposed rewrites. Optional tracked private links per reviewer. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.

★ 5
getedgehq
getedgehq/skills

x-growth-playbook

X Growth Playbook. Analyse a person's own X (Twitter) posts and tell them what to post next, with the numbers behind every claim. Compares quote posts vs originals, links vs no links, short vs long, time of day in their timezone, media vs text and the topics they name, reports medians with n, then writes a 10-step plan and the next 7 posts in their voice. Use when the user says "analyse my X posts", "what works on my Twitter", "how do I grow on X", "what should I post next on X", "audit my X account", or shares an X data archive, X API export or a list of their posts. Runs on the user's computer.

★ 5
getedgehq
getedgehq/skills

workplan

Create, update, or close work plans for multi-step tasks. Use when starting refactors, bug lists, feature work, migrations, or any task with 2+ steps. Also use after auto-compaction to re-orient. Triggers: "workplan", "work plan", "create a plan", "what's the plan", "where was I", or when Claude detects a multi-step task that needs tracking.

★ 5