Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Ads Creative Factory

ASecurity

Use when producing ad creatives at volume: research angles, Ogilvy-style copy, Meta Ads Library checks, carousel builds, Meta publish with UTM, and HTML report. Triggers on \"ad creatives\", \"creative factory\", \"carousel ads\", \"publish meta ads\". Non-triggers: copy only with no production publish or report (use marketing-campaign). Outcome: a batch of published creatives with UTM plus a multi-ad HTML report.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill ads-creative-factory --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ads Creative Factory?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ads Creative Factory
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-ads-creative-factory/badge)](https://www.skillsdirectory.com/skills/majinmagros-ads-creative-factory)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: ads-creative-factory
description: "Use when producing ad creatives at volume: research angles, Ogilvy-style copy, Meta Ads Library checks, carousel builds, Meta publish with UTM, and HTML report. Triggers on \"ad creatives\", \"creative factory\", \"carousel ads\", \"publish meta ads\". Non-triggers: copy only with no production publish or report (use marketing-campaign). Outcome: a batch of published creatives with UTM plus a multi-ad HTML report."
metadata:
  origin: ECC
---

# Ads Creative Factory

Folders plus skills that close the loop: research -> copy -> creative ->
publish with UTM -> report. Copy alone is not the output; published ads
with tracking plus a report are.

## When To Activate

- The user says produce creatives, build carousels, publish to Meta, or
  run the full marketing process in folders.
- Output must include tracked publish (UTM) and a readable report.
- Angles must be grounded in SEO data and Ads Library research.
- Volume matters: batches of variants, not one-off posts.

## Workflow

1. Set up folders: one folder per stage (research, copy, creative,
   publish, report). Each folder has its own checklist and done rule.
2. Research: pull search demand for the offer, list competitor angles
   from the Meta Ads Library, and pick 3 angles to test.
3. Write copy: short Ogilvy-style variants per angle (headline, primary
   text, CTA). One promise per variant; cut the rest.
4. Build creatives: render statics and carousels from templates with a
   headless browser script. Fixed sizes, safe zones, and brand tokens.
5. Review gate: human picks keep, fix, or drop per creative. Only
   approved items advance to publish.
6. Publish with UTM: push approved creatives to Meta with campaign, ad
   set, and ad naming plus UTM on every link. Record IDs back to files.
7. Report: generate one HTML page with spend-to-date hooks, creative
   thumbnails, angles, UTM links, and status per ad.
8. Iterate: pause losers, vary winners (hook, image, CTA), and log the
   hypothesis per change for the next batch.

## Tracking Rule

- Every outbound link carries UTM (source, medium, campaign, content).
  No UTM = no publish. Pixel events are verified before spend scales.

## Anti-Patterns

- Copy with no publish and no report -> work that cannot be measured.
- Publishing without UTM -> unattributable traffic.
- Ripping competitor creatives instead of researching angles.
- One variant per angle -> no test, no learning.
- Skipping the human review gate before spend.
- Mixing naming conventions across batches.

## Relations

- `marketing-campaign`: copy and positioning; this skill adds production.
- `content-engine`: platform-native copy systems feeding the factory.
- `autopilot-content-factory`: autopilot posting after approval.
- `ads-operator`: account ops and hypothesis log for live campaigns.

## Exemplo

```text
Lote: 3 ângulos x 2 variantes = 6 criativos
research/oferta-x/angles.md → copy/ (headline+texto+CTA) → creative/ (1080x1080 + carrossel)
Review: keep 4, fix 1, drop 1 → publish com utm_source=meta&utm_campaign=oferta-x
Report: report-2026-09-13.html com gasto, thumbnails e status por ad
```

## Sources

- Meta Ads Library (angle research): https://www.facebook.com/ads/library/
- Meta Marketing API (campaign structure): https://developers.facebook.com/docs/marketing-api/

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →