creative-cadence-operating-system

creative-cadence-operating-system is a skill for Claude Code, Codex from swan-gtm/gtm-skills. It costs 35 tokens per session (4,859 once invoked), scanned A, original, MIT.

A system for planning the production of Meta advertising creative, including concepts, formats, testing, iteration, and retirement. Creative means the words, images, videos, or carousels people see in an ad.

In plain words
What is it for?
Use it to plan creative schedules, prioritise changes such as hooks and visuals, source concepts, choose formats, run tests, score quality, and retire ads.
Why use it?
It gives teams a repeatable way to decide what to make, what to change in a working ad, and when to replace an ageing one. This keeps creative testing tied to campaign performance.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan creative schedules, prioritise changes such as hooks and visuals, source concepts, choose formats, run tests, score quality, and retire ads.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swan-gtm/gtm-skills/creative-cadence-operating-system
Install

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.

Any agent
npx skills add swan-gtm/gtm-skills --skill creative-cadence-operating-system
Clone the repo
git clone --depth 1 https://github.com/swan-gtm/gtm-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for creative-cadence-operating-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/creative-cadence-operating-system/github.svg)](https://agentmods.dev/skills/swan-gtm/gtm-skills/creative-cadence-operating-system)
Your own site
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/creative-cadence-operating-system"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/creative-cadence-operating-system/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.

agentmods 80×15 button for creative-cadence-operating-system

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/creative-cadence-operating-system"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/creative-cadence-operating-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,859 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.04859
Opus 5 $0.00017 $0.02429
Sonnet 5 $0.00007 $0.00972
Haiku 4.5 $0.00003 $0.00486

Measured 8d ago against content hash b3dcc30fd55f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

creative-cadence-operating-system 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 8d 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.

skills/ivan-falco/creative-cadence-operating-system/SKILL.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creative Cadence Operating System - Meta B2B

The complete system for what creative to build, when to build it, how to iterate, and when to retire it. Companion to the Meta Ads Operating System (which governs when to swap/graduate/scale ads). This system governs the CREATIVE PRODUCTION pipeline that feeds the OS.


Core Principle

Creative accounts for 56-70% of ad performance on Meta (post-Andromeda). The algorithm uses creative - copy, images, video transcripts, carousels - as the primary signal for who to serve your ads to. Targeting inputs are suggestions; creative is the real filter.

Your creative is your targeting. Your hook is your filter. Your iteration velocity determines your scaling ceiling.


1. The Iteration Priority Hierarchy

When iterating on a winning ad, change elements in this order. Each element has decreasing impact on performance.

Priority Element Impact Reasoning
1 Hook (first 3 seconds / first line) Highest 90% of viewers decide in the first 3 seconds whether to engage. The hook determines who stays. Changing the hook changes who your ad reaches - it's the single highest-leverage creative variable.
2 Visual Treatment High Human faces increase engagement 38%. 4:5 aspect ratio delivers 18% higher CTR and 22% lower CPA than other ratios. The visual is what stops the scroll.
3 Format (static/video/carousel/UGC) Medium Format determines consumption pattern. Video allows storytelling (21-35 day lifespan), carousel allows multiple hooks (21-35 days), UGC builds trust (28-42 days). Format change = "new ad" to the algorithm.
4 Body Copy / CTA Lower Once someone is hooked, body copy matters less than the initial capture. CTA changes produce marginal differences unless the CTA is fundamentally mismatched.

Why Hook-First?

  • 90% of people bounce if not captured in 3 seconds (video) or 1-2 seconds (static)
  • Target hook rate: 20-25% (people who watch past 3 seconds / total impressions)
  • Hook rate below 15% = the ad will never perform, regardless of body quality
  • Changing the hook on a winning concept can extend its lifespan by 2-4 weeks

Read the full file on GitHub · 376 lines

Changes

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.

  1. 8d ago First seen · 376 lines · 35 tokens per session scan A b3dcc30fd55f

Subscribe to this mod's changes

creative-cadence-operating-system is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 4,859 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.

Related

Other skills, from other repositories

update-brand-kit

Maintain a brand kit — the canonical brand context an ad or content pipeline reads (positioning, audience, voice, standing instructions, brand-type, value-props, colors), plus manage the product list and attach product photos. Use when someone says "update my brand kit", "set my brand voice/audience", "add a product…

gooseworks-ai/goose-skills · 126 tokens

studio

Generate AI ad creatives — images, copy, and briefs. Use when the user wants to generate ad images, create ad creatives with AI, make an ad, build a creative brief, clone a competitor ad, resize creatives for different placements, or edit existing images. Also use when the user mentions "AI ad generation", "ad…

adkit/ads-mcp · 91 tokens

ad-read-script

Turns a brand brief into a host-read ad script that fits the show's tone, meets sponsor requirements, and sounds spoken — not read.

ur-grue/autopunk-media-skills · 31 tokens

autonomous-facecam-editing

Transformer une prise talking-head brute (une personne face caméra) en pub motion-graphics 9:16 prête pour Meta/TikTok — pré-cut des silences, recadrage serré carré + plein cadre centré visage (miroir optionnel), transcription mot-à-mot, charte volée au site, storyboard « une carte par phrase » (count-ups, listes…

gquthier/autonomous-shortform-facecam-editing · 191 tokens

ads-creative

Creative Brief Generator for designers, video editors, and content teams.

zubair-trabzada/ai-ads-claude · 16 tokens

ad-creative-agent

A guide for editing one user-supplied photo, such as changing its background, removing objects, retouching it, or applying a visual style.

DeepKolor/deepkolor-agent-skills · 202 tokens