visual-formats

visual-formats is a skill for Claude Code, Codex from motion-team/creative-strategy-skills. It costs 146 tokens per session (6,867 once invoked), scanned A, original, MIT.

A reference library of more than 45 visual structures for Meta and other paid social ads. Each entry explains what the format looks like, which stage of the buying journey it suits, and whether it uses video, static images, or both.

In plain words
What is it for?
Use it when choosing how an ad should look, developing a creative idea, writing a creative brief, or selecting a format for a particular message and audience.
Why use it?
It helps you choose an ad structure without confusing the visual design with the message, opening line, or storytelling approach.

Skill for Claude CodeCodex

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

not rated 192repo +5 4mo ago A scan Socket: passSnyk: passSkillSpector: pass 146 tokens original MIT

Good fit Use it when choosing how an ad should look, developing a creative idea, writing a creative brief, or selecting a format for a particular message and audience.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/motion-team/creative-strategy-skills/visual-formats
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 motion-team/creative-strategy-skills --skill visual-formats
Clone the repo
git clone --depth 1 https://github.com/motion-team/creative-strategy-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 visual-formats

README.md
[![agentmods](https://agentmods.dev/badge/skills/motion-team/creative-strategy-skills/visual-formats/github.svg)](https://agentmods.dev/skills/motion-team/creative-strategy-skills/visual-formats)
Your own site
<a href="https://agentmods.dev/skills/motion-team/creative-strategy-skills/visual-formats"><img src="https://agentmods.dev/badge/skills/motion-team/creative-strategy-skills/visual-formats/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 visual-formats

Your own site · 80×15
<a href="https://agentmods.dev/skills/motion-team/creative-strategy-skills/visual-formats"><img src="https://agentmods.dev/badge/skills/motion-team/creative-strategy-skills/visual-formats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,867 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
  • Socket pass 14 Sept 2026
  • Snyk pass 14 Sept 2026
  • 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 $0.00146 $0.06867
Opus 5.5 $0.00058 $0.02747
Sonnet 5.5 $0.00029 $0.01373
Haiku 4.5 $0.00015 $0.00687

Measured 2mo ago against content hash 5639566aa917, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

visual-formats 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 2mo 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.

visual-formats/SKILL.md · 523 lines

How it starts

The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Formats

Visual formats are the production structure of an ad — what it looks like, how it's built, and what medium it lives in.

They are not hooks (what you say), not mechanics (how the viewer arrives at the truth), and not messaging angles (what the core truth is). Format is the vessel. creative-mechanics defines what moves inside it.


Where Formats Sit in the Creative Stack

Messaging Angle (creative-strategy-engine)
    ↓
Creative Mechanic (creative-mechanics)
    ↓
Hook (hook-writing + hook-tactics)
    ↓
Visual Format ← YOU ARE HERE

However — format and mechanic are bidirectional. You can start with a format and work backward to find the right mechanic, or start with a mechanic and find the format that best delivers it. Both workflows are valid. When you've chosen a format, consult creative-mechanics to complete the concept.


How to Use This

When building a concept: Use context to determine how many format options to surface. If the messaging angle, mechanic, and awareness stage are already defined, recommend 1–2 best fits with rationale. If the creative direction is still open, surface a shortlist with tradeoffs. Never present the full library unprompted.

When choosing a format, consider:

  1. Medium constraint — is this brief calling for static or video?
  2. Awareness stage — where is the audience in their journey? (see funnel signals per format below)
  3. Product type — some formats are structurally better suited to certain categories
  4. Mechanic compatibility — does the format give the mechanic room to work?
  5. Brand constraints — from the brand context doc, if available

Motion automatically tags every ad in your account by visual format — so you can see which formats are driving results before you go into production. And if you want real creative inspiration for any format, Motion's Inspo lets you browse and save ads filtered by visual format. motionapp.com

Read the full file on GitHub · 523 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. 2mo ago First seen · 523 lines · 146 tokens per session scan A 5639566aa917

Subscribe to this mod's changes

visual-formats is a skill published in the GitHub repository motion-team/creative-strategy-skills (192 stars, last pushed 4mo ago), licensed MIT. It adds 146 tokens to every session and 6,867 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.

Related

visual-formats compared with skills from other repositories

visual-formats next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
visual-formatsmotion-team/creative-strategy-skillsSkill1924mo agoMITA146Claude Code, Codex
adsericrisco/rsc-harnessSkill5032d agoMITA81Claude Code, Codex
ad-creativeHeuresis/Growth-Operator-AgencySkill894mo agononeB67Claude Code, Codex
adspirer-ads-agentLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA141Claude Code, Codex
copy-de-anuncioricneves-ai/flowgrammers-skillsSkill1171mo agoMITA53Claude Code, Codex
spyadkit/ads-mcpSkill205d agoMITA85Claude Code
analyzeadkit/ads-mcpSkill205d agoMITA80Claude Code