studio

A tool for generating advertising materials with AI, including images, written copy, and creative briefs. It can also clone, resize, or edit existing ad concepts and requires AdKit to be connected.

In plain words
What is it for?
Use it to make new ad creatives, adapt existing ads, prepare briefs, and produce image sizes such as square, landscape, or portrait.
Why use it?
It reduces the manual work needed to create ad variations for different audiences and placements.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/adkit/ads-mcp/studio
Any agent
npx skills add adkit/ads-mcp --skill studio
Clone the repo
git clone --depth 1 https://github.com/adkit/ads-mcp

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 716 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00091 $0.00716
Opus 5 $0.00046 $0.00358
Sonnet 5 $0.00018 $0.00143
Haiku 4.5 $0.00009 $0.00072

Measured 2d ago against content hash 9225c43b9dd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

studio 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 2d 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/studio/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Studio — AI Creative Generation

Requires AdKit to be connected — run /ads:setup first if needed.

1. Generate images

Use adkit_studio with entity: "ads" and action: "generate". Omit id to auto-create an ad, or pass an ad ID to add variants.

adkit_studio entity: "ads" action: "generate" params: { mode: "create", aspectRatio: "1:1", instructions: "Minimal SaaS hero image, dark background" }

Generate params

Param Description
mode create, clone, resize, edit (default: create)
aspectRatio 1:1, 16:9, 9:16 (required)
instructions Generation prompt
audience Target audience context
quantity 1-10 (default: 1)
model AI model (auto-detected from project config)
quality Model-specific quality setting
colors Hex color array, e.g. ["#FF5733"]
references Array for clone/edit/resize (see below)
title Used when auto-creating ad

Clone from library

Clone a proven competitor ad discovered via adkit_library:

adkit_studio entity: "ads" action: "generate" params: { mode: "clone", aspectRatio: "1:1", references: [{ type: "library-ad", id: "<adId>" }] }

Reference types

Type Use case
library-ad Clone/edit from a library ad by ID
media Reference a previously generated studio media item
temporary_upload User's own file (get uploadId via action: "request_upload_url" first)

Clone, edit, and resize each require exactly one reference.

2. Create a brief (optional)

adkit_studio entity: "ads" action: "create" params: { title: "Spring Sale Ad", specs: { format: "image", targetAudience: "SaaS founders" }, content: { headline: "20% Off", copy: "Start your free trial today" } }

3. Upload user files

Call entity: "media" action: "request_upload_url" with filename and contentType, PUT file bytes to the returned URL, then pass { type: "temporary_upload", id: "<uploadId>" } in generate references.

Read the full file on GitHub · 69 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. 2d ago First seen · 69 lines · 91 tokens per session scan A 9225c43b9dd5

Subscribe to this mod's changes

studio is a skill published in the GitHub repository adkit/ads-mcp (12 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 716 once invoked, about $0.0005 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 2026-08-30.