chatgpt-image-ad

chatgpt-image-ad is a skill for Claude Code from novoads/agent-skills. It costs 159 tokens per session (6,326 once invoked), scanned A, original, MIT.

A workflow for creating standalone image advertisements for Meta platforms with the ChatGPT Image 2 model, also called gpt-image-2. Meta platforms include services such as Facebook and Instagram.

In plain words
What is it for?
Use it when you need one or more static Meta ad creatives generated with ChatGPT Image 2.
Why use it?
It gives image-ad requests a fixed model and prepares the files for a separate Meta-ad-building workflow. It does not upload the ads to Meta.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is --source-image ./generated/T36-....png \.

Part of the skills plugin — 17 skills shipped together , and of skills

Good fit Use it when you need one or more static Meta ad creatives generated with ChatGPT Image 2.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/novoads/agent-skills
agentmods
npx agentmods add skills/novoads/agent-skills/chatgpt-image-ad

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 17 skills.

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 chatgpt-image-ad

README.md
[![agentmods](https://agentmods.dev/badge/skills/novoads/agent-skills/chatgpt-image-ad/github.svg)](https://agentmods.dev/skills/novoads/agent-skills/chatgpt-image-ad)
Your own site
<a href="https://agentmods.dev/skills/novoads/agent-skills/chatgpt-image-ad"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/chatgpt-image-ad/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 chatgpt-image-ad

Your own site · 80×15
<a href="https://agentmods.dev/skills/novoads/agent-skills/chatgpt-image-ad"><img src="https://agentmods.dev/badge/skills/novoads/agent-skills/chatgpt-image-ad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 182
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 205
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Tool Misuse · line 47
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Data Exfiltration · line 153
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Agent Snooping · line 334
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00159 $0.06326
Opus 5 $0.00079 $0.03163
Sonnet 5 $0.00032 $0.01265
Haiku 4.5 $0.00016 $0.00633

Measured 10d ago against content hash 8d3840c72f72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

chatgpt-image-ad scanned grade A with 1 finding 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_image.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -X POST "$NOVOADS_BASE_URL/v1/estimates" \
skills/chatgpt-image-ad/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chatgpt-image-ad

Generate one or more standalone Meta ad image creatives via Novoads' POST /v1/images with model: "gpt-image-2". Hands the image paths off to your Meta-ad-builder skill — this skill does not upload to Meta itself.

If the shared/ files are not on disk

Then this skill was installed on its own from skills.sh and the rest of the pack stayed behind. Fetch each missing file from https://raw.githubusercontent.com/novoads/agent-skills/main/<path>, where <path> is one of shared/skills/image-ad-prompting/OVERVIEW.md, shared/skills/image-ad-prompting/prompting/prompt-library.md, shared/skills/image-ad-prompting/prompting/safety-suffixes.md, shared/skills/image-ad-prompting/prompting/template-format.md and shared/skills/chatgpt-image-ad/prompting/guide.md. Or take everything at once with git clone https://github.com/novoads/agent-skills.git. That install has no scripts/check-novoads-env.sh either, so set NOVOADS_API_KEY in the environment yourself and let the first call report the key.

Read order

Paths below are from the repo root. This skill is copied into .claude/skills/ and .cursor/skills/ by sync-skill.sh, so a relative link out of it would break in those copies — read these from the repo you are working in.

  1. This file — endpoint, auth, upload flow, workflow phases.
  2. shared/skills/image-ad-prompting/OVERVIEW.md — the ecosystem hub: which skill, which model, what the family does and doesn't do.
  3. shared/skills/chatgpt-image-ad/prompting/guide.md — model-specific prompting (what gpt-image-2 is good/bad at, when to switch to nano-banana-pro).
  4. shared/skills/image-ad-prompting/prompting/prompt-library.md — 40 validated templates with per-model notes.
  5. shared/skills/image-ad-prompting/prompting/safety-suffixes.md — the 3 always-on guards.
  6. skills/chatgpt-image-ad/scripts/generate_image.py — the helper script (Python stdlib only).

For anything about the API itself that this file does not answer — error codes, rate limits, concurrency, the upload contract — the novoads-api skill's reference.md is the authority.

Read the full file on GitHub · 347 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 347 lines · 159 tokens per session scan A 8d3840c72f72

Subscribe to this mod's changes

chatgpt-image-ad is a skill published in the GitHub repository novoads/agent-skills (14 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 6,326 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

video-shotcraft

Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real page screenshots + 2.5D camera moves + beat-synced cuts + sound design). Use when the user asks to turn a frontend project or webpage into a product video, says "use video-shotcraft to make a…

Vincentwei1021/video-shotcraft · 204 tokens

xiaohongshu-auto-posting

Automates the complete Xiaohongshu (XHS / Little Red Book) content operation workflow: pain-point topic collection → style case collection → topic selection → content writing → publishing → performance tracking. Use when user mentions xiaohongshu auto posting, xhs auto post, little red book posting, xiaohongshu post…

browser-act/skills · 182 tokens

tiktok-shop-branding

Brand building and positioning on TikTok Shop. Brand identity development, content pillars, community engagement, brand storytelling, and authenticity strategies. Use when the user asks about TikTok branding, brand building, brand identity, or brand positioning on TikTok.

nexscope-ai/eCommerce-Skills · 55 tokens

tiktok-shop-content-strategy

TikTok Shop content creation strategy and planning. Trending formats, viral hooks, product showcasing, hashtag strategy, and content calendar development. Use when the user asks about TikTok content strategy, viral content creation, TikTok marketing, or content planning.

nexscope-ai/eCommerce-Skills · 56 tokens

ppt-design-skill

Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.

sunchaokun/PPT-Design-Skill · 35 tokens

etsy-digital-products

Digital product creation and selling — templates, printables, planners, digital art, delivery setup.

nexscope-ai/eCommerce-Skills · 23 tokens