Openai Ads logo

Openai Ads

Organization
hyperfx-ai
openai-ads

Plan and manage OpenAI Ads (ChatGPT ads) campaigns end-to-end via the Hyper MCP — API-key auth, account discovery, geo targeting, image upload, chat_card and product-feed creatives, custom audiences, conversion tracking, status flow, and insights, with integer-micros money values. Use when the user wants to launch OpenAI ads, ChatGPT ads, chat card ads, manage OpenAI ad groups or audiences, or pull OpenAI Ads insights.

Overview

Publisherhyperfx-ai
Repositorymarketing-skills
Skill nameopenai-ads
Stars
107
Forks
21
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hyperfx-ai on GitHub. Read the source before you install it.

Installation

Install the Openai Ads AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hyperfx-ai/marketing-skills/tree/main/skills/openai-ads
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hyperfx-ai/marketing-skills.git /tmp/marketing-skills
mkdir -p .claude/skills
cp -r /tmp/marketing-skills/skills/openai-ads .claude/skills/openai-ads
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Openai Ads in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Openai Ads on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Openai Ads is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OpenAI Ads Campaigns

Strategic guide for managing the OpenAI Advertiser API. All operations go through https://api.ads.openai.com/v1.

Requirements

If openai_ads_ad_accounts_get is not found, the integration to connect is OpenAI Ads. After connecting, openai_ads_health_check() verifies the key — if connected=false, the API key is missing, invalid, or expired.

How to run the tools in this skill

Every tool in this skill is named by its canonical tool name. Run it with the call your surface gives you:

SurfaceFind a toolRun it
Hyper chatCall the tool by its name; search_tools(queries=["<provider> <action>"]) shows its parameters<name>(...)
MCP client (Claude, Cursor, Codex, ChatGPT)search("<what you want to do>"), then describe("<name>")call_read("<name>", {...}), call_write or call_destructive: the one that describe names in call_with
Hyper CLIhyperai search "<what you want to do>", then hyperai describe <name>hyperai call <name> --json '{...}'

If a tool is not found: in Hyper chat, find its toolkit id with discover_toolkits and pass it to enable_toolkit. On an MCP client or the CLI, tell the user which integration to connect in Hyper.

Out of scope — defer to other skills

  • Creative generation (ad imagery, copy) → ad-creative-generation / image-generation.
  • Cross-platform campaign launches → use this skill for OpenAI Ads, then invoke meta-ads / google-ads separately.

Critical Rules

CRITICAL: Auth is bearer API-key auth, not OAuth. One Ads API key is scoped to exactly one ad account. There is no list ad accounts endpoint; openai_ads_ad_accounts_get returns the connected account for that key.

CRITICAL: All money values on inputs are integer micros. $1.00 = 1_000_000 micros. $50/day = 50_000_000. The daily_spend_limit_micros minimum is 1_000_000 ($1). The ad group max_bid_micros is capped at 100_000_000 ($100). Insights responses use plain floats in account currency, not micros.

CRITICAL: Always create campaigns, ad groups, and ads with status="paused". Surface what was created to the user, then activate using the dedicated activate endpoint after approval.

CRITICAL: Ads have review_status. New ads enter in_review and will not serve until review_status="approved", even if status="active".

CRITICAL: chat_card creatives require target_url and file_id. Upload the image first via openai_ads_images_upload, then pass the returned file_id to openai_ads_create. PNG, 1024x1024, <= 1 MB.

IMPORTANT: Creative types are chat_card and product_ad_template. Product-ad templates get image and destination URL from the selected product feed item, so they do not require file_id or target_url.

IMPORTANT: Campaign bidding_type can be impressions or clicks. Ad group billing_event_type can be impression or click.

Tool surface

JobTools
Accountopenai_ads_ad_accounts_get, openai_ads_update_ad_account, openai_ads_activate_ad_account, openai_ads_pause_ad_account, openai_ads_health_check
Campaignsopenai_ads_campaigns_create, openai_ads_campaigns_get, openai_ads_campaigns_list, openai_ads_campaigns_update, openai_ads_campaigns_pause, openai_ads_campaigns_activate, openai_ads_campaigns_archive
Ad groupsopenai_ads_ad_groups_create, openai_ads_ad_groups_get, openai_ads_ad_groups_list, openai_ads_ad_groups_update, openai_ads_ad_groups_pause, openai_ads_ad_groups_activate, openai_ads_ad_groups_archive
Adsopenai_ads_create, openai_ads_get, openai_ads_list, openai_ads_update, openai_ads_pause, openai_ads_activate, openai_ads_archive
Images & targetingopenai_ads_images_upload, openai_ads_search_geo_locations
Audiencesopenai_ads_create_custom_audience, openai_ads_create_custom_audience_upload, openai_ads_get_custom_audience, openai_ads_list_custom_audiences, openai_ads_archive_custom_audience
Conversionsopenai_ads_create_conversion_pixel, openai_ads_create_conversion_api_key, openai_ads_create_conversion_event_setting, openai_ads_list_conversion_event_settings, openai_ads_get_conversion_insights
Insightsopenai_ads_account_insights_get, openai_ads_campaign_insights_get, openai_ads_ad_group_insights_get, openai_ads_insights_get
Cache snapshotopenai_ads_cache, openai_ads_caches_get, openai_ads_caches_refresh

Phase 1: Account Discovery

Run these after connect:

text
openai_ads_ad_accounts_get()
openai_ads_campaigns_list(limit=100)
openai_ads_list_custom_audiences(limit=100)
openai_ads_list_conversion_event_settings(limit=100)

The connect-time context builder may have already populated a cached snapshot. Prefer:

text
openai_ads_caches_get()

If success=False because the cache is empty, refresh once:

text
openai_ads_caches_refresh()

Phase 2: Plan and Confirm

Before creating anything, confirm with the user:

  • Objective in plain language.
  • Daily and/or lifetime budget in account currency.
  • Target geos: simple country codes like ["US", "GB"], or location IDs from openai_ads_search_geo_locations.
  • Any custom audiences to include or exclude.
  • Whether this is a normal chat_card campaign or a product-feed campaign.
  • Headline (title, <= 50 chars), body (<= 100 chars), and click-through URL for chat_card.
  • One image asset for chat_card, either a public URL or a base64 blob.
  • Max bid in micros (max_bid_micros; for example 2_000_000).
  • Optional context_hints, short natural-language phrases that describe when the ad should show.
  • Optional conversion event setting IDs to attach to the campaign.

If anything is missing, ask. Do not invent budgets, geos, or copy.

All reference files live in references/. Read them at references/<file> (e.g. references/campaign-creation.md).

Routing table

The user wants to…Read these files first
Launch a chat card or product-feed campaignPhases 1–2 above → references/campaign-creation.md
Target regions / DMAs / custom georeferences/campaign-creation.md — Geo Targeting
Create or manage custom audiencesreferences/audiences-and-conversions.md
Set up conversion tracking (pixel, API key, event settings)references/audiences-and-conversions.md
Activate after reviewreferences/campaign-creation.md — Activation
Pull insights / manage status / refresh the cache snapshotreferences/insights-and-operations.md

Safety Rules

Never:

  • Pass dollar amounts directly. All money inputs are micros.
  • Activate a campaign, ad group, ad, or account without explicit user approval.
  • Skip image upload for a chat_card; it needs a real file_id.
  • Use geo exclusions; use included geos and audience exclusions instead.
  • Assume an ad is delivering just because status="active". Always check review_status.
  • Treat archive as reversible.
  • Promise paid traffic on a new ad. New ads sit in review_status="in_review" until OpenAI approves them.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Openai Ads AI skill do?

Plan and manage OpenAI Ads (ChatGPT ads) campaigns end-to-end via the Hyper MCP — API-key auth, account discovery, geo targeting, image upload, chat_card and product-feed creatives, custom audiences, conversion tracking, status flow, and insights, with integer-micros money values. Use when the user wants to launch OpenAI ads, ChatGPT ads, chat card ads, manage OpenAI ad groups or audiences, or pull OpenAI Ads insights.

Why use Openai Ads on TypingMind?

Because you install it once and use it with any model. Openai Ads is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Openai Ads in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hyperfx-ai/marketing-skills/tree/main/skills/openai-ads. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Openai Ads?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Openai Ads?

As many as you like. As long as a model supports skills, you can use Openai Ads with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Openai Ads AI skill free?

Yes. It is published on GitHub by hyperfx-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇