AI Knowledge Hub
Menu

Marketing Plugins / Intelligence

ChatGPT Advertising Experiment Plugin

Install a task-led ChatGPT Ads experiment workflow with planning skills, read-only API access, conversion reconciliation, policy gates, and a one-command mock lab.

Not verifiedComponent bundleRequirements & limits

Inputs

  • The packaged experiment and conversion fixtures for the offline lab

Outputs

  • An offline experiment, conversion-validation and reconciliation evidence bundle

Before you begin

  • Python 3.9 or newer for the offline lab. Credentials are required separately for live reads.

Try this first

Inspect the packaged offline sample before running it. After file installation, use the stated runtime from the installed package directory.

Limits for this step
  • The included OpenAI Ads client does not mutate campaigns, ad groups, ads, files, or feeds.
  • Live provider writes remain unavailable until a supported OpenAI Ads mutation adapter is implemented and independently verified.
  • Packaged programs have independent setup and verification requirements. Reading or copying this procedure does not verify their execution.
Inspect offline sampleHide offline sampleSynthetic example

Runtime · Python 3.9 or newer. Run from the installed package directory after file installation.

python3 scripts/run_mock_lab.py

Expected result · output/mock-evidence-bundle.json from packaged fixtures, with no network calls.

This is the release’s documented sample, separate from evidence of operation in your environment.

Summary sources · Catalogue metadata, plugin.yaml, README.md, examples/experiment.json · v0.2.0 · Release package

View package contentsHide package contentsv0.2.0

Bundled skills

Bundled tools

Packaged hooks

require-measurement-before-activation

Require Measurement Before Activation

Trigger before any campaign activation or tracking change.

Intent

  • require a completed signal ownership ledger
  • require event IDs and deduplication rules for browser and server events
  • require an independently verifiable business outcome
  • block activation when platform-reported conversions are the only evidence source
  • require named approval owners for tracking and campaign changes

Install plugin files

These commands install package files and generate runtime configuration where supported. Confirm discovery in your agent app, then check configuration, authentication and a first useful operation.

Install (Codex)

./bin/skills-hub install --module plugins --entry marketing/[email protected] --runtime codex

Install (Claude)

./bin/skills-hub install --module plugins --entry marketing/[email protected] --runtime claude

Install (Generic)

./bin/skills-hub install --module plugins --entry marketing/[email protected] --runtime generic --target ./my-agent/plugins

Bundled skills, agents and tools are placed in the selected runtime directories. Hooks stay inside the plugin directory. Codex and Claude targets also receive a generated plugin manifest.

No security review is declared for this release. Review bundled components, required secrets and approval rules before live use.

How You Can Use This

Not verified

Resource form: Component bundle

Current operational evidence for your environment is not shown here. Check the implementation, installation requirements and limits before use.

First run: Run `python3 scripts/run_mock_lab.py` after installation to create an offline evidence bundle.

Setup required

  • Python 3.9 or newer is required to run the offline mock lab.

Current limits

  • The included OpenAI Ads client does not mutate campaigns, ad groups, ads, files, or feeds.
  • Live provider writes remain unavailable until a supported OpenAI Ads mutation adapter is implemented and independently verified.

Packaged executable helpers

Each program has its own setup requirements and operational evidence. Reading or copying the instructions does not verify these programs.

scripts/run_mock_lab.py · Not verified · Local program

First run: python3 scripts/run_mock_lab.py

  • Requires Python 3.9 or newer and performs no network calls.
What installation and verification mean
File installation
Places package files and generated configuration in the selected directories.
Native discovery
Your agent app finds and accepts the instructions, tools or plugin registrations.
Mock execution
Exercises sample fixtures. Connected data and provider effects need a separate check.
Connected operation
Requires current configuration, provider authentication, scoped permissions and a successful operation in your intended environment.

Declared compatibility

Compatibility unknown: versions and capabilities have not been declared.

Classification: inferred

Capability readiness

Mock lab

Not verified · Sample fixtures

Run the deterministic experiment, conversion-validation, and reconciliation workflow without credentials or network access.

  • Uses packaged fixtures only and cannot establish provider readiness.

Live read

Not verified · Read only

Read bounded OpenAI Ads account, campaign, ad, and insights data through the authenticated read-only client.

  • Configure and verify the included OpenAI Ads API client against the intended provider account.
  • Provider authentication attests the ad account rather than the individual human owner of the API key.

Live write

Unavailable

Live writes unavailable: no supported OpenAI Ads mutation adapter is included in this release.

Recorded classification · not-verified · Release declaration

  • No supported OpenAI Ads mutation adapter is included, so control-plane or executor setup cannot enable provider writes.
Technical details and release files

Review and lifecycle

Review maturity: Experimental

Security review declaration: Not declared

Lifecycle: Active

These release declarations are separate from evidence that a workflow operates in your environment.

Metadata

ID: marketing/chatgpt-advertising-experiment-plugin

Tags: chatgpt-ads, advertiser-api, experimentation, measurement, agentic-commerce, governance

Latest: 0.2.0

Runtimes: codex, claude, generic

Requirements

Secrets: 0

Approvals: 0