agentleFS
Sign inStart free
imMamdouhaboammarimMamdouhaboammar/chatgpt-ads/llms-full.txt

chatgpt-ads

llms.txt1 starsChanged 2 months agoMITView on GitHub

Universal AI knowledge base and operating skill pack for ChatGPT Ads research, planning, creative generation, measurement, and guarded automation across Claude, Codex, Cursor, and Gemini CLI.

The file

Create a free account to mount
Files
llms-full.txt
# ChatGPT Ads Multi-Agent System

> Universal AI knowledge base and operating skill pack for ChatGPT Ads research, planning, creative generation, measurement, and guarded automation across Claude, Codex, Cursor, and Gemini CLI.

- Author: Mamdouh Aboammar (https://github.com/imMamdouhaboammar)
- Repository: https://github.com/imMamdouhaboammar/chatgpt-ads
- Version: 0.4.0
- License: MIT

## Core Overview
ChatGPT Ads is an independent, MIT-licensed knowledge and operating engine designed for AI agents and developers building automated, privacy-preserving advertising workflows on ChatGPT. It adheres to strict fail-closed security invariants, POSIX descriptor-backed path traversal (O_NOFOLLOW), and deterministic evidence tracking.

## Architecture & Skill Manifests
- [Main Skill Orchestrator](SKILL.md): Master router dispatching across 12 domain skills.
- [OpenAI Codex Plugin Manifest](.codex-plugin/plugin.json): Configuration for OpenAI Codex and ChatGPT developer sessions.
- [Claude Marketplace Manifest](marketplace.json): Plugin schema specification for Claude Desktop and Claude Code.
- [Skills.sh Registry Manifest](.skills.json): Hub listing enabling `npx skills add imMamdouhaboammar/chatgpt-ads`.
- [Knowledge Brain Index](brain/index.md): Sourced facts, claims, and verified citations.

## The 12 Domain Skills
1. `chatgpt-ads`: Orchestrator and workflow router.
2. `chatgpt-ads-research`: Sourced platform evidence verification and ledger queries.
3. `chatgpt-ads-readiness`: Client eligibility, ad policy prerequisites, and account setup.
4. `chatgpt-ads-plan`: Campaign strategy, pacing budgets, and unit economics.
5. `chatgpt-ads-creative`: Ad copy briefs, multi-modal prompt variations, and compliance.
6. `chatgpt-ads-measurement`: Attribution modeling, conversion tracking, and tracking integrity.
7. `chatgpt-ads-analyze`: Performance diagnostics, funnel degradation, and anomaly analysis.
8. `chatgpt-ads-experiment`: Geo-lift and A/B split testing methodology.
9. `chatgpt-ads-policy`: Advertising guidelines and regulatory constraints.
10. `chatgpt-ads-launch`: Staged change validation and batch verification.
11. `chatgpt-ads-operate`: Guarded account operations with local checkpoint locks.
12. `chatgpt-ads-monitor`: Pacing alerts, drift monitoring, and anomaly detection.

## CLI & Runtime Invariants
- Safe I/O: POSIX descriptor-backed no-follow traversal, Darwin root alias normalization.
- Zero credential leakage: Scanned against secret patterns before public release.
- Bounded local queries: `python3 -m chatgpt_ads_brain query "<question>"`.

## Comprehensive File Index
- [Operator Kit](docs/OPERATOR_KIT.md): Deterministic verification suite and packaging guide.
- [Product Boundaries](docs/PRODUCT_BOUNDARIES.md): Distinction between local simulations and live account actions.
- [Quickstart Guide](docs/QUICKSTART.md): Step-by-step synthetic first run.
- [Security Policy](SECURITY.md): Vulnerability disclosure and offline secret detection.
- [Changelog](CHANGELOG.md): Version release history and audit hardening.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free