indranilbanerjee/digital-marketing-pro

686 stars · Last commit 2026-08-01

Open-source AI marketing plugin for agencies & in-house teams — 158 skills, 25 specialist agents, 12-Part Strategy Flow, Cowork team-persistent, EU AI Act Article 50 ready, 6-platform AEO/GEO incl. Google AI Mode. Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. MIT-licensed.

README preview

# Digital Marketing Pro

> **Your agency just signed a 50-brand client. The previous agency left no playbook. Three brands are bleeding budget, two have stale positioning, one is launching in a regulated jurisdiction next month. Where do you start?**

Run `/digital-marketing-pro:engagement` against each brand. Same 12-Part Strategy Flow, same Four Core Documents, same 61-step structure — auditable across the entire portfolio in ~60 minutes per brand on Claude Opus-class models (measured on Opus 4.8; Opus 5 is the current equivalent at the same price). No more inconsistent depth between brands. No more "what did the last agency do?" mysteries. No more compliance gaps in regulated jurisdictions.

Open-source AI marketing plugin — **158 skills, 24 specialist agents, EU AI Act Article 50 ready, Cowork team-persistent**. Built for marketing agencies, in-house teams running 50–200 brands, and consultancies. Installs on **Claude Code** (CLI + IDE), **Anthropic Cowork**, **OpenAI Codex**, **Cursor 2.5+**, **GitHub Copilot CLI**, **Google Antigravity 2.0**, **Hermes Agent**, and **OpenClaw** + 35+ Agent Skills platforms. Created by [Indranil Banerjee](https://indranil.in) · [LinkedIn](https://www.linkedin.com/in/askneelnow/) · [X](https://x.com/askneelnow).

[![Version](https://img.shields.io/badge/version-3.17.1-blue.svg)](CHANGELOG.md)
[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
[![Stars](https://img.shields.io/github/stars/indranilbanerjee/digital-marketing-pro?style=flat&logo=github&color=yellow)](https://github.com/indranilbanerjee/digital-marketing-pro/stargazers)
[![Forks](https://img.shields.io/github/forks/indranilbanerjee/digital-marketing-pro?style=flat&logo=github&color=blue)](https://github.com/indranilbanerjee/digital-marketing-pro/network/members)
[![Issues](https://img.shields.io/github/issues/indranilbanerjee/digital-marketing-pro?logo=github)](https://github.com/indranilbanerjee/digital-marketing-pro/issues)
[![Last commit](https://img.shields.io/github/last-commit/indranilbanerjee/digital-marketing-pro?logo=github)](https://github.com/indranilbanerjee/digital-marketing-pro/commits/main)
[![Tests](https://img.shields.io/badge/tests-210%2F210%20passing-brightgreen.svg)](tests/)
[![Platforms](https://img.shields.io/badge/platforms-8%20native%20%2B%2035%20Agent%20Skills-success.svg)](#works-on-40-agent-harnesses-via-the-agent-skills-open-standard)
[![Cowork](https://img.shields.io/badge/cowork-team%20persistent-purple.svg)](#supported-surfaces-v3171)
[![EU AI Act](https://img.shields.io/badge/EU%20AI%20Act-Article%2050%20ready-darkred.svg)](skills/context-engine/compliance-rules.md)

> 🆕 **Just shipped — v3.17.1 (July 30, 2026): registry reconciliation + the anonymity guard.** The canonical model registry caught up with the July-9 GPT-5.6 GA and the Claude 5 family on its balanced/fast aliases (`latest-balanced-anthropic` → claude-sonnet-5, `latest-balanced-openai` → gpt-5.6-terra, `latest-fast-openai` → gpt-5.6-luna; GPT-5.5/5.4 marked superseded with replacement routing) — caught by this repo's own cross-registry drift tests. Plus a new machine-enforced source-anonymity guard that scans every file on every test run. Previously — **v3.17.0 (July 29): the Line-by-Line Audit.** Every one of the repo's 530 files — all 158 skills, 24 agents, 18 commands, 86 scripts, and every doc — was read end-to-end by a 16-reader audit fleet and re-verified against July-2026 ground truth. ~250 fixes shipped: dead platforms and retired tools purged (Google Podcasts, Chartable, GSC legacy tools, GARM, HARO, giropay…), stale API/model claims corrected, doc↔script contract drift eliminated (every documented flag, payload, and threshold now matches the code), the storage split-brain fully closed, statistical tables regenerated from the plugin's own calculators, and the self-containment guard extended to docs/, scripts/, and root. 210/210 tests green. [Read what's new →](#whats-new) · [Full changelog →](CHANGELOG.md)

View full repository on GitHub →