indranilbanerjee/contentforge

20 stars · Last commit 2026-08-01

Open-source enterprise content production plugin — 21 skills, 13 agents, 11 quality gates, 29-pattern AI humanizer, fact-checker, real .docx output with C2PA signing (EU AI Act Article 50 ready). Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. By Indranil Banerjee (indranil.in).

README preview

# ContentForge

> **You need to ship 30 articles this quarter that pass GPTZero, sound human, cite real sources, and route to the right internal pages. Your team is three people. You have nine weeks. Your last "AI-written" batch got flagged by the editor for hallucinated stats.**

Run `/contentforge:create-content` against each topic. The 10-phase pipeline produces a publication-ready `.docx` with 35-pattern humanizer, fact-checker subagent, three-category internal linking, and C2PA provenance for EU AI Act compliance — in 30–60 minutes per piece on Claude Opus 4.8. No re-edits for AI voice. No hallucinated citations. No orphan content.

Open-source enterprise content production pipeline — **22 skills · 13 specialist agents · 10 quality gates · 35-pattern AI-detection humanizer**. Built for marketing teams producing high volumes of long-form content that need brand voice consistency, citation integrity, and an internal-link strategy that turns content into a funnel. 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-3.18.2-blue.svg)](CHANGELOG.md)
[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
[![Stars](https://img.shields.io/github/stars/indranilbanerjee/contentforge?style=flat&logo=github&color=yellow)](https://github.com/indranilbanerjee/contentforge/stargazers)
[![Forks](https://img.shields.io/github/forks/indranilbanerjee/contentforge?style=flat&logo=github&color=blue)](https://github.com/indranilbanerjee/contentforge/network/members)
[![Issues](https://img.shields.io/github/issues/indranilbanerjee/contentforge?logo=github)](https://github.com/indranilbanerjee/contentforge/issues)
[![Last commit](https://img.shields.io/github/last-commit/indranilbanerjee/contentforge?logo=github)](https://github.com/indranilbanerjee/contentforge/commits/master)
[![Tests](https://img.shields.io/badge/tests-173%2F173%20passing-brightgreen.svg)](tests/)
[![Platforms](https://img.shields.io/badge/platforms-8%20native%20%2B%2035%20Agent%20Skills-success.svg)](#supported-surfaces-v3182)
[![Cowork](https://img.shields.io/badge/cowork-compatible-purple.svg)](#cross-platform-compatibility)
[![EU AI Act](https://img.shields.io/badge/EU%20AI%20Act-Article%2050%20ready-darkred.svg)](docs/c2pa-production-cert.md)

> 🆕 **Just shipped — v3.18.2 (July 30, 2026): four new capabilities, execution-verified + the anonymity guard.** **Author/E-E-A-T byline layer** (`author_profiles` in the brand profile → Phase 3 byline → Person JSON-LD in Phase 6 — no more authorless content), **Case Study** and **Newsletter** as built-in content types 7 and 8 (case studies enforce a client-data provenance rule: fabricating a client metric halts the pipeline), and **`/contentforge:cf-aeo-check`** — a post-publication AI-citation check that probes your target queries, audits on-page extractability, tracks deltas across re-checks, and routes losses to `content-refresh` with evidence. 22 skills, 173 tests. [Full changelog →](CHANGELOG.md)

View full repository on GitHub →