numman-ali

Editorzero — AI skill for Claude Code

AI community

Open-source, self-hostable AI-native docs platform.

How to install Editorzero

This entry records only its repository, not the path inside it, so there is no exact command to give. Open numman-ali/editorzero and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Editorzero does

Open-source, self-hostable AI-native docs platform. Humans and AI agents as peer co-editors. Phase 1: architecture and ADRs.

Alternatives in AI

Multica — Make humans and AI agents work as one team — open-source and self-hostable 47.8k ★
WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
Skill Seekers Roadmap — Transform Skill Seekers into the easiest way to create Claude AI skills from any knowledge source - documentat 11.1k ★

README

**AI-native, self-hostable docs. Humans and agents as peer co-editors.**

One capability layer. Four surfaces: API · CLI · MCP · Web UI. Full parity, enforced.

🧪 **A real production experiment in complex agentic engineering.** Every line of code, every ADR, every architectural decision is driven end-to-end by Anthropic's frontier Opus model (currently Opus 4.8, 1M-context).

[![Status](https://img.shields.io/badge/status-Phase%203%20%C2%B7%20WIP-orange.svg)](docs/continuation.md) [![License](https://img.shields.io/badge/License-AGPL--3.0-blue.svg)](LICENSE) [![Node](https://img.shields.io/badge/Node-22%20LTS-3fb950.svg)](package.json) [![Built with Opus 4.8](https://img.shields.io/badge/built%20with-Claude%20Opus%204.8-8b5cf6.svg)](https://www.anthropic.com)

[Status](#-status) · [What It Is](#-what-is-editorzero) · [Experiment](#-the-experiment) · [Invariants](#️-hard-invariants) · [Parity](#-four-surface-parity) · [Roadmap](#️-roadmap) · [Contributing](#-contributing)

🚧 Status

**Work in progress.** The compiled `ez` CLI is the first runnable artifact (verified end-to-end); the Web UI is not yet built. The platform is currently in **Phase 3 — verification harness + feature slices**.

Phase	What	State
0 · Orient	Brief, invariants, working assumptions	✅ Closed
1 · Research + ADRs	20 ADRs (0001–0020), cross-model red-team	✅ Closed
2 · Architecture	End-to-end design, 3 red-team passes (including cross-model)	✅ Closed
3 · Verification harness + feature slices	24 capabilities across doc / collection / workspace / audit; API + CLI + MCP adapters live; full test lanes	🏗 In progress
4 · Feature slices	Full capability surface across all four adapters	—
5 · Hardening + launch	Security pass, load tests, runbook, threat model	—