ervareza

Boost Skill — Data skill for Claude Code

Data community

Universal /boost multi-agent reasoning and independent verification pipeline for all AI coding CLIs (Hermes, Claude Code, Codex, OpenCode, Cursor, Aider).

How to install Boost Skill

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

What Boost Skill does

Universal /boost multi-agent reasoning and independent verification pipeline for all AI coding CLIs (Hermes, Claude Code, Codex, OpenCode, Cursor, Aider).

Alternatives in Data

Opencode Mem — OpenCode plugin that gives coding agents persistent memory using local vector database 1.5k ★
Autonovel — An autonomous novel writing pipeline, by Hermes Agent 1.5k ★
AI Data Extraction — extract all your personal data history from cursor, codex, claude-code, windsurf, and trae 1.3k ★

README

⚡ BOOST SKILL (Universal `/boost` Protocol)

Multi-Agent Reasoning & Independent Physical Verification Pipeline for All AI Coding CLIs

⚡ 1-Line Quick Install

Install **Boost Skill** across all detected AI agent environments on your machine in one command:

curl -fsSL https://raw.githubusercontent.com/ervareza/boost-skill/main/install.sh | bash

*Or install globally via npm / npx:*

npx boost-skill install

Automatically discovers and installs adapters for **Hermes Agent**, **Claude Code**, **OpenAI Codex CLI**, **OpenCode**, and adds the universal `boost` CLI binary to your PATH.

📖 What is the `/boost` Protocol?

In September 2026, Google introduced the **`/boost`** slash command in the **Google Antigravity CLI**, moving AI development away from fragile single-turn generation into a **distributed multi-agent reasoning and physical verification pipeline**.

Instead of an AI assistant generating code and asking you to review unverified files, `/boost`:

Isolates all work in an ephemeral Git worktree — keeping your active branch and working directory 100% clean.
Decomposes the problem across specialized subagent streams (Inv