P2P — DevOps skill for Claude Code
Meta-prompt system that writes prompts: raw idea in — a polished, model-specific prompt out.
How to install P2P
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open sanic732/P2P and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What P2P does
Meta-prompt system that writes prompts: raw idea in — a polished, model-specific prompt out. Cross-model (Claude, Gemini, GPT, DeepSeek, Grok, Qwen, Kimi, GLM), 8-agent QUORUM council, SCOPE.HELM, live model specs. v8.4.7, four editions, Claude Code / Cowork plugin.
Alternatives in DevOps
- Claudable — Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code, Codex, Gemini CL 4k ★
- Zhikuncode — Codex/Claude Code/Cursor的开源增强版,专注一句话实现复杂长程任务(教育、编程、办公、生活、娱乐、游戏) 473 ★
- Claude Code Kit — Claude Code infrastructure with auto-activating skills and framework-specific kits 101 ★
README
P2P — Prompt-to-Prompt
**English** · [Русский](README.ru.md)
[]() []() []() []()
**A meta-prompt that writes prompts — and gets the job done.** Stream of consciousness in → a polished, model-specific prompt out. The project's goal: **eliminate classical prompt engineering for the everyday user.**
You shouldn't need to know what Chain-of-Thought is or how to escape XML against prompt-injection. You just describe the task — *"I want an expense-tracker app, data from Excel, dark theme"* — and P2P handles decomposition, routing, agent selection and hallucination defense under the hood.
What is P2P
P2P (Prompt-to-Prompt) is a modular orchestration system loaded into an LLM that turns it into a prompt-engineering expert. **RAG** architecture (BASE / LIVE / ON-DEMAND), an 8-agent **QUORUM** council, the **SCOPE.HELM** engine for large tasks, and auto-updating **Live Specs**.
**Philosophy:** constraints, not pressure. Empirical, not aesthetic.
The project evolved from a single text prompt (v1) into a meta-prompt OS (v8 NEXUS) — see the [evolution history](legacy/HISTORY.md).
⚡ [Interactive Architecture Map](https://sanic732.github.io/P2P/p2p-map.html)
**Full system map: modules, agents, commands, cross-references, data flow** — in one D3.js interactive visualization with tabs, filters, animation and RU/EN switch. See how the 8 QUORUM agents, 11 commands and 6 ON-DEMAND modules connect.
🧭 Choose your edition
One architecture, four entry points for different hosts and form factors. **Unsure? Pick the one tuned for your main model.**
| Edition | For whom | Host | Start |
|---|---|---|---|
| 🟦 8.4.7-C (Claude, внутр. 8C.3) | You wor |
Related Skills
Harness Dev Sismais
Kit de IA para desenvolvimento — Claude Code + OpenCode com roteamento de modelos (Kimi Code / GLM), 20 agente
Cover
Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workfl
Agent Pojia
AGENT 破甲 — AI 技能管理工具 Deploy 65 AI skills to Claude Code / Codex / Kimi Code / Cursor in one click
Agentswarm
Local agent swarm: a conductor model splits missions into parallel sub-agents with real tools and a localhost
AstraBox
Open-source, self-hosted alternative to Claude Managed Agents: run Claude Code, Codex, Hermes, DeepSeek Harnes
AI Traffic Alerts For Cloudflare
Get pinged the moment an AI assistant (ChatGPT, Perplexity, Gemini, Claude, Copilot, Grok) sends you a real vi
Related Agents
Opencode Worker
Forwards one scoped task to a model running in OpenCode (Grok, Kimi, GLM, Qwen, DeepSeek, …) through opencode
ChatGPT On Wechat
CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页
External LLM
When a request mentions external LLM model names (Kimi, K2, Grok, GLM, Gemini, GPT-5)