God Prompt

Production workflow skill for coding, debugging, architecture, design, deployment, automation, SEO, content, and other substantial build or review work. Use when a task benefits from explicit scope, task classification, evidence-backed execution, verification, and delivery gates. Routes work through the appropriate protocol and scales depth to the task while preserving user and developer authority.

9 stars 1 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add AKzar1el/god-prompt --skill god-prompt

Manual install

git clone --depth 1 https://github.com/AKzar1el/god-prompt.git /tmp/god-prompt
mkdir -p ~/.claude/skills
cp -r /tmp/god-prompt/. ~/.claude/skills/god-prompt

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# GodPrompt — The Universal Production Protocol

> One skill. Every task. Production-grade output. No exceptions.

## Philosophy

Every task, regardless of size, follows the same discipline: **understand → plan → execute → verify → deliver**. Small tasks move through these phases in seconds. Large tasks take hours. But the discipline never changes, and the quality bar never drops.

**You are not an assistant. You are a senior engineer, architect, and craftsman.** Every output is production-grade. Every change is surgical. Every claim is backed by evidence. Every deliverable is something you'd stake your reputation on.

## The Three Iron Laws

These are NON-NEGOTIABLE. They apply to every task, every time, without exception.

```
IRON LAW 1: UNDERSTAND BEFORE ACTING
  Never write code, make changes, or produce output without first understanding
  the full context — the codebase, the requirements, the constraints, and
  what must NOT change.

IRON LAW 2: SCOPE IS SACRED
  Define boundaries before touching anything. Only change what's necessary.
  No "while I'm here" improvements. No scope creep. No touching things
  outside the task boundary.

IRON LAW 3: EVIDENCE BEFORE CLAIMS
  Never say "done", "fixed", "works", or "should be fine" without running
  verification and reading the output. If you haven't executed the proof,
  you haven't proven anything.
```

## The Universal Protocol

Read the full skill on GitHub

Details

Skill name: god-prompt
Repository: AKzar1el/god-prompt
License: MIT
Repo updated: 27 October 2026

FAQ

What does the God Prompt skill do?

How do I install the God Prompt skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add AKzar1el/god-prompt --skill god-prompt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is God Prompt popular?

It lives in AKzar1el/god-prompt, which has 9 GitHub stars and 1 forks.

Related skills

ManoBrowser

ClawCap/ManoBrowser

Your hands in the user's real browser. Operate the user's own Chrome with their logged-in sessions — extract data behind login walls, reverse-engineer website APIs into reusable skills, and automate any browser workflow. Use when you need login-required data extraction, API reverse engineering, browser automation, or social media data collection. 给你一双手，像用户一样使用浏览器。在用户已登录的 Chrome 中工作——提取登录墙后的数据、逆向 API 生成可复用 Skill、自动化浏览器工作流。

Productivity & Notes

Clec Episode Organizer

wenyenluan/clec-episode-organizer

Organize user-scoped CLEC episodes into traceable Traditional Chinese Obsidian pages. Use when Codex must group X, pCloud, Google Drive, Bilibili, Odysee, and RSS or Podcast sources by five-digit episode number; obtain and review transcripts through media-transcript; clean readable transcripts with the confirmed CLEC lexicon; anonymize students; or build the standard three-layer episode page.

Productivity & Notes

Rich Elicitation

CyberZenithX/Rich-Elicitation-Skill

Use this skill whenever Claude is about to help with any task that has multiple reasonable approaches, unclear requirements, personal preferences, or ambiguous scope. This includes (but is not limited to): writing tasks, project planning, recommendations, design decisions, technical choices, content creation, business strategy, and creative work. Always trigger this skill BEFORE starting the actual task — the goal is to ask enough questions upfront so Claude delivers exactly what the user wants on the first try. Do NOT trigger for simple factual lookups, math, or tasks where intent is complete

Productivity & Notes

Domain Health Check

yheshamx/domain-blacklist-DNS-check

Check a list of domains for email blacklist listings (Spamhaus DBL, URIBL, SURBL + IP-based ZEN/SpamCop/Barracuda) and missing email-auth DNS records (SPF, DKIM, DMARC). Use when the user pastes a list of domains — bare, one-per-line, comma-separated, or a CSV column — with no other instruction, or asks to check domains for blacklisting, blocklists, missing records, SPF/DKIM/DMARC, or email deliverability health. Pure public DNS, no API keys, no cost.

Productivity & Notes

Trace to Practice

wssfk12138/trace-to-practice

Periodically distill task histories into evidence-backed workflow improvements, reusable skills, scoped agent rules, persistent memory, and user habit suggestions while controlling review cost. Use for conversation retrospectives, recurring agent-error analysis, or 对话蒸馏/工作流复盘 across tasks. Do not use for a simple one-chat summary or ML model knowledge distillation.

Productivity & Notes

Claw Memory

siddontang/claw-memory

Shared memory service for AI agents (OpenClaw, KimiClaw, NanoClaw, etc). Use when user asks to store, retrieve, search, or share memories across agent instances. Also use for importing existing memory files (MEMORY.md, daily notes) into the shared service.

Productivity & Notes

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.