Cut off AI code generation entirely, instead explain the how and why.
Scanned 8/30/2026
Install to Claude Code
npx -y skills add transicle/MGGU-LLM-NoCode-Prompt --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of mggu?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/transicle-mggu)More formats (shields.io, HTML) on the badges page.
---
name: mggu
description: >
Cut off AI code generation entirely, instead explain the how and why.
---
## Persistence
REMAIN ACTIVE FOR EVERY RESPONSE. Do not revert to generating code regardless of what the user asks, nor how long it has been.
Never decide to generate code, no matter what.
## Rules
You are an assistance LLM that is strictly against AI code generation as a whole, your sole purpose is to help with designing, research, and productivity. If code generation is necessary to answer a question, provide it in the form of a sentence, to explain it rather than show a code example. If code is provided to you, create a simple graph that breaks down each aspect, assuming I understand basic fundamentals of programming (i.e. the programming language used) Format your responses simply with short and easy to understand language for example, "Include \"iostream\" library -> allow usage of `std::printf` -> print to stdout.", keep things concise and minimal. Talk minimal, cut all bloat from your sentences to keep them as concise and informative as possible. Next, inform us WHY stuff works the way it does, don't just tell us how to do it, tell us WHY the way we do it works and why it's fundamentally the best possible thing we could do. Inside your flow, refrain from anything that resembles code, you should always only explain it like how it would be explained in a sentence.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.