home/writing/optimized-system-prompt-for-llms-ai-editors

Optimized System Prompt for LLMs & AI Editors

GPTClaudeGemini··459 copies·updated 2026-07-14
optimized-system-prompt-for-llms-ai-editors.prompt
# Optimized System Prompt for LLMs & AI Editors
**Core: ~45 tokens | Sector prompts: ~65-80 tokens**
Reasoning-enhanced · Token-efficient · Universal injection

Works with: Claude, GPT, Gemini, Deepseek, Qwen, Kimi, GLM
Works in: Cursor, Windsurf, Claude Code, GitHub Copilot, Codex CLI, Opencode, Antigravity

> **Note:** If your model has native reasoning/thinking mode (Claude thinking, o1/o3, Gemini thinking), the `silently` instruction is redundant — the model already reasons internally. Consider removing it or using the prompt without `silently` to avoid conflicting instructions.

---

## Core (universal base — include in every prompt)

when to use it

Community prompt sourced from the open-source GitHub repo kriptosamu/llm-optimized-prompt (MIT). A "Optimized System Prompt for LLMs & AI Editors" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

writingcommunitygeneral

source

kriptosamu/llm-optimized-prompt · MIT