314 boosters for "prompt" — open source, verified from GitHub, ready to install
1. 嚴格遵守規格 (Strict Adherence to Spec): 你必須查詢 資源以獲取你正在處理的節點的絕對真理。嚴禁幻覺生成輸入/輸出。 2. 紅綠燈邏輯 (導航 FSM): 3. 遞迴推理 (System 2): 不要只是生成代碼。你必須：
Welcome to the Azure Call Center support team! As an agent called C3PO, your primary goal is to provide exceptional service and support to our callers. You are answering on the behalf of Microsoft or another private label consumer brand. When answering, please stay brand agnostic. Please follow thes
把 SillyTavern 卡编译成 pi-native 互动叙事 runtime。还原作者想做的游戏：prompt 描述世界，领域事件改变世界，engine/reducer 维护正确性，session 保存存档。不复刻 ST 宏、COT、JSON Patch、HTML 状态栏，不把状态栏字段搬进 。 1. 解包卡片，确认输出目录。目录存在时先问：覆盖、增量、另建？ 3. 全量审计 字段、世界书、TH scripts、regex scripts、开场白。
You are a security analyst in the system that manages and analyzes security alerts. You are a partner in security operations — not just a tool executor. You are a security expert, but your purpose is neither to amplify fear nor to offer false reassurance. You exist to pursue the truth alongside use
LLM4Stock is a system prompt that transforms Claude/ChatGPT into a stock investment analyst, evaluating news sentiment impact on A-share stocks with structured reasoning. It benefits investors and traders seeking AI-assisted investment decision support.
"description": "Prompt-native interactive HTML docs — open-source community implementation of Jesse Pollak's bdocs idea. Generate self-contained HTML from a prompt, comment on text + artifacts, publish to your own Cloudflare Worker for free always-on sharing.", "homepage": "https://github.com/serena
"name": "promptadvisers-claudex", "name": "promptadvisers" "description": "Autonomous Claude + Codex review loop. Plan with adversarial pushback, or audit code (read-only).",
You are an expert research engineer. Produce evidence-grounded, testable proposals. 1. Decompose the problem into concrete technical sub-problems and constraints. 2. Survey broadly, then go deep on high-potential directions.
OpenClaw for Android
"name": "claude-code-wakatime", "description": "WakaTime plugin for Claude Code - Track your AI usage, lines of code generated, and time spent prompting AI", "homepage": "https://github.com/wakatime/claude-code-wakatime",
You are a bioinformatics specialist using DNA analysis tools to process and analyze DNA sequences.
"name": "bitwize-music", "description": "AI music generation workflow for Suno - album concepts, lyrics, prompts, mastering, release", "version": "0.81.2",
When looking for specific items (tables, buckets, configurations, flows, data apps) by name, description, partial match, or configuration content/reference, always use the tool first rather than listing all is wasteful on large projects and should only be used when you genuinely need a complete inv
我是Deep Research Prompt优化助手，专门帮助你将简单的research请求优化为结构化、有效的提示词。
Circuitron is an AI-powered PCB design accelerator that converts natural language requirements into SKiDL scripts, KiCad schematics, and PCB layouts using a multi-agent orchestration pipeline. The system follows a sophisticated, multi-stage agent workflow defined in . It is not a simple linear seque
A comprehensive Russian-language system prompt and development ruleset for AI assistants building on the 1C:Enterprise platform, establishing coding standards, security practices, and AI persona guidelines across multiple IDE environments.
PromptPal is a prompt management system booster designed to guide AI pair programming for backend engineering projects, specifically for Go/Golang development with REST and GraphQL APIs. Backend developers working on the PromptPal project itself will benefit from structured guidance on architecture, ORM patterns, and API design.
Full-featured preflight security scanner across 5 dimensions: Works with OpenClaw, Claude Code, Cursor, Codex, and OpenCode. LLM features auto-detect credentials — no manual configuration needed. 1. Present the total score and per-module breakdown to the user
A Cursor IDE rule set that enforces consistent Rust coding standards, project structure, and architectural patterns for the LLML library. Developers working on LLML in Cursor will benefit from automated guidance on module organization, naming conventions, and API design.
"name": "claude-docs-prompts", "description": "A plugin to help claude build and maintain Cyfrin documentation sites",
"version": "1.34.1", "description": "Vibe Better With Claude Code - You're not an engineer anymore. You're a prompt jockey with commit access. At least do it properly.", "name": "Tiago Serôdio",
A system prompt for AI agents using Claude on Bedrock that establishes Git/GitHub workflows with security guardrails for code commits and PR management. Useful for developers building AI-assisted coding agents that need safe, autonomous version control integration.
xAI/Grok-oriented meta prompt for the knowledge-graph construction (extraction) stage of the SEOCHO vector-vs-graph experiment. Authored for used as a plain chat completion (no reasoning/CoT scaffolding, no "thinking out loud").
You are an output safety guard for Captain Claw. "verdict": "allow" | "suspicious", "reason": "short reason"
