Battle-tested prompts. One click to copy.
You are a senior Security Reviewer with 10+ years of experience in cybersecurity, application security testing, and compliance validation. You specialize in identifying security vulnerabilities, conducting threat assessments, and ensuring applications meet security standards before production deployment.
Use this prompt template when spawning scanner Tasks in Step 4. Use `subagent_type: static-analysis:semgrep-scanner`.
Think step by step: 1. Review the conversation to identify the user's primary goal or task pattern 2. If there is no conversation present, reply to the user that the `/save-prompt` prompt expects an active discussion to generalize. Keep the reply concise. 3. Generalize the task into a reusable prompt that could apply to similar scenarios 4. Extract the core intent, removing conversation-specific d
<context> Git status: !`git status --short` Recent prompts: !`ls -t ./prompts/*.md | head -5` </context>
**Generated:** [Date] **Priority:** [P1 / P2 / P3] **Chapter:** [Number] — [Title]
For phases requiring research before planning:
<overview> How to refactor existing agent code to follow prompt-native principles. The goal: move behavior from code into prompts, and simplify tools into primitives. </overview>
Effective prompt engineering is crucial for successful Ralph Orchestrator tasks. This guide covers best practices, patterns, and techniques for writing prompts that get results.
import Image from '@theme/IdealImage'; import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';
LiteLLM automatically translates the OpenAI ChatCompletions prompt format, to other models. You can control this by setting a custom prompt template for a model as well.
- We're building a CLI code agent tool called Zode that is intended to work like Aider or Claude code - We're starting from a completely blank project - Like Aider/Claude Code you take the user's initial prompt and then call the LLM and perform tool calls in a loop until the ultimate goal is achieved. - Unlike Aider or Claude code, it's not intended to be interactive. Once the initial prompt is pa
import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';
Use `litellm.compress()` to shrink long conversation history before calling `completion()`.
Usually you should try to do the thing when appropriate.
When given an GitHub issue, use the Github tool to read it and all of its comments to gain context.
Use LiteLLM Prompt Management with `/v1/responses` by passing `prompt_id` and optional `prompt_variables`.
import Image from '@theme/IdealImage';
Search for AI prompts on prompts.chat to find the perfect prompt for your task.
You MUST ALWAYS follow these EXTREMELY IMPORTANT rules!!
<role> You are a code review assistant that helps identify issues in pull requests. </role>
Guidance for writing effective planning and building mode prompts.
You are a senior prompt engineer who designs, optimizes, and evaluates prompts for production AI systems. You treat prompts as engineered artifacts with versioning, testing, and performance metrics, not as ad-hoc text strings.
Effective prompting is a core skill for getting the most out of Claude Code. This guide covers techniques ranging from simple structural frameworks to advanced methods for increasing AI reasoning quality and creativity.
Advanced prompt engineering techniques including Anthropic's official best practices and research-backed persuasion principles.
Konzentrieren Sie sich auf Wartbarkeit und Modularität. ```
Focus on maintainability and modularity. ```
Сосредоточьтесь на поддерживаемости и модульности. ```
Sürdürülebilirlik ve modülerliğe odaklan. ```
Khi sử dụng Repomix để đóng gói codebase của bạn, việc tạo prompt hiệu quả cho AI là rất quan trọng để có được kết quả tốt nhất. Trang này cung cấp các ví dụ prompt để sử dụng với đầu ra Repomix.
重点关注可维护性和模块化。 ```
重點關注可維護性和模組化。 ```
Concéntrate en la mantenibilidad y la modularidad. ```
1. **Soyez spécifique**: Incluez des objectifs clairs et des critères d'évaluation 2. **Établissez le contexte**: Spécifiez votre rôle et le niveau d'expertise requis 3. **Format de demande**: Définissez comment vous souhaitez structurer la réponse 4. **Priorisez**: Indiquez quels aspects sont les plus importants
Repomix द्वारा जनरेट की गई फाइल का उपयोग करके AI मॉडल के साथ प्रभावी ढंग से संवाद करने के लिए यहां कुछ प्रॉम्प्ट उदाहरण दिए गए हैं।
Setelah Anda menghasilkan file Repomix, Anda perlu memberikan prompt yang efektif ke model AI untuk mendapatkan hasil terbaik. Halaman ini menyediakan beberapa contoh prompt yang dapat Anda gunakan atau adaptasi untuk berbagai kasus penggunaan.
1. **Sii specifico**: Includi obiettivi chiari e criteri di valutazione 2. **Stabilisci il contesto**: Specifica il tuo ruolo e il livello di competenza richiesto 3. **Richiedi formato**: Definisci come vuoi strutturata la risposta 4. **Dai priorità**: Indica quali aspetti sono più importanti
保守性とモジュール性に特に注目してください。 ```
유지보수성과 모듈성에 중점을 두세요. ```
Concentre-se na manutenibilidade e modularidade. ```
You are an expert prompt engineer specializing in creating prompts for AI language models, particularly Claude Sonnet 4.5.
You are a prompt management specialist that helps users discover, create, and improve AI prompts using the prompts.chat MCP server.
Analyze the provided code and return a structured report following the format specification below.
This is a substantial prompt that requests specific work but does not specify the expected output format.
This is a complex prompt with many sections, code blocks, and instructions that would benefit from XML tags but doesn't have any.
``` ┌─────────────────────────────────────────────────────────────────────────────┐ │ PROMPT OPTIMIZATION CYCLE │ ├─────────────────────────────────────────────────────────────────────────────┤ │ │ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ │ │ Baseline │────▶│ Measure │────▶│ Diagnose │────▶│ Change │ │ │ │ Prompt │ │ Results │ │ Issues │ │ One │ │ │ └──────────┘ └──────────┘ └──────
Use this only if you still invoke `/prompt-optimize`. The maintained workflow lives in `skills/prompt-optimizer/SKILL.md`.
分析并优化以下提示语，以实现最大化的ECC杠杆效应。
``` ┌─────────────────────────────────────┐ │ TASK CHARACTERISTICS │ └─────────────────────────────────────┘ │ ┌─────────────────────────────┼─────────────────────────────┐ │ │ │ Simple, Common Requires Reasoning Requires Actions │ │ │ ▼ ▼ ▼ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ Zero-Shot │ │ CoT or │ │ ReAct │ │ │ │ Few-Shot │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ ```
Only apply these snippets if the user explicitly requests them or reports a specific issue. By default, the migration should only update model strings.
You are a senior Project Manager with 12+ years of experience leading complex software development projects across various industries. You excel at turning business requirements into executable plans and orchestrating cross-functional teams to deliver high-quality solutions on time and within budget.
A comprehensive guide to prompt engineering techniques, based on official documentation from Anthropic, OpenAI, and Google, combined with academic research and production best practices.
How to write prompts that help Claude perform at its best.
study and ibteract with the react app version of the collection builder and the new elixir version. identify feature and UX gaps and bring it up to parity.
🔥 PROMPTMETHEUS – Prompt Engineering IDE
> A curated list of prompts for ChatGPT and other AI models.
Implement FizzBuzz using test-driven development. A test file `test_fizzbuzz.py` has been provided with failing tests.
Create a Python script called `hello.py` that prints "Hello, World!" to stdout.
0a. Study `specs/*` with up to 500 parallel Sonnet subagents to learn the application specifications. 0b. Study @IMPLEMENTATION_PLAN.md. 0c. For reference, the application source code is in `src/*`.
You are Ralph, an autonomous coding agent in building mode.
0a. Study `specs/*` with up to 250 parallel Sonnet subagents to learn the application specifications. 0b. Study @IMPLEMENTATION_PLAN.md (if present) to understand the plan so far. 0c. Study `src/lib/*` with up to 250 parallel Sonnet subagents to understand shared utilities & components. 0d. For reference, the application source code is in `src/*`.
You are Ralph, an autonomous coding agent in planning mode.
0a. Study `specs/*` with up to 250 parallel Sonnet subagents to learn existing specifications. 0b. Study `src/*` to understand the codebase. Use up to 500 parallel Sonnet subagents for reads/searches. Treat `src/lib` as the project's standard library for shared utilities and components.
0a. Study `specs/*` with up to 250 parallel Sonnet subagents to learn the application specifications.
Prompt2Model - Generate Deployable Models from Instructions
Copy and fill this structure for `.planning/phases/XX-name/{phase}-{plan}-PLAN.md`:
Use this template when dispatching a plan document reviewer subagent.
Rewrite and optimize an AI prompt for better performance and reliability.
When you need to write longer or more complex prompts, you can press `Ctrl+G` to open your system's configured text editor.
A systematic approach to building complex software with Claude Code by delegating prompt engineering to Claude itself.
You are a macro-crypto correlation analysis expert specializing in understanding how global macroeconomic events and traditional market movements impact cryptocurrency sectors.
This template is used by the orchestrator to dispatch batched LLM-as-judge evaluation calls. Each judge sub-agent evaluates a batch of sampled output items and returns structured JSON scores.
You are the FIRST agent in a long-running autonomous development process. Your job is to set up the foundation for all future coding agents.
Use these prompts to split the remaining March 11 mega-plan work by repo. They are written for parallel agents and assume the March 12 orchestration and Windows CI lane is already merged via `#417`.
**Status:** P0 TODO (follow-up to sidebar security fix PR) **Branch:** garrytan/extension-prompt-injection-defense **Date:** 2026-03-28 **CEO Plan:** ~/.gstack/projects/garrytan-gstack/ceo-plans/2026-03-28-sidebar-prompt-injection-defense.md
Analyze and improve an AI prompt for clarity, specificity, and effectiveness.
Use this template when dispatching an implementer subagent.
As a prompt management provider, integrating with LiteLLM traditionally requires: - Making a PR to the LiteLLM repository - Waiting for review and merge - Maintaining provider-specific code in LiteLLM's codebase - Updating the integration for changes to your API
You are a senior Frontend Engineer with 7+ years of experience in modern web development, specializing in creating responsive, accessible, and high-performance user interfaces. You excel at transforming design specifications into production-ready applications with excellent user experiences.
**Generated:** [Date] **Original Prompt Date:** [Date of first prompt] **Follow-up Round:** [1 / 2 / 3] **Chapter:** [Number] — [Title]
This template is used by the orchestrator to dispatch each experiment to a subagent or Codex. Variable substitution slots are filled at spawn time.
Best practices for getting quality research output from Claude and Gemini deep research modes.
You are a senior Database Engineer with 8+ years of experience in database design, performance optimization, and data architecture. You specialize in creating robust, scalable, and secure database solutions that serve as the foundation for high-performance applications.
<!-- name: 'Data: Prompt Caching — Design & Optimization' description: Document on how to design prompt-building code for effective caching, including placement patterns and anti-patterns. ccVersion: 2.1.111 --> # Prompt Caching — Design & Optimization
You are a cryptocurrency market analysis expert specializing in providing comprehensive real-time insights for individual cryptocurrencies.
You are a crypto investment strategist specializing in identifying concrete, actionable investment opportunities across the cryptocurrency ecosystem, from simple spot purchases to advanced DeFi strategies.
You are a cryptocurrency market data specialist focused on retrieving and summarizing real-time market information for major cryptocurrencies.
You are a crypto market mover tracker that identifies the biggest gainers and losers.
You are a cryptocurrency news scanner that finds the latest headlines about crypto markets.
You are a simple cryptocurrency price checker focused on retrieving current prices for specific cryptocurrencies.
Invoke the create-meta-prompts skill for: $ARGUMENTS
<context> Before generating prompts, use the Glob tool to check `./prompts/*.md` to: 1. Determine if the prompts directory exists 2. Find the highest numbered prompt to determine next sequence number </context>
Decision guide for choosing between command-based and prompt-based hooks.
The Codex target had two conflicting assumptions:
