Prompts

Reusable prompts, system-prompt archives, and learning resources

Prompt

Spec Kit

github/spec-kit
Coding★ 133.4k

GitHub's official open-source spec-driven development toolkit, connecting requirements, clarification, planning, tasks, implementation, and convergence checks through reviewable prompt commands.

Tutorial & guideGitHub CopilotClaude CodeCodex CLI
Prompt

Prompt Engineering Guide

dair-ai/Prompt-Engineering-Guide
Prompt engineering★ 77.5k

An open learning resource covering prompting, context engineering, RAG, and AI agents.

Tutorial & guideMultiple models
Prompt

AI Agents for Beginners

microsoft/ai-agents-for-beginners
Education★ 74.6k

Microsoft's open 18-lesson AI agent course covers design patterns, tool use, agentic RAG, multi-agent systems, context, memory, deployment, and security with Python and .NET examples.

Interactive courseTutorial & guideMicrosoft Agent FrameworkMicrosoft Foundry
Prompt

Claude Cookbooks

anthropics/claude-cookbooks
Prompt engineering★ 51.8k

Anthropic's official collection of Claude examples and guides for tool use, the Agent SDK, extended thinking, multimodal work, evaluation, and prompting patterns.

Tutorial & guidePrompt collectionClaude APIJupyter Notebook
Prompt

Loop Engineering

cobusgreyling/loop-engineering
Agent orchestration★ 11.3k

Loop Engineering provides reusable prompt patterns, scaffolds, and CLI tools for running budgeted, human-gated repository loops such as daily triage, PR babysitting, and CI cleanup with Codex, Claude Code, Grok, and OpenCode.

Tutorial & guideCodexClaude CodeGrok
Prompt

专家会诊

maxiaobang7/agentmatter#content/prompts/12-practical-ai-prompts.md#prompt-06-expert-panel
Agent orchestration★ 1

Selects three genuinely complementary professional perspectives, compares their paths and risks, and uses cross-examination to identify consensus, disagreement, and assumptions.

Tutorial & guideText-based AI assistants
Prompt

换成好问题

unix2dos/brain-prompts#Alfred_Core.md#003_换成好问题
Prompt engineering★ 1

A two-turn prompt that delays the final answer, asks the model to identify assumptions, missing information, and a common mistake, and then asks one key question before responding.

Tutorial & guideMulti-turn AI assistantsAlfred Snippets