Browse all resources

A community-built prompt discovery and collection project with a website, CLI, plugins, and MCP support.

An archive of system prompts, tool definitions, and model information organized by AI product.

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

Anthropic's official interactive course covering prompt structure, few-shot examples, tool use, and retrieval.

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.

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

Microsoft's open generative AI course with 21 lessons on prompt engineering, text apps, chat, search, image generation, and agent foundations.

The example collection from the official OpenAI Cookbook, covering prompt design, structured outputs, tool use, evaluation, and production patterns.

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.

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

A collection of reusable Markdown Prompt Patterns, strategies, and a Go CLI for building inspectable, customizable AI workflows.

A web, desktop, and browser-extension tool for optimizing, testing, evaluating, and saving prompts, with self-hosting options.

A CLI and library for versioned prompt and model-output evaluations, plus red-team testing for LLM applications, agents, and RAG workflows.

LangGPT is a method for writing reusable prompts with separate role, goal, rules and workflow sections. Copy its Markdown template into a chat interface and adapt it for writing, learning or information tasks without installing software.

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.

A compact prompt engineering guide covering model limitations, prompt risks, and practical strategies.

A hand-curated index of prompt and context engineering resources, covering papers, tools, models, benchmarks, courses, and security material.

Awesome Seedance collects source-traced Seedance 2.5/2.0 video prompts, 25 copy-ready templates, cross-model retest records, and 59 installable Skills to help creators turn a shot intent into a structured video prompt.

A Microsoft 365 and Power Platform community collection of copyable prompts, Copilot Studio agent instructions, and GitHub Copilot skills.

Uses six to nine main questions to map health, work, play, love, values, and energy, separates gravity problems, and creates three five-year paths with prototypes.

Uses up to ten main questions about early interests, unconscious competence, energy patterns, and envy, then builds a personal talent manual from the user's evidence.

Finds three assumptions behind a decision, selects the one most likely to change the conclusion, and designs a small experiment with metrics and stop or continue criteria.

Builds the strongest case for both directions, compares conditions, benefits, risks, and hard objections, and asks one question most likely to change the conclusion.

Removes domain jargon to identify the problem structure, searches history and at least three distant fields for analogous mechanisms, and ends with a reversible experiment.

Reduces a problem to unavoidable facts, unverified assumptions, the real goal, and practical constraints, then derives a feasible path without relying on convention.

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

Separates a claim into verifiable facts, inferred conclusions, and value judgments, checks sources and context, and then audits the reasoning chain.

Studies how a subject developed over time, compares it with relevant peers using consistent dimensions, and connects historical capabilities and constraints to future paths.

Reverse-engineers a strong product, page, process, or finished work into its audience, structure, key decisions, definition of done, reusable principles, and a practice exercise.

Explains one concept in a beginner-friendly form and a precise professional form, then maps the terms, flags misconceptions, and asks comprehension questions.

A multi-turn prompt that delays advice, asks one decision-changing question at a time, separates facts from interpretations and goals, and ends with a more precise question.