Sagar Verma

Opening of the Bolt.new system prompt. Documents WebContainer's browser bound Node.js runtime, the lack of native binaries, pip, and git, and the bolt file modifications diff forma

Anthropic's metaprompt, from the official cookbook, is a battle tested 'prompt that writes prompts'. Feed it a task and an optional list of input variables; it returns a fully stru

Worked HotpotQA example from Yao et al. 2022 showing the ReAct pattern: interleave reasoning traces with tool actions to ground answers in retrieved evidence. Source: https://githu

Two prompt chain for grounded QA. Prompt 1 pulls verbatim quotes; prompt 2 turns those quotes into the final answer. Forcing extraction first cuts hallucination dramatically. Promp

Writes a movie review covering plot, themes, acting, direction, and cinematography, with a personal emotional read. Source: https://github.com/f/awesome chatgpt prompts

The default ChatPromptTemplate that powers LangChain's OpenAI tools agent. Plug your own domain instructions in front of it. Source: https://smith.langchain.com/hub/hwchase17/opena

Chapter 7 Using Examples / Few Shot . Demonstrates how two worked examples of a paragraph structured individuals list train Claude to produce the same shape on a new paragraph, no

Rewrites input so it would pass naive plagiarism detection, with no extra commentary. Source: https://github.com/f/awesome chatgpt prompts

Anthropic Chapter 6 Precognition / Thinking Step by Step . The canonical 'let Claude argue both sides before deciding' template. Pairs a savvy reader system prompt with explicit XM

The most famous prompt from the awesome chatgpt prompts repo 1,800+ contributors . Turns the model into a deterministic Linux terminal emulator that only outputs what the shell wou

From the Anthropic cookbook's building moderation filter.ipynb . A production style moderation prompt that uses explicit ALLOW/BLOCK guidelines, a <thinking scratchpad, and an <out

The original Kojima et al. zero shot CoT pattern. Append the trigger to any reasoning question and the model lays out its work instead of jumping to an answer. Source: https://www.

From the same Anthropic prompt engineering guide. The canonical XML tagging recipe for any prompt that mixes instructions, context, examples, and variable inputs used throughout th

Builds characters, settings, dialogue, and twisty plotlines for film and TV scripts. Source: https://github.com/f/awesome chatgpt prompts

The few shot variant of Anthropic's moderation cookbook. Demonstrates that, for short labels, well chosen positive and negative examples often beat chain of thought. Source: https:

From the Anthropic prompt engineering guide. Counter acts the 'AI slop' look in generated UI by forcing Claude to present multiple distinct design directions before writing code. P

Breaks down math concepts into simple steps with examples and visuals. Source: https://github.com/f/awesome chatgpt prompts

Synthetic eval data generator from the OpenAI Evals cookbook. Used to bootstrap a test set from nothing more than a table schema. Source: https://cookbook.openai.com/examples/evalu

Opening section of the v0 production system prompt. Notable for its strict rules about how AskUserQuestions interacts with parallel tool calls, image asset handling, and a project

Appendix 10.1 Chaining Prompts . Two turns: 1 ask for ten words ending in 'ab'; 2 follow up with a request to replace any non real words. Demonstrates the multi turn 'have Claude d

The three pillars OpenAI recommends prepending to any GPT 4.1 coding agent. They turn a one shot model into a loop that keeps working until the task is actually finished. Source: h

Researches both sides of a topic, presents arguments for each, refutes opposing points, and draws conclusions backed by evidence. Source: https://github.com/f/awesome chatgpt promp

From the Anthropic prompt engineering guide section on agentic systems. A concrete system prompt snippet that tells Claude Opus 4.7 when to spawn subagents counter balancing its de

From patterns/agents/evaluator optimizer.ipynb . Two cooperating prompts: a generator that produces a solution with <thoughts and <response blocks and an evaluator that returns PAS

Detects any input language, translates to English, and rewrites at a higher register. Great for non native writers polishing emails or essays. Source: https://github.com/f/awesome

Designs concrete strategies, affirmations, and actions to help someone reach a stated goal. Source: https://github.com/f/awesome chatgpt prompts

Builds stand up routines on current events, blending wit and personal anecdotes. Source: https://github.com/f/awesome chatgpt prompts

Generates engaging stories with theme and audience awareness. Useful for parents, teachers, or content creators. Source: https://github.com/f/awesome chatgpt prompts

Sibling to the Linux Terminal prompt. Useful for teaching JS or quick mental evaluation without opening a browser console. Source: https://github.com/f/awesome chatgpt prompts

Chapter 9 of Anthropic's interactive prompt engineering tutorial includes this complex legal services prompt that demonstrates retrieval over research with citation formatting, pre

Canonical example from Wei et al. 2022 showing how interleaving worked reasoning into few shot exemplars dramatically improves arithmetic and commonsense tasks. Source: https://git

Opening identity and tool calling section from the leaked Windsurf Cascade prompt. Notable for the AI Flow framing, the strict tool calling discipline, and the unusual instruction

Opening section of Cursor's leaked production system prompt Agent Prompt 2.0 . Establishes the model's tool palette and gives detailed when to use and when not to use guidance for

Anime mode prompt using the niji 6 model. Calling out the studio Ghibli and the medium hand painted texture, soft pastels is what keeps it on style. Source: https://witechpedia.com

From the cookbook's using citations.ipynb . Pairs the Claude Citations API with a short, focused system prompt to ground answers in help center documents. Cited spans are returned

Production system prompt from the OpenAI structured outputs cookbook recipe. It instructs the model to emit each solution step as an equation alongside an explanation field, ready

RAG system prompt from the embeddings QA recipe. The closing sentence is what stops hallucinations on questions outside the retrieved articles. Paired role message: You answer ques

OpenAI's recommended pattern for summarizing an article into a fixed schema. Each field is described inline so the model knows exactly what the JSON shape means. Source: https://co

The exact PromptTemplate string shipped with LangChain's ReAct agent. Drop your tools into {tools} and {tool names} and the model follows the loop until it emits a Final Answer . S

Opening section of Devin's leaked system prompt. Establishes Devin's identity as an autonomous SWE, defines when to communicate with the user, and lays out the planning vs standard

Also from the cookbook summarization guide. The 'reduce' step that combines per chunk summaries generated cheaply with Haiku into one coherent, sectioned final summary using Sonnet

Reasoning model system prompt for catching inconsistencies in tabular data. Returns a tight JSON contract that downstream code can branch on. Source: https://cookbook.openai.com/ex

Microsoft's documented chatbot template. The two line instruction block is what keeps the assistant from answering off topic questions, and the IRS fallback URL prevents hallucinat

Dave Hulbert's plain English distillation of Tree of Thoughts. Works on any chat model no search algorithm required and dramatically improves multi step reasoning. Source: https://

Three short agent prompts from the Swarm style orchestration cookbook. Each agent's "routine" is what the LLM treats as its operating procedure when control is handed off. Source:

Opening sections of Perplexity's leaked system prompt. Strict on inline numeric citations, markdown structure, no moralization, and no "based on search results" hedging. Source: ht

From the basic workflows.ipynb notebook in patterns/agents . Demonstrates the 'route' workflow: classify a ticket, then dispatch to a specialized sub prompt. Reproduced verbatim ar

Verbatim system prompt from the Anthropic Research multi agent pattern. The 'research lead' classifies a user query as depth first, breadth first, or straightforward, then plans an

Entity extraction system prompt that drives a tool calling search over a product database. Notice how the prompt enumerates valid categories so the model snaps its parameter values

The community standard SDXL negative prompt. Weighted parentheses e.g. :1.4 push the model harder against the lowest quality artifacts while leaving room for style. Source: https:/

Chapter 4 Separating Data and Instructions . Compares the un tagged form 'Yo Claude. {EMAIL} < Make this email more polite' with the safer tagged form below. The XML wrap is what s

From how to make sql queries.ipynb in the cookbook. A minimal, schema aware text to SQL prompt that constrains the model to output only the SQL. A more reliable extended version, f

Classic Wei et al. few shot CoT exemplars. Each example shows the reasoning trace explicitly, which conditions the model to do the same on the final query. Source: https://www.prom

A high detail SDXL prompt that fuses art history references Max Ernst, Yinka Shonibare, shin hanga with photographic specs. Pair with the negative prompt to keep the render clean.

Wang et al. self consistency uses the same CoT shape as Wei et al., then samples multiple reasoning paths and majority votes. Use these exemplars verbatim and sample at temperature

From the cookbook's summarization guide. A focused prompt for sublease/legal agreement summarization that uses a system role, explicit section headers, an XML output format, prefil

From the official Anthropic prompt engineering guide for the Claude 4.7 family. Two single line additions that calibrate verbosity in either direction useful as a system prompt fra

Conducts a turn based mock interview for any role. Includes a templated variable so you can swap the position without rewriting the prompt. Source: https://github.com/f/awesome cha

The most pulled RAG prompt on LangChain Hub. Three sentence answer cap plus an explicit "say you don't know" clause makes it a safe default for production RAG. Source: https://smit

Microsoft's recommended structure for break the task down prompts. Uppercase section headers, delimiters and an explicit SEARCH "query" affordance make the output trivially parseab

Canonical ReAct exemplar from Yao et al. The thought/action/observation rhythm is what makes ReAct prompts work copy this shape when wiring an LLM to a search tool. Source: https:/

Chapter 8 Avoiding Hallucinations . A grounded QA template: extract the most relevant quote into <scratchpad , judge whether it answers the question, and only then write a brief nu

From Chapter 9 of Anthropic's interactive prompt engineering tutorial. A canonical complex prompt skeleton that combines task context, tone, rules, examples, conversational history

From misc/generate test cases.ipynb in the cookbook. A meta prompt that takes a prompt template with {{variables}} and generates synthetic test cases in a structured XML format the

Explores philosophical questions, conducts theoretical research, and proposes ethical frameworks. Source: https://github.com/f/awesome chatgpt prompts

Cyberpunk meets film photography prompt. Calling out a real film stock Kodak Portra 400 is what gives Midjourney its grain and color science. Source: https://witechpedia.com/best m

Classic 1 shot example from Brown et al. 2020 GPT 3 paper showing in context learning: define a new word, give one usage example, and the model generalizes. Source: https://github.

Named entity recognition prompt that locks the model to a single, closed label set. Pinning the categories is what makes the output safe to feed into a downstream parser. User turn

Opening sections of Anthropic's officially published system prompt for Claude Sonnet 4.5 release notes, Sept 2025 . Notable for prose first formatting guidance, sparse bullet usage

Photography formula prompt for Midjourney v6 subject + context + camera + lens + lighting + parameters. The style raw flag dials back Midjourney's default stylization for editorial

One line system prompt from the function calling recipe. It is responsible for the model's habit of asking clarifying questions rather than fabricating function arguments. Pair it