Chapter 9 of Anthropic's interactive prompt engineering tutorial includes this complex legal services prompt that demonstrates retrieval over research with citation formatting, pre
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 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
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 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.
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
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
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
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
A prompt chaining pipeline that first pulls verbatim relevant quotes from a long document, then uses those quotes to generate a grounded answer to your question. Use it when you ne
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
Guides you on enriching LLM prompts with database schemas, sample data, and table relationships to improve generated SQL quality. Use this when Claude is producing inaccurate or in
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://
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
A Claude skill that creates three structured spec files requirements, design, and tasks before any code is written, giving AI agents a shared source of truth. Use it when starting
