从这里开始
提示词检查清单(复制即用):让输出更好
一份实用的检查清单,可以粘贴到任何提示词里,用来减少歧义、改善结构。
打开指南 →
如何强制输出有效的JSON(不带markdown)
把数据提取并转换成严格JSON的提示词模板:写明字段、类型、null规则和校验步骤,让输出可以直接解析。
打开指南 →
Code prompts that actually work (debug, refactor, tests)英文
How to stop getting generic answers: force diffs, constraints, and test checklists.
打开指南 →
Marketing prompts without hype (safe claims)英文
Templates for landing copy and ads that avoid exaggeration and keep claims realistic.
打开指南 →
Chain-of-thought prompting: make the model show its reasoning英文
How to elicit step-by-step reasoning to improve accuracy on complex tasks.
打开指南 →
Summarization prompts that preserve meaning (not just reduce length)英文
Templates to summarize long texts while keeping the right level of detail, key facts, and tone.
打开指南 →
Role prompting: how to assign personas for better AI outputs英文
Use expert roles to unlock specialized behavior in any AI model — and avoid the common mistake of vague titles that change nothing.
打开指南 →
ChatGPT职场提示词:邮件、报告与会议模板
可复用的ChatGPT职场常见任务提示词模板——专门避开那些让输出空泛、注水的模糊指令。
打开指南 →
Claude提示词指南:XML标签、长上下文与结构化推理
如何编写提示词,发挥Claude对XML标签的支持、大上下文窗口,以及审慎、注重引用出处的推理能力。
打开指南 →
Prompts for Gemini: format control, grounding, and structured output英文
How to write prompts that get consistent, well-structured output from Gemini — including format examples, grounding constraints, and multimodal tips.
打开指南 →
Prompts for Grok: directness, real-time context, and structured responses英文
How to write prompts that get direct, high-signal responses from Grok — including tone controls, real-time awareness, and structuring tips.
打开指南 →
AI prompt templates for business: planning, reports, and customer support英文
Ready-to-use AI prompt templates for common business workflows — from project planning and status reports to customer support scripts and decision memos.
打开指南 →
DeepSeek提示词指南:代码、数据提取与分析推理
如何编写提示词,让DeepSeek给出精确、结构清晰的输出——涵盖代码任务、严格的JSON提取和多步骤分析推理。
打开指南 →
Few-shot prompting: how to show examples instead of just explaining英文
Few-shot prompting uses examples inside the prompt to show the model exactly what you want — more reliable than verbal instructions alone for formatting, tone, and structure.
打开指南 →
How to score and improve your prompt quality before sending it英文
A self-evaluation framework to score prompt quality before running it — covering goal clarity, context completeness, format constraints, and common failure modes.
打开指南 →
System prompts: how to set persistent instructions for ChatGPT, Claude, and Gemini英文
How to write system prompts (custom instructions) that shape every response without repeating yourself — covering persona, constraints, output format, and escalation rules.
打开指南 →
保留原意、语气和语域的AI翻译提示词
用AI翻译内容的模板——包含语气匹配、语域控制、领域术语表,以及防止常见翻译错误的约束条件。
打开指南 →
Image generation prompts: structure, style, and composition for better AI images英文
How to write image prompts that get consistent, intentional results — covering subject, style, composition, lighting, and negative constraints for DALL-E, Gemini Imagen, and similar models.
打开指南 →
Prompt chaining: how to break complex tasks into sequential AI steps英文
Prompt chaining feeds the output of one prompt as input to the next, handling tasks too complex for a single round-trip. Learn the core patterns and where they fail.
打开指南 →
AI writing prompts for blogs, emails, and creative content英文
Writing prompts that produce structured, on-brand content — with tone, audience, format, and length controls built in. No generic filler.
打开指南 →
How to write prompts for AI with image and file inputs (multimodal)英文
Multimodal prompts combine text instructions with images, PDFs, or screenshots. Learn how to direct AI attention to what matters and extract structured output reliably.
打开指南 →
Zero-shot prompting: how to get reliable results without providing examples英文
Zero-shot prompting asks the model to solve a task from instructions alone — no examples included. Learn when it works, when to add examples, and the constraints that make zero-shot reliable.
打开指南 →
Prompts for GPT: how to get structured, reliable output from ChatGPT英文
How to write prompts that get consistent, well-structured output from GPT models — using format templates, output constraints, and instruction placement to reduce variation.
打开指南 →
AI brainstorming prompts: generate and filter ideas without generic filler英文
How to use AI for brainstorming without getting obvious, repetitive ideas — covering divergent generation, constraint-based prompting, and structured filtering.
打开指南 →
Kimi提示词指南:长上下文、文档分析与深度研究
如何编写提示词,充分发挥Kimi的大上下文窗口和出色的文档理解能力。
打开指南 →
AI prompts for data analysis: SQL, trends, and interpretation英文
Prompt templates for data analysis tasks — generating SQL queries, interpreting results, spotting trends, and cleaning messy datasets.
打开指南 →
用AI学习的提示词:辅导、概念检验与学习指南
把AI变成耐心导师的提示词模板——用于讲解概念、检验理解、制定学习计划,并把新知识和你已经掌握的内容联系起来。
打开指南 →
Prompts for Perplexity: grounded answers from the web英文
How to write Perplexity prompts for the Agent API presets (fast, low, medium, high): specific questions that seed better searches, capped lists, honest 'not found' answers, and filters as parameters instead of prose.
打开指南 →
如何调试输出不理想的提示词
一套系统的方法:找出提示词失效的原因,不靠反复试错就把它修好。
打开指南 →
AI prompts for product managers: PRDs, user research, and prioritization英文
Copy-paste prompt templates for the recurring PM workflows that AI handles well: writing specs, synthesizing research, and structuring prioritization decisions.
打开指南 →
Prompt templates for summarization: documents, meetings, and research英文
Copy-paste templates to summarize long documents, meeting notes, and research reliably — with format and length controls built in.
打开指南 →
How to write better prompts for Claude英文
Practical patterns for getting consistent, high-quality output from Claude — what it excels at, how to structure requests, and where it needs explicit guidance.
打开指南 →
AI prompts for sales teams: outreach, discovery, and proposals英文
Copy-paste prompt templates for the recurring sales workflows where AI genuinely saves time — cold outreach, discovery prep, and proposal writing.
打开指南 →
AI prompts for customer support: ticket responses, FAQs, and escalation scripts英文
Copy-paste prompt templates for the recurring customer support tasks where AI saves the most time — drafting ticket replies, writing help articles, and preparing escalation summaries.
打开指南 →
Structured output prompting: how to get reliable JSON, tables, and lists from any AI英文
Techniques and templates for prompting AI to return structured, machine-readable output consistently — without hallucinated fields, format drift, or plain-text contamination.
打开指南 →
AI prompts for HR and recruiting: job descriptions, interview questions, and evaluations英文
Practical AI prompt templates for HR teams and recruiters — writing job descriptions that attract the right candidates, preparing structured interview question sets, and summarizing candidate evaluations.
打开指南 →
AI prompts for legal teams: contract drafting, document review, and research英文
Practical AI prompt templates for lawyers, paralegals, and legal ops teams — drafting contract clauses, reviewing agreements for risk, summarizing case law, and extracting structured information from legal documents.
打开指南 →
AI prompts for finance teams: report analysis, earnings summaries, and financial modeling英文
Practical AI prompt templates for finance professionals — analyzing financial statements, summarizing earnings calls, explaining variances, drafting board-ready commentary, and accelerating financial modeling.
打开指南 →
Context engineering: how to structure what you give an AI for better outputs英文
Context engineering means deciding what goes into an AI's input, in what order and at what level of detail. Why context quality often matters more than prompt phrasing, with practical patterns for reliable outputs.
打开指南 →
AI prompts for software developers英文
Practical AI prompts for software engineers: code review, PR descriptions, debugging, documentation, and architecture decisions.
打开指南 →
Negative prompting: how to tell AI what not to do英文
A practical guide to using negative constraints in AI prompts — what to exclude, what to avoid, and how to set boundaries that actually stick.
打开指南 →
AI prompts for content creators英文
AI prompts for YouTubers, bloggers, and social media creators: ideation, scripting, repurposing, and publishing workflows that save real production time.
打开指南 →
How to prompt reasoning models (GPT-6, Claude Opus 5.5, Gemini, Grok, DeepSeek)英文
Practical patterns for prompting models that think before answering: what to specify, what to leave to the model, and how each current model sets reasoning depth with effort or thinking level instead of prompt wording.
打开指南 →
AI prompts for teachers and educators英文
Where AI genuinely saves teacher preparation time — lesson plans, rubrics, student feedback, and differentiated content — and what always needs human review.
打开指南 →
How to rewrite a prompt for better results英文
A practical rewriting process: how to identify what is missing, restructure for clarity, and iterate without starting from scratch.
打开指南 →
AI prompts for research: literature review, synthesis, and gap analysis英文
How to use AI as a research assistant for evidence synthesis, literature gap analysis, and reading summaries — without hallucinated citations.
打开指南 →
Conversational prompting: maintaining context in multi-turn AI chats英文
How to keep AI responses consistent across a long conversation: when to reset context, how to correct the model mid-chat, and how to hand off state to a new session.
打开指南 →
AI prompts for UX and product design: copy, specs, and critique英文
Where AI fits in a design workflow: writing microcopy, reviewing design specifications, generating user story maps, and writing component requirements.
打开指南 →
AI prompts for email: drafts, replies, and thread summaries英文
Copy-paste AI prompts for work email in ChatGPT, Claude, or Gemini: draft from bullet points, reply to a long thread, summarize decisions and owners, and adjust tone without losing facts.
打开指南 →
How to build a prompt library for your team英文
A practical system for shared AI prompt templates at work: what to include in each entry, how to name and version prompts, how to review quality before sharing, and when to retire a template.
打开指南 →
AI prompts for meetings: agendas, notes, action items and follow-ups英文
Prompt templates for the full meeting cycle: turn a goal into an agenda, turn a transcript or rough notes into decisions and action items with owners, and draft the follow-up without inventing commitments.
打开指南 →
AI prompts for Excel and Google Sheets formulas英文
How to prompt ChatGPT, Claude or Gemini for spreadsheet formulas that work the first time: describe the layout, give sample rows and the expected result, name your app, and ask for edge cases. Includes templates for writing, explaining and fixing formulas.
打开指南 →
How long should a prompt be? Prompt length for ChatGPT, Claude and Gemini英文
There is no ideal word count. A prompt should be as long as the information the model needs to do the task the way you want, and no longer. How to tell when a prompt is too short or too long, what to cut, what to keep, and how to structure long prompts.
打开指南 →
AI prompts for presentations: slide outlines, speaker notes and decks from documents英文
How to use ChatGPT, Claude or Gemini to plan a presentation: start from the audience and the one decision or idea you need, get a slide-by-slide outline, turn a long document into slides without inventing data, and write speaker notes. Includes copy-paste templates.
打开指南 →
How to test one prompt across ChatGPT, Claude, Gemini, Grok and DeepSeek英文
A practical method to compare AI models on your own task: fix the prompt and the inputs, write pass/fail criteria before reading answers, run a small sample and decide on evidence. Includes test-case and rubric templates.
打开指南 →
AI prompts for status reports: weekly updates, project reports and executive summaries英文
How to use ChatGPT, Claude or Gemini to turn notes, tickets and meeting minutes into clear status reports: what to paste, how to separate progress from risks, how to avoid invented progress, and how to adapt one update for your team and for leadership. Copy-paste templates included.
打开指南 →
AI prompts for competitor analysis: profiles, comparison tables and positioning英文
How to use ChatGPT, Claude, Gemini or Perplexity for competitor analysis without invented facts: what sources to give the model, how to keep every claim traceable, how to build a fair comparison table, and how to turn findings into positioning. Copy-paste templates included.
打开指南 →
AI prompts for SOPs: turn how-you-work into clear, testable procedures英文
How to use ChatGPT, Claude or Gemini to write SOPs from walkthroughs, notes or transcripts: what the model needs, concrete steps, finding gaps before someone follows it, and turning it into a checklist. Templates included.
打开指南 →
AI prompts for customer feedback analysis: themes, evidence and priorities you can trust英文
How to use ChatGPT, Claude or Gemini to analyze reviews, survey answers and support tickets: define themes before counting, quote the evidence, separate frequency from severity, and avoid invented percentages. Templates included.
打开指南 →
AI prompts for proposals and RFP responses: answer the brief, not a generic pitch英文
How to use ChatGPT, Claude or Gemini to answer an RFP or write a client proposal: extract every requirement first, draft only from your own approved material, mark gaps instead of inventing claims, and check compliance before sending. Templates included.
打开指南 →
通义千问(Qwen)提示词指南:Alibaba的六段式框架、分隔符与JSON模式
依据阿里云百炼(Model Studio)官方的提示词指南和API文档,介绍如何为Qwen3.8 Max、Qwen3.7 Plus和Qwen3.8 Flash编写提示词。
打开指南 →
智谱GLM提示词指南:约束尽早给出,角色要有用,JSON要明确
依据智谱的通用提示词工程指南和GLM-5.3文档,介绍如何为Z.ai(智谱AI)的GLM-5.3和GLM-5.3 Flash编写提示词。
打开指南 →
MiniMax提示词指南:MiniMax-M3的编程与智能体提示词
根据MiniMax的API文档,介绍如何为MiniMax-M3和MiniMax-M3.1 Flash编写提示词:验收标准、固定采样、没有JSON模式时如何拿到JSON,以及工具调用循环。
打开指南 →
豆包(Doubao)提示词指南:为Doubao Seed 2.1讲清目标和场景
依据火山引擎(Volcengine)针对推理模型的建议,介绍如何在火山方舟(Volcengine Ark)上为ByteDance的Doubao Seed 2.1 Pro、Lite和Turbo编写提示词。
打开指南 →