100 ChatGPT Prompts & Commands: The Ultimate List for Coding, Marketing, Video & Business
What this article covers
- 100 tested ChatGPT prompts and command codes across 10 categories.
- Slash-style short commands (
/optimize, /template, /matrix, /table), usable as prompt prefixes.
- Per category: concrete commands with example prompts.
- How to customize the codes and combine them with system prompts.
Introduction
The most effective ChatGPT users don’t work with long-form sentences. They use command codes: brief, precise directives that tell the model exactly what to do. /optimize, /table, /matrix, /template - these prefix-style prompts are reproducible, faster to type, and deliver more consistent results than free-form writing.
This list contains 100 such codes across 10 categories, with prompt text you can use directly. They work with ChatGPT (GPT-4o, o3) and can be adapted for other models. See also the Claude version and for local models the Ollama prompt engineering guide.
How the codes work
A command is a prefix + your input. Example:
/optimize
[Your text here]
ChatGPT interprets the command as an instruction and the rest as input. You can combine them: /optimize as table or /matrix with 3 options.
Category 1: Coding & Development (10 commands)
| Command | What it does | Example prompt |
|---|
/optimize | Optimize code (performance, readability) | “/optimize [Code]: focus on runtime” |
/debug | Find and explain errors | ”/debug [Code + error message]“ |
/refactor | Restructure code without changing behavior | ”/refactor [Code] to Clean Code” |
/test | Generate unit tests | ”/test [Function] with pytest” |
/document | Write docstrings/comments | ”/document [Code] in Google style” |
/review | Code review with findings | ”/review [Code]: security + performance” |
/explain | Explain code line by line | ”/explain [Code] for beginners” |
/regex | Build and explain regex | ”/regex for email validation” |
/sql | Generate/optimize SQL query | ”/sql for top 10 customers by revenue” |
/api | Design API endpoint | ”/api REST endpoint for User CRUD in FastAPI” |
Category 2: Marketing & Advertising (10 commands)
| Command | What it does | Example prompt |
|---|
/copy | Write ad copy | ”/copy for [Product], target audience: young parents” |
/campaign | Campaign concept | ”/campaign for launch of [Product], budget 5k” |
/tagline | Generate slogan/tagline | ”/tagline for [Brand], 5 variations” |
/audience | Build target persona | ”/audience for [Product]“ |
/funnel | Think through funnel stages | ”/funnel for [Product], awareness to sale” |
/ab-test | Create A/B variations | ”/ab-test for subject line [Text]“ |
/brand-voice | Define tonality | ”/brand-voice for [Brand]: 5 adjectives + example” |
/ad | Ad copy for platform | ”/ad for Meta Ads, [Product], hook + CTA” |
/newsletter | Newsletter draft | ”/newsletter about [Topic], 3 sections” |
/launch | Sketch launch plan | ”/launch for [Product], 4-week plan” |
Category 3: Video Editing & Content Production (10 commands)
| Command | What it does | Example prompt |
|---|
/script | Write video script | ”/script for YouTube video about [Topic], 10 min” |
/storyboard | Plan shots/scenes | ”/storyboard for 60s product video” |
/hook | First 5 seconds of video | ”/hook for video about [Topic], 3 variations” |
/thumbnail | Thumbnail idea + text | ”/thumbnail for [Video title]“ |
/chapters | Generate chapter markers | ”/chapters from this transcript: [Text]“ |
/broll | B-roll ideas list | ”/broll for [Topic] video” |
/shorts | Short version for Shorts/Reels | ”/shorts from this script: [Text]“ |
/voiceover | Voiceover text with timing | ”/voiceover for 30s clip, calm tone” |
/title-video | Video title variations | ”/title-video for [Topic], CTR-optimized” |
/description | Video description + tags | ”/description for [Video], SEO-optimized” |
Category 4: Writing & Content (10 commands)
| Command | What it does | Example prompt |
|---|
/rewrite | Rewrite text | ”/rewrite [Text], more professional” |
/expand | Expand text | ”/expand [Text], double the length” |
/shorten | Shorten text | ”/shorten [Text] to 100 words” |
/tone | Change tone | ”/tone [Text] → casual instead of formal” |
/proofread | Proofread and style | ”/proofread [Text]“ |
/simplify | Simplify complexity | ”/simplify [Text] for non-experts” |
/headline | Headline variations | ”/headline for [Article topic], 5 options” |
/intro | Write introduction | ”/intro for article about [Topic]“ |
/conclusion | Write conclusion/summary | ”/conclusion for [Article summary]“ |
/translate | Translate with style | ”/translate [Text] into English, natural” |
Category 5: SEO (10 commands)
| Command | What it does | Example prompt |
|---|
/keywords | Keyword ideas + intent | ”/keywords for [Topic], 20 items with intent” |
/meta | Meta title + description | ”/meta for page about [Topic]“ |
/outline | SEO article outline | ”/outline for [Keyword], H2/H3 structure” |
/schema | Schema.org markup | ”/schema for FAQ page about [Topic]“ |
/interne-links | Link suggestions | ”/interne-links for article about [Topic]“ |
/title | Title tag variations | ”/title for [Keyword], CTR-optimized” |
/snippet | Featured snippet text | ”/snippet for question [Question], 40 words” |
/content-gap | Find missing subtopics | ”/content-gap in this article: [Text]“ |
/eeat | E-E-A-T improvements | ”/eeat for article about [Topic]“ |
/lokal-seo | Local SEO copy | ”/lokal-seo for [Company] in [City]“ |
Category 6: Business & Productivity (10 commands)
| Command | What it does | Example prompt |
|---|
/swot | SWOT analysis | ”/swot for [Company/Idea]“ |
/pitch | Elevator pitch | ”/pitch for [Product], 60 seconds” |
/meeting | Agenda + notes | ”/meeting agenda for team retro” |
/email | Professional email | ”/email to [Person], purpose: [X], tone: friendly” |
/report | Structure report | ”/report from this data: [Text]“ |
/agenda | Meeting agenda | ”/agenda for 30-min meeting about [Topic]“ |
/todo | Prioritize tasks | ”/todo from this mess: [List]“ |
/brainstorm | Ideas list | ”/brainstorm 20 ideas for [Problem]“ |
/decision | Decision matrix | ”/decision between [Option A/B/C]“ |
/summary | Summarize | ”/summary of [Text], 3 bullet points” |
Category 7: Data Analysis & Tables (10 commands)
| Command | What it does | Example prompt |
|---|
/analyze | Analyze data/text | ”/analyze these numbers: [Data]“ |
/matrix | Comparison matrix | ”/matrix [Options] by criteria [X,Y,Z]“ |
/table | Output as table | ”/table [Data] with columns [A,B,C]“ |
/chart | Chart idea + code | ”/chart for this data in Python/matplotlib” |
/compare | A vs. B comparison | ”/compare [A] vs [B] by [Criteria]“ |
/forecast | Trend estimate | ”/forecast based on [Data]“ |
/segment | Segment data | ”/segment this list by [Criterion]“ |
/survey | Build survey questions | ”/survey for customer satisfaction, 10 questions” |
/insight | Extract insights | ”/insight from this report: [Text]“ |
/csv | Structure as CSV | ”/csv this data: [Text]“ |
| Command | What it does | Example prompt |
|---|
/post | Generate platform post | ”/post for LinkedIn about [topic]“ |
/thread | X/Twitter thread | ”/thread about [topic], 5 tweets” |
/caption | Instagram caption | ”/caption for photo of [description]“ |
/hashtags | Hashtag set | ”/hashtags for [topic], 15 pieces” |
/bio | Profile bio | ”/bio for [person/brand], 150 characters” |
/reply | Reply to comment | ”/reply to this comment: [text]“ |
/viral | Viral framework post | ”/viral post about [topic], Problem-Agitate-Solve” |
/poll | Poll post | ”/poll for [community] about [topic]“ |
/carousel | LinkedIn carousel content | ”/carousel about [topic], 8 slides” |
/content-plan | Weekly content plan | ”/content-plan for [channel], 1 week” |
Category 9: Learning & Education (10 Commands)
| Command | What it does | Example prompt |
|---|
/explain-einfach | Explain like you’re 5 | ”/explain-einfach [concept]“ |
/quiz | Generate quiz questions | ”/quiz on [topic], 10 questions with answers” |
/flashcards | Flashcards | ”/flashcards for [topic], front/back” |
/lesson | Mini-lesson | ”/lesson about [topic] for beginners” |
/tutor | Socratic tutor | ”/tutor teach me [topic] through questions” |
/analogy | Find analogy | ”/analogy for [complex concept]“ |
/example | Practical examples | ”/example for [concept], 3 examples” |
/study-plan | Study plan | ”/study-plan for [topic] in 4 weeks” |
/eli5 | Explain like I’m 5 | ”/eli5 [topic]“ |
/fehler | Common mistakes on topic | ”/fehler when learning [topic]“ |
| Command | What it does | Example prompt |
|---|
/template | Build prompt template | ”/template for recurring task [X]“ |
/framework | Set thinking framework | ”/framework analyze with Porter’s Five Forces” |
/persona | Adopt role | ”/persona handle as experienced [role]“ |
/roleplay | Simulate scenario | ”/roleplay customer conversation, I’m the seller” |
/chain | Step by step | ”/chain think step by step about [problem]“ |
/iteriere | Improve in rounds | ”/iteriere this text 3x better” |
/critique | Critique output | ”/critique your own answer” |
/improve-prompt | Improve prompt | ”/improve-prompt my prompt: [text]“ |
/system | Set system behavior | ”/system always respond as [role]“ |
/format | Set output format | ”/format answer as markdown table” |
How to combine the codes
/persona handle as senior marketing consultant.
/template create a reusable template.
/matrix compare the 3 variants in a table.
/table show the result as a table with columns [variant, pro, con, recommendation].
Commands stack, each one adds a rule. Pro tip: save frequent combinations as Custom Instructions or GPTs so they’re always active.
For local models
The codes work with Ollama and local models too. Instead of repeating them per message, put them in the system prompt. See System Prompts and Prompt Engineering.
Further reading
Key takeaways:
- Slash codes (/optimize, /template, /matrix) are reusable prompt shortcuts.
- 100 commands in 10 categories: coding, marketing, video, copy, SEO, business, data, social, learning, meta.
- Codes are combinable; each adds a rule.
- For local models: put the same codes in the system prompt.
- Save frequent combinations as Custom Instructions.
FAQ
Are these official ChatGPT commands?
No, they’re conventions that ChatGPT reliably understands. You can define your own codes; the model interprets /optimize or /table as a work instruction. The slash is just a readable prefix.
Do they work in every model?
Yes: GPT-4o, o3, Claude, Gemini, and local models (Ollama) understand the directives. Quality varies by model; with smaller local models, prefer simpler codes.
Can I combine codes?
Yes: codes stack rules. /persona sets the role, /table the format, /optimize the quality. Order doesn’t matter; all apply at once.
Define my own codes?
Yes, tell the model once “From now on, /x means: [instruction]” and keep using the code. Or save frequent combinations in Custom Instructions or GPTs permanently.
What about local AI (Ollama)?
Same codes, but put the rules in the system prompt so they apply persistently. See the Ollama System Prompts article.
Sources and further reading