AI Prompt Commands Cheat Sheet: Claude Code, Cursor, Codex, Midjourney
The first fifteen commands or parameters from every platform in the AI prompts reference, on one static page. The prompts reference catalogs the operation layer of AI tools: slash commands, @-mentions, image and video generation parameters, API fields and configuration keys. Each entry is a literal, typeable token taken from the vendor's official documentation, never a prompt-writing tip.
Fifteen rows is enough to show the shape of each tool's command surface (which ones use slash commands, which use CLI flags, which expose parameters only through an API) without turning this page into the full 776-row database. The per-tool links go to the complete tables, each with source links, category notes and hand-written recipes where we have them.
- Claude Code (111)
- Cursor (37)
- GitHub Copilot (31)
- OpenAI Codex CLI (58)
- Aider (43)
- Midjourney (38)
- Stable Diffusion (A1111) (36)
- Suno AI (6)
- LM Studio (24)
- DeepSeek (22)
- GLM (Z.ai) (23)
- Kimi (Moonshot AI) (22)
- Kling AI (24)
- Vidu (24)
- MiniMax (Hailuo) (24)
- PixVerse (26)
- Manus (27)
- Qwen (Alibaba Model Studio) (29)
- Tencent Hunyuan (22)
- OpenClaw (66)
- Nous Hermes (42)
- MCP (Model Context Protocol) (30)
- Agent Instruction Files (11)
Claude Code — first 15 of 111, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| /add-dir <path> | Add a working directory for file access during the current session | Type a partial path to see matching directory suggestions; press Tab to accept one. Most .claude/ configuration is not discovered from the added directory. |
| /advisor model|off | Enable or disable the advisor tool, which consults a second model for guidance at key moments during a task | Accepts fable, opus, sonnet, or a full model ID. fable requires Fable 5 access. |
| /agents | As of v2.1.198, running /agents prints a reminder to ask Claude to create or manage subagents, or to edit .claude/agents/ or... | On v2.1.197 and earlier, opens an interactive interface for creating and managing subagent configurations |
| /autocompact auto|<tokens> | Set the auto-compact window: how full the context window gets before Claude Code compacts automatically | Pass a size such as 500k, or auto to return to the window tuned for your model. Claude Code saves the value to user settings and applies it to the current session. |
| /autofix-pr prompt | Spawn a Claude Code on the web session that watches the current branch's PR and pushes fixes when CI fails or reviewers leave comments | Detects the open PR from your checked-out branch with gh pr view; to watch a different PR, check out its branch first. By default the cloud session is told to fix every CI failure and review... |
| /background prompt | Detach the current session to run as a background agent and free this terminal | Pass a prompt to send one more instruction before detaching. Monitor the session with claude agents. |
| /batch <instruction> | Skill. Orchestrate large-scale changes across a codebase in parallel | Researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan. Once approved, spawns one background subagent per unit in an isolated git worktree. |
| /branch name | Create a branch of the current conversation at this point, so you can try a different direction without losing the conversation as it stands | Switches you into the branch and preserves the original, which you can return to with /resume. To run a copy as a separate background session instead of switching into it, use /fork; to hand a... |
| /btw question | Ask a side question about the current session without adding to the conversation | If you run /btw without a question, Claude Code shows your most recent side question so you can browse earlier answers; if you haven't asked one yet, Claude Code prints a usage line. Before... |
| /bug report | Report a bug or share your conversation | You choose how much session history to include and confirm on a consent screen before anything is sent. When you're signed in to Anthropic on a first-party connection, the report goes to... |
| /cd <path> | Move this session to a new working directory, keeping the conversation and its prompt cache | Type a partial path to see matching directory suggestions; press Tab to accept one. Claude Code prompts you to trust the workspace if you haven't worked in it before, and --resume finds the moved... |
| /chrome | Configure Claude in Chrome settings | Type the command in the Claude Code prompt. |
| /claude-api migrate|managed-agents-onboard|prompt-audit | Skill. Load Claude API and Managed Agents reference material for your project's language | Also activates automatically when your code imports anthropic or @anthropic-ai/sdk. Run migrate to upgrade existing Claude API code to a newer model, managed-agents-onboard for a walkthrough that... |
| /clear name | Start a new conversation with empty context | Pass a name to label the previous conversation in the /resume picker. To free up context while continuing the same conversation, use /compact instead. |
| /code-review low|medium|high|xhigh|max|ultra --fix --comment pr#|branch|path | Skill. Review the current diff, or a PR number, branch, or path you pass, for correctness bugs and cleanup opportunities | Pass --fix to apply findings, --comment to post them as inline GitHub PR comments, or ultra to run a deep cloud review. With ultra on a github.com PR target, --post preselects posting the finished... |
Cursor — first 15 of 37, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| /model [filter] | Select a model. Press Tab to edit | Type it at the start of the cursor-agent CLI prompt. |
| /run-everything [on|off|status] | Toggle Run Everything or show its status | Also: /auto-run. Type it at the start of the cursor-agent CLI prompt. |
| /plan [prompt] | Switch to Plan mode, show the current plan, or submit a prompt in Plan mode | Type it at the start of the cursor-agent CLI prompt. |
| /ask | Toggle Ask mode for read-only questions | Type it at the start of the cursor-agent CLI prompt. |
| /debug [prompt] | Toggle Debug mode or submit a prompt in Debug mode | Type it at the start of the cursor-agent CLI prompt. |
| /goal [objective] | Give the agent a long-lived objective to work towards until it's fully complete. Rolling out | Type it at the start of the cursor-agent CLI prompt. |
| /logs | Show the debug log path and copy it to the clipboard | Type it at the start of the cursor-agent CLI prompt. |
| /update | Update Cursor Agent to the latest version | Type it at the start of the cursor-agent CLI prompt. |
| /max-mode | Toggle Max Mode on legacy request-based plans | Type it at the start of the cursor-agent CLI prompt. |
| /rename <name> | Rename the current chat session | Type it at the start of the cursor-agent CLI prompt. |
| /clear | Start a new chat session | Also: /new, /new-chat, /newchat. Type it at the start of the cursor-agent CLI prompt. |
| /resume | Open recent chats and resume one | Type it at the start of the cursor-agent CLI prompt. |
| /fork | Fork the current chat into a new session | Type it at the start of the cursor-agent CLI prompt. |
| /summarize | Summarize the conversation to reduce context | Also: /compress. Type it at the start of the cursor-agent CLI prompt. |
| /rewind | Jump back to a previous message | Type it at the start of the cursor-agent CLI prompt. |
GitHub Copilot — first 15 of 31, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| /clear | Start a new chat session | Clears the current Copilot Chat conversation in VS Code. |
| /explain | Explain how the code in your active editor works | Select code first for a focused explanation. |
| /fix | Propose a fix for problems in the selected code | Highlight the broken code, then run the command. |
| /fixTestFailure | Find and fix a failing test | Copilot locates the failing test and proposes a repair. |
| /help | Quick reference and basics of using GitHub Copilot | Lists available commands and usage basics. |
| /new | Create a new project | Scaffolds a new workspace from your description. |
| /tests | Generate unit tests for the selected code | Select a function or class before running. |
| #block | Include the current block of code in the prompt | Type # in the chat box, then the variable name. |
| #class | Include the current class in the prompt | Scopes the context to the enclosing class. |
| #comment | Include the current comment in the prompt | Useful when iterating on a doc comment. |
| #file | Include the current file's content in the prompt | Attaches the whole active file as context. |
| #function | Include the current function or method in the prompt | Scopes the context to the enclosing function. |
| #line | Include the current line of code in the prompt | Narrowest context scope available. |
| #path | Include the file path in the prompt | Passes the location, not the contents. |
| #project | Include the project context in the prompt | Broadest scope; slower but most informed. |
OpenAI Codex CLI — first 15 of 58, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| /permissions | Relax or tighten approval requirements mid-session, such as switching between Auto and Read | Relax or tighten approval requirements mid-session, such as switching between Auto and Read. |
| /ide | Pull editor context into the next prompt without re-explaining what's open in your IDE | Pull editor context into the next prompt without re-explaining what's open in your IDE. |
| /keymap | Inspect and persist custom shortcut bindings in config.toml | Inspect and persist custom shortcut bindings in config.toml. |
| /vim | Switch between Vim normal/insert behavior and the default composer editing mode | Switch between Vim normal/insert behavior and the default composer editing mode. |
| /setup-default-sandbox | Replace the degraded Windows sandbox after Codex offers the elevated setup | Replace the degraded Windows sandbox after Codex offers the elevated setup. |
| /sandbox-add-read-dir | Unblock commands that need to read an absolute directory path outside the current readable | Unblock commands that need to read an absolute directory path outside the current readable. |
| /agent, /subagents | Inspect or continue work in a spawned subagent thread | Inspect or continue work in a spawned subagent thread. |
| /apps | Attach an app as $app-slug before asking Codex to use it | Attach an app as $app-slug before asking Codex to use it. |
| /plugins | Inspect plugin tools, install suggested plugins, or manage plugin availability | Inspect plugin tools, install suggested plugins, or manage plugin availability. |
| /hooks | Inspect configured hooks, trust new or changed hooks, or disable non-managed hooks before they | Inspect configured hooks, trust new or changed hooks, or disable non-managed hooks before they. |
| /clear | Reset the visible UI and chat context together when you want a fresh start | Reset the visible UI and chat context together when you want a fresh start. |
| /rename | Give a saved session a recognizable name without leaving the TUI | Give a saved session a recognizable name without leaving the TUI. |
| /archive | Remove the current session from active session lists without deleting its transcript | Remove the current session from active session lists without deleting its transcript. |
| /delete | Remove the transcript and descendant sessions when archiving isn't enough | Remove the transcript and descendant sessions when archiving isn't enough. |
| /compact | Use after long runs so Codex retains key points without blowing the context window | Use after long runs so Codex retains key points without blowing the context window. |
Aider — first 15 of 43, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| /add | Add files to the chat so aider can edit them or review them in detail | Add files to the chat so aider can edit them or review them in detail |
| /architect | Enter architect/editor mode using 2 different models. If no prompt provided, switches | Enter architect/editor mode using 2 different models. If no prompt provided, switches to architect/editor mode. |
| /ask | Ask questions about the code base without editing any files. If no prompt provided, switches | Ask questions about the code base without editing any files. If no prompt provided, switches to ask mode. |
| /chat-mode | Switch to a new chat mode | Switch to a new chat mode |
| /clear | Clear the chat history | Clear the chat history |
| /code | Ask for changes to your code. If no prompt provided, switches to code mode | Ask for changes to your code. If no prompt provided, switches to code mode. |
| /commit | Commit edits to the repo made outside the chat (commit message optional) | Commit edits to the repo made outside the chat (commit message optional) |
| /context | Enter context mode to see surrounding code context. If no prompt provided, switches to context | Enter context mode to see surrounding code context. If no prompt provided, switches to context mode. |
| /copy | Copy the last assistant message to the clipboard | Copy the last assistant message to the clipboard |
| /copy-context | Copy the current chat context as markdown, suitable to paste into a web UI | Copy the current chat context as markdown, suitable to paste into a web UI |
| /diff | Display the diff of changes since the last message | Display the diff of changes since the last message |
| /drop | Remove files from the chat session to free up context space | Remove files from the chat session to free up context space |
| /edit | Alias for /editor: Open an editor to write a prompt | Alias for /editor: Open an editor to write a prompt |
| /editor | Open an editor to write a prompt | Open an editor to write a prompt |
| /editor-model | Switch the Editor Model to a new LLM | Switch the Editor Model to a new LLM |
Midjourney — first 15 of 38, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| /imagine | Generate image | Generate an image from a text prompt. |
| /describe | Describe image | Describe an uploaded image in text. |
| /blend | Blend images | Blend 2-5 images together. |
| /settings | Settings | Configure model version, quality, etc. |
| /info | Account info | Check subscription and usage. |
| U1~U4 | Upscale | Upscale the selected image. |
| V1~V4 | Create variation | Generate a variation of the selected image. |
| --ar <w:h> | Aspect Ratio: change the image shape from the default square | Also: --aspect. Example: --ar 2:3. Place after the prompt text. |
| --chaos <0-100> | Vary the results more between grid images | Also: --c. Higher values give more unexpected compositions. |
| --oref <url> | Omni Reference: use a person's likeness or an object's form | Replaces Character Reference in V7. |
| --no <object> | Tell Midjourney what you do not want in the image | Example: --no plants removes plants from results. |
| --profile | Personalization: apply your personalized profile or moodboard style | Also: --p. |
| --quality <value> | Control detail level and processing time | Also: --q. |
| --repeat <n> | Generate multiple image sets from a single prompt | Also: --r. Subscription tier limits apply. |
| --seed <number> | Fix the starting noise for testing and experimenting | Same seed and prompt reproduce similar results. |
Stable Diffusion (A1111) — first 15 of 36, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| (word) | Increase attention to word by a factor of 1.1 | Wrap any prompt token in parentheses. |
| ((word)) | Increase attention by 1.21 (1.1 x 1.1) | Stack parentheses to multiply the effect. |
| [word] | Decrease attention to word by a factor of 1.1 | Square brackets reduce emphasis; no numeric weight allowed. |
| (word:1.5) | Set an explicit attention weight on word | Weights work with () only. Default weight is 1.1. |
| (word:0.25) | Decrease attention by an explicit factor | Values below 1 reduce influence (0.25 = quarter strength). |
| \(word\) | Use literal parentheses characters in the prompt | Escape with backslashes: anime_\(character\). |
| BREAK | Fill the current 75-token chunk with padding and start a new chunk | Must be uppercase. Controls how long prompts are split. |
| [from:to:when] | Prompt editing: swap from one text to another mid-sampling | when is a step number or a 0.0-1.0 fraction of steps. |
| [to:when] | Add text to the prompt after a fixed number of steps | Adds the to text once step when is reached. |
| [from::when] | Remove text from the prompt after a fixed number of steps | Drops the from text once step when is reached. |
| [cow|horse] | Alternating words: swap tokens every other sampling step | Step 1 uses cow, step 2 horse, and so on. |
| prompt1 AND prompt2 | Composable diffusion: combine multiple prompts | AND must be uppercase. Supports weights: a cat :1.2 AND a dog. |
| <lora:filename:multiplier> | Apply a LoRA at the given strength | Filename without extension; multiplier usually 0-1. Not allowed in the negative prompt. |
| <hypernet:filename:multiplier> | Apply a Hypernetwork at the given strength | Same syntax family as LoRA extra networks. |
| embedding-filename | Trigger a Textual Inversion embedding by its filename | Place the embedding's filename anywhere in the prompt. |
Suno AI — 6 entries, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| [Verse] | Verse section | Specify a verse section in the song. |
| [Chorus] | Chorus section | Specify a chorus section. |
| [Bridge] | Bridge section | Specify a bridge section. |
| [Outro] | Outro | Specify the outro section. |
| Genre tags | Set genre | Tag genres like pop, rock, jazz, hip-hop. |
| BPM | Set tempo | Specify the song BPM (tempo). |
LM Studio — first 15 of 24, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| Temperature | Creativity (0-1) | Higher = more creative, lower = more deterministic. |
| Context Length | Token window | Max tokens for input + output combined. |
| Top P | Nucleus sampling | Probability mass threshold for token selection. |
| Repeat Penalty | Avoid repetition | Penalise recently used tokens to reduce repetition. |
| GPU Layers | GPU offload | Number of model layers to offload to GPU. |
| /v1/chat/completions | OpenAI-compatible chat endpoint served by LM Studio | POST against the local server started with lms server start. |
| /v1/completions | OpenAI-compatible text completion endpoint | POST; legacy completion style rather than chat messages. |
| /v1/embeddings | OpenAI-compatible embeddings endpoint | POST; returns vectors for the loaded embedding model. |
| /v1/responses | OpenAI-compatible responses endpoint | POST; newer response-style API surface. |
| /v1/models | List models currently available to the local server | GET; mirrors the OpenAI models listing shape. |
| temperature | Inference parameter: sampling randomness | Set per request in the config object, e.g. { "temperature": 0.6 }. |
| maxTokens | Inference parameter: maximum tokens to generate | Set per request alongside temperature in the prediction config. |
| topP | Inference parameter: nucleus sampling cutoff | Set per request in the prediction config. |
| structured | Inference parameter that enforces a schema on the output | Pass a schema so the model must emit conforming JSON. |
| lms server start | Start the local LM Studio server | Serves the OpenAI-compatible endpoints listed above. |
DeepSeek — first 15 of 22, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| model | The model used for the chat completion | This fingerprint represents the backend configuration that the model runs with. |
| messages | A list of messages comprising the conversation so far | JSON body field of POST /chat/completions. |
| temperature | What sampling temperature to use, between 0 and 2 | Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. |
| top_p | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the... | So 0.1 means only the tokens comprising the top 10% probability mass are consid |
| max_tokens | The maximum number of tokens that can be generated in the chat completion | The total length of input tokens and generated tokens is limited by the model's context length. |
| frequency_penalty | This parameter is no longer supported | It will not take effect if you pass it to the API. |
| presence_penalty | This parameter is no longer supported | It will not take effect if you pass it to the API. |
| stop | Up to 16 sequences where the API will stop generating further tokens | JSON body field of POST /chat/completions. |
| stream | If set, partial message deltas will be sent | Tokens will be sent as data-only server-sent events (SSE) as they become available, with the stream terminated by a |
| stream_options | Options for streaming response | Only set this when you set If set, an additional chunk will be streamed before the field on this chunk shows the token usage statistics for the... |
| response_format | An object specifying the format that the model must output | Setting to { "type": "json_object" } enables JSON Output, which guarantees the message the model generates is valid JSON. |
| tools | A list of tools the model may call | Currently, only functions are supported as a tool. |
| tool_choice | Controls which (if any) tool is called by the model | means the model will not call any tool and instead generates a message. |
| logprobs | Whether to return log probabilities of the output tokens or not | If true, returns the log probabilities of each output token returned in the |
| top_logprobs | An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with... | JSON body field of POST /chat/completions. |
GLM (Z.ai) — first 15 of 23, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| model | The model code to be called | GLM-5.3, GLM-5.2, GLM-5.1, GLM-5-Turbo are the latest flagship model series, foundational models specifically designed for agent applications. |
| messages | The current conversation message list as the model’s prompt input, provided in JSON array format, e.g.,`{“role”:... | Possible message types include system messages, user messages, assistant mess |
| do_sample | When do_sample is true, sampling strategy is enabled; when do_sample is false, sampling strategy parameters such as... | Default value is `true`. |
| stream | This parameter should be set to false or omitted when using synchronous call | It indicates that the model returns all content at once after generating all content. |
| reasoning_effort | Controls the model's reasoning effort level, takes effect when `thinking` is enabled | Default is `max`, supported by `GLM-5.2` and above. |
| temperature | Sampling temperature, controls the randomness of the output, must be a positive number within the range: `[0.0, 1.0]` | The GLM-5.3, GLM-5.2, GLM-5.1, GLM-5, GLM-4.7, GLM-4.6 series default value is `1.0`, GLM-4.5 series |
| top_p | Another method of temperature sampling, value range is: `[0.01, 1.0]` | The GLM-5.3, GLM-5.2, GLM-5.1, GLM-5, GLM-4.7, GLM-4.6, GLM-4.5 series default value is `0.95`, GLM-4-32B-0414-128K default value is `0.9`. |
| max_tokens | The maximum number of tokens for model output, the GLM-5.3, GLM-5.2, GLM-5.1, GLM-5, GLM-4.7, GLM-4.6 series... | JSON body field (integer) of POST /paas/v4/chat/completions. |
| tool_stream | Whether to enable streaming response for Function Calls | Default value is false. |
| tools | A list of tools the model may call | Currently, only functions are supported as a tool. |
| tool_choice | Controls how the model selects a tool | JSON body field (field) of POST /paas/v4/chat/completions. |
| stop | Stop word list | Generation stops when the model encounters any specified string. |
| response_format | Specifies the response format of the model | Defaults to text. |
| request_id | Passed by the user side, needs to be unique; used to distinguish each request, 6–64 characters | If not provided by the user side, the platform will generate one by default. |
| user_id | Unique ID for the end user, 6–128 characters | Avoid using sensitive information. |
Kimi (Moonshot AI) — first 15 of 22, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| model | Model ID to call; kimi-k3 is the default | Set to a model ID from the Models & Modes table below. |
| messages | The conversation message list; supports dynamic tool messages | A {"role": "system", "tools": [...]} message can be inserted at any position. |
| max_completion_tokens | Maximum tokens to generate | Kimi K3 defaults to 131072 and can be set up to 1048576. Replaces the deprecated max_tokens. |
| max_tokens | Deprecated token limit field | Use max_completion_tokens instead. |
| response_format | Controls the output format; {"type": "json_object"} enables JSON mode | Default is {"type": "text"}. In JSON mode you must also guide the model to output JSON in the prompt. |
| stop | Stop words that halt generation on a full match | Up to 5 strings, each at most 32 bytes; matched words are not output. |
| stream | Return the response as a stream | Boolean, default false. |
| stream_options | Options for streaming responses | Object with child attributes for stream behavior. |
| tools | A list of tools the model may call | Standard function-tool definitions. |
| tool_choice | Controls whether and how the model calls tools | auto (default), none, required, or an object forcing a specific function. |
| logprobs | Return log probabilities of the output tokens | Boolean, default false; values arrive in the logprobs field of the response. |
| top_logprobs | Number of most likely tokens to return per position | Integer 0-20; requires logprobs: true. |
| prediction | Predicted Output configuration to speed up largely-known responses | Useful when regenerating a file with only minor changes. |
| prompt_cache_key | Cache key to raise cache hit rates across similar requests | For coding agents, typically a session or task ID; reuse it when a session resumes. |
| safety_identifier | Stable per-user identifier for abuse detection | Hash the username or email rather than sending it raw. |
Kling AI — first 15 of 24, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| contents | Reference input collection: prompts, images, Elements | Array of typed inputs forming the generation request. |
| "type": "prompt" | Prompt input identifier inside contents | Carries the text field with positive and negative descriptions. |
| "type": "first_frame" | First-frame image input identifier | Anchors the opening frame of the generated video. |
| "type": "last_frame" | Last-frame image input identifier | Anchors the closing frame of the generated video. |
| "type": "element" | Element input identifier | References a reusable Element in the generation. |
| "type": "image" | Appearance reference image (Motion Control) | Generated characters follow the reference image; proportions should match the motion video. |
| "type": "video" | Motion reference video identifier (Motion Control) | Drives character motion from a reference clip. |
| text | Prompt text content, positive and negative descriptions | String field inside a prompt-type content item; can add elements and motion effects. |
| settings | Output configuration object: resolution, duration, and related fields | Container for generation output parameters. |
| multi_shot | Whether to generate multi-shot video | Boolean; when false, multi-shot prompts will not produce multi-shot output. |
| audio | Audio generation switch for the video | Values: native (audio matching the visuals) or off (silent). |
| resolution | Resolution of the generated video | Set inside the settings object. |
| options | General configuration: callback address, watermark, and similar | Container object alongside contents and settings. |
| callback_url | Callback URL for task result notifications | Server sends a notification on task status change; see the Callback Protocol. |
| external_task_id | Custom task ID, unique within the account | Does not overwrite the system task ID; usable for status queries. |
Vidu — first 15 of 24, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| model | Model name | Accepted values:viduq3-turbo, viduq3-pro , viduq2 , viduq1 -viduq3-turbo: Compared to viduq3-pro, the generation speed is faster -viduq3-pro: Supports audio-visual synchronization,... Required. |
| style | The style of output video | Defaults to general, Accepted values: general anime - general : General style. Allows style control through prompts - anime: Anime style. Optimized for anime aesthetics, with better... |
| prompt | Text prompt A textual description for video generation, with a maximum length of 5000 characters | Required. |
| duration | Video duration | Default values vary by model: - viduq3-pro,viduq3-turbo: default 5s, available: 1 - 16 - viduq2: default 5s, available: 1 - 10 - viduq1: default 5s, available: 5 |
| seed | Random seed - | Defaults to a random seed number - Manually set values will override the default random seed |
| aspect_ratio | The aspect ratio of the output video | Defaults to 16:9, accepted: 16:9 9:163:4 4:3 1:1 Note:3:4& 4:3only support q2 & q3 model |
| resolution | Resolution | Default values vary by model & duration: - viduq3-pro , viduq3-turbo (1-16s): default 720p, available: 540p, 720p, 1080p - viduq2 (1-10s): default 720p, available: 540p 720p 1080p -... |
| movement_amplitude | The movement amplitude of objects in the frame | Defaults to auto, accepted value: auto small medium large This parameter does not take effect when using the q2 & q3 model |
| images | An image to be used as the start frame of the generated video For fields that accept images: - Only accepts 1 image -... | - Supported formats: png, jpeg, jpg, webp - The aspect ratio of the images must be less than 1:4 or 4:1 - All images are limited to 50MB - The post body of the HTTP request should not... Required. |
| voice_id | Voice ID, The Q3 series model is not effective Used to determine the voice character in the video | The system will automatically recommend a suitable voice, and optional values can be found in the Voice List. You can also use the Voice Cloning API to clone any voice. The voice_id... |
| is_rec | Whether to use the recommended prompt | - true: Yes, the system will automatically generate and apply a recommended prompt to create the video. The number of recommended prompts = 1. - false: No, the video will be generated... |
| auto_subjects | Optional | Whether to use the intelligent entity library capability, default is false, optional values are true and false... | - false: Do not use the intelligent agent library capability. |
| subjects | Required | When using the q3, q2, q1, and 2.0 models, only the main body of the image and text can be used - The maximum... | JSON body field of the Vidu generation endpoints. |
| videos | Optional | The video URL corresponding to the subject | All subjects share a 13s duration (each image subject = 1s). Must provide either this or images. - Note 1: This parameter is only supported by the viduq2-pro model. - Note 2: When using... |
| bgm | Whether to add background music to the generated video.（q3 model not available） Default: false | Acceptable values: true, false. When true, the system will automatically add a suitable BGM. BGM has no time limit and the system automatically adapts. BGM does not take effect when the... |
MiniMax (Hailuo) — first 15 of 24, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| model | Model name | Currently available: MiniMax-H3. |
| content | Array of multimodal input describing the information used to generate the video | Each element is distinguished by type (text / image_url / video_url / audio_url) and can be labeled with a role. Every request must include one non-empty text item (the prompt is... |
| resolution | Video resolution | Currently available: 768P, 2K. |
| duration | Duration of the generated video in seconds | Required, integer. Available values: 4-15. |
| ratio | Aspect ratio of the generated video | Defaults to adaptive (the most suitable ratio is chosen automatically based on the input; the actual ratio can be read from the ratio field of the query endpoint). Available values:... |
| callback_url | Callback URL for task status changes | Once configured, the MiniMax server first sends a verification request containing a challenge field (you must return the challenge unchanged within 3 seconds to complete verification);... |
| "type": "text" | Text prompt content item; every scenario must include one | Inside the content array, with the prompt in the text field. |
| "type": "image_url" | Image input content item | Supplies a reference or first-frame image to the generation. |
| "type": "video_url" | Video input content item | Supplies a reference video to the generation. |
| "type": "audio_url" | Audio input content item | Supplies reference audio to the generation. |
| role | Position or purpose of a content item | Conditionally required depending on the content type. |
| MiniMax-H3 | Current video generation model ID (Hailuo 03) | Set as the model field value. |
| model | Model ID | JSON body field of the OpenAI-compatible chat endpoint. |
| service_tier | Service tier for request admission | Supported values are standard and priority. If omitted, the request uses the standard tier. The priority price is 1.5 times the standard price and ensures priority admission so the... |
| messages | A list of messages containing the conversation history | Supports text, image, video, and tool call content. |
PixVerse — first 15 of 26, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| aspect_ratio | Aspect ratio | other models : 16:9, 4:3, 1:1, 3:4, 9:16 v6/c1 models : 16:9, 4:3, 1:1, 3:4, 9:16, 2:3, 3:2, 21:9 |
| duration | Video duration | v.3.5/v4/v4.5 : 5/8 (v3.5 1080p cannot use 8) v5 : 5/8 v5.5/v5.6 : 5/8/10 (1080p cannot use 10) v6/c1 : 1~15 |
| model | Model version (now supports | v3.5/v4/v4.5/v5/v5.5/v5.6/v6/c1 |
| prompt | Prompt <= 5000 characters | JSON body field of the PixVerse video generation endpoints. |
| quality | Video quality ("360p", "540p", "720p", "1080p") | JSON body field of the PixVerse video generation endpoints. |
| seed | Random seed, | range: 0 - 2147483647 |
| generate_multi_clip_switch | Supported in | v5.5/v6 models. Single or multi-clip switch. controls single-clip and multi-clip generation modes. true: Multi-clip , false: Single-clip. default value : false |
| generate_audio_switch | Supported in | v5.5/v5.6/v6/c1 models. Audio switch. Controls whether the video has audio. true: Audio on , false: Audio off . default value : false |
| sound_effect_switch | Supported in | v5 models and below. |
| sound_effect_content | Supported in | v5 models and below. Activated when sound_effect_switch=true, Describe the sound effect you want. Leave blank for auto generation. |
| lip_sync_tts_switch | Supported in | v5 models and below. Set to true if you want to enable this feature. Default is false. |
| lip_sync_tts_content | Supported in | v5 models and below. ~140 (UTF-8) characters |
| lip_sync_tts_speaker_id | Supported in | v5 models and below. id from Get speech tts list |
| img_id | Image ID from Upload image API | single image or single-image templates |
| img_ids | img_ids is only for multi-image templates | ex) "img_ids ":[0,0] |
Manus — first 15 of 27, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| project_id | Project ID to associate this task with | The project's instruction will be automatically applied. Use project.list to get available project IDs. |
| locale | Locale for the task output language (e.g., "en", "zh-CN", "ja") | Defaults to the user's account locale setting. |
| interactive_mode | When enabled, the agent may pause and ask follow-up questions if the input is insufficient | When disabled (default), the agent proceeds with best-effort execution without asking. |
| hide_in_task_list | When true, the task will not appear in the Manus webapp task list | The task is still accessible via the task_url in the response. Useful for automated/background tasks. |
| share_visibility | Controls who can view the task | "private" (default) — only the task creator can view. "team" — all team members can view. "public" — anyone with the share_url can view without authentication. |
| agent_profile | Agent profile to use for the task | "manus-1.6" (default) — standard capability. "manus-1.6-lite" — lightweight, faster responses. "manus-1.6-max" — maximum capability. Free personal accounts are downgraded to... |
| title | Custom title for the task | If not provided, a title will be auto-generated based on the input message. |
| structured_output_schema | JSON Schema for structured output extraction | When provided, the agent runs normally, then a post-processing step extracts a result conforming to your schema. The schema must follow the Structured Output subset of JSON Schema: all... |
| message.content | String (plain text) or array of ContentPart objects | User text is limited to approximately 5,000 estimated tokens per request; the exact character count varies by language and content. For an array, the limit applies to the combined text... |
| message.connectors | List of connector IDs to enable for this task | Resolution order when omitted: 1) if the task belongs to a project, the project's default connectors are used; 2) otherwise, the user's default enabled connectors are used. Use... |
| message.enable_skills | Skill IDs to enable for this task | If empty or omitted, loads the skills the user has enabled in their account settings. Use skill.list to retrieve available skill IDs. |
| message.force_skills | Skill IDs the agent must invoke during this task | Forced skills are automatically available even if not listed in enable_skills. |
| message.task_references | Task IDs of existing tasks to reference from this message | The agent can then browse the conversation and files of those tasks on demand. Each entry must be a bare 22-character alphanumeric task ID — a full task URL, or a shortcut value such as... |
| "type": "text" | Must be "text" | Field of a ContentPart item inside message.content. |
| text | The text content of the message | Across a ContentPart array, all text parts must contain no more than approximately 5,000 estimated tokens in total. |
Qwen (Alibaba Model Studio) — first 15 of 29, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| model | Model to call | Supported families: Qwen LLM (commercial and open source), Qwen-VL, Qwen-Coder, Qwen-Omni, Qwen-Math, plus DeepSeek, Kimi, GLM and MiniMax. Required. |
| messages | Conversation context passed to the model, in conversational order | Required. System message, if present, must come first. |
| temperature | Sampling temperature controlling output diversity | Value range [0, 2). Set either temperature or top_p, not both. |
| top_p | Nucleus sampling probability threshold | Value range (0, 1.0]. Set either temperature or top_p, not both. |
| top_k | Number of candidate tokens sampled during generation | Larger is more random. null or a value above 100 disables the top_k strategy. |
| repetition_penalty | Penalty for consecutive repeated sequences | 1.0 means no penalty; raise it to reduce repetition. No strict upper bound. |
| presence_penalty | Controls content repetition across the generated text | Value range [-2.0, 2.0]. Positive reduces repetition, negative increases it. |
| max_completion_tokens | Maximum output length, including chain-of-thought and answer | Generation stops early with finish_reason length if exceeded. |
| enable_thinking | Switch thinking mode on for mixed-thinking models | Applies to Qwen3 family, Qwen3-Omni-Flash and Qwen3-VL models. |
| thinking_budget | Maximum tokens allowed for the thinking process | Applies to Qwen3 family, GLM and Kimi models; kimi-k3 does not support it. |
| reasoning_effort | Inference intensity level | Valid values vary by model; DeepSeek-V4 and GLM default to high, with max available. |
| seed | Random seed for reproducible results | Same seed and unchanged parameters return the same result as far as possible. |
| tools | Array of tool objects the model may call in function calling | If set and the model decides to call a tool, tool info is returned in the response. |
| stream_options | Configuration for streaming output | Takes effect only when stream is true; include_usage adds token usage to the last chunk. |
| audio | Voice and format of the output audio | Qwen-Omni models only, and requires modalities set to ["text","audio"]. |
Tencent Hunyuan — first 15 of 22, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| Model | Model name to call | Required. Example: hunyuan-turbos-latest. Billing differs by model. |
| Messages.N | Chat context array, ordered oldest to newest | Required. Up to 40 entries. Role values: system, user, assistant, tool. System, if present, must be first; user and assistant alternate. |
| Stream | Streaming response switch | Defaults to false. When true, results arrive incrementally over SSE in Choices[n].Delta. |
| StreamModeration | Content moderation switch for streaming output | Boolean. |
| Temperature | Sampling temperature controlling output randomness | Float. Set either Temperature or TopP, not both. |
| TopP | Nucleus sampling probability threshold | Float. Set either Temperature or TopP, not both. |
| Seed | Random seed for reproducible output | Non-zero positive integer up to 10000. Not recommended unless needed; unsuitable values degrade quality. |
| Stop.N | Custom stop strings that end generation | Array of strings. |
| Tools.N | List of callable tools for function calling | Effective only on hunyuan-turbos, hunyuan-t1 and hunyuan-functioncall models. |
| ToolChoice | Tool usage mode | Values: none, auto, custom. Defaults to auto. Effective on hunyuan-turbo and hunyuan-functioncall models. |
| EnableThinking | Chain-of-thought reasoning switch | Enabled by default. Currently effective only on the hunyuan-a13b model. |
| EnableEnhancement | Capability enhancement switch, such as search | Boolean. |
| ForceSearchEnhancement | Force search enhancement on | Boolean. |
| EnableSpeedSearch | Turn on the fast search variant | Defaults to false. When on and search is triggered, streaming returns the first token sooner. |
| SearchInfo | Return SearchInfo in the response when search is triggered | Defaults to false. |
OpenClaw — first 15 of 66, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| /new [model] | Archive the current session and start a fresh one | Type in any connected chat channel or the Control UI. |
| /reset [soft [message]] | Reset the current session in place | soft keeps the transcript, drops reused CLI backend session ids, and reruns startup |
| /name <title> | Name or rename the current session | Omit the title to see the current name and a suggestion |
| /compact [instructions] | Compact the session context | See Compaction |
| /stop | Abort the current run | Type in any connected chat channel or the Control UI. |
| /session idle <duration|off> | Manage thread-binding idle expiry | Type in any connected chat channel or the Control UI. |
| /session max-age <duration|off> | Manage thread-binding max-age expiry | Type in any connected chat channel or the Control UI. |
| /export-session [path] | Owner-only | Export the current session to HTML inside the workspace. Alias: /export |
| /export-trajectory [path] | Export a JSONL trajectory bundle for the current session | Alias: /trajectory |
| /think <level|default> | Set the thinking level or clear the session override | Aliases: /thinking, /t |
| /verbose on|off|full | Toggle verbose output | Alias: /v |
| /trace on|off | Toggle plugin trace output for the current session | Type in any connected chat channel or the Control UI. |
| /fast [status|auto|on|off|default] | Show, set, or clear fast mode | Type in any connected chat channel or the Control UI. |
| /reasoning [on|off|stream] | Toggle reasoning visibility | Alias: /reason |
| /elevated [on|off|ask|full] | Toggle elevated mode | Alias: /elev |
Nous Hermes — first 15 of 42, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| <|start_header_id|>role<|end_header_id|> | Llama 3.1 chat header tokens used by Hermes 4 405B | Roles: system, user, assistant. Each turn ends with <|eot_id|>. Smaller Hermes 4 models use ChatML instead. |
| <|eot_id|> | End-of-turn token in the 405B prompt format | Closes each header-delimited message. |
| thinking=True | Chat template flag that activates reasoning mode | Pass to the tokenizer chat template; alternatively use the deep-thinking system prompt from the model card. |
| <think> </think> | Tags enclosing the model's internal reasoning | Emitted when reasoning mode is active; strip them to get the final answer only. |
| You are a deep thinking AI... | Official reasoning-mode system prompt | Full text on the model card. Additional system instructions before or after it adjust thinking effort, style, and format. |
| <tools> </tools> | System-prompt tags wrapping the JSON tool signatures | Function definitions go inside these tags in the system message. |
| <tool_call> </tool_call> | Tags the model emits around a JSON function call | Parse the JSON inside to execute the call. |
| <tool_response> </tool_response> | Tags wrapping the tool result you feed back | Return the function output inside these tags in a tool role message. |
| /new [name] | Start a new session (fresh session ID + history) | Alias: /reset. Optional [name] sets the initial session title — e.g. |
| /clear | Clear screen and start a new session | Type in the Hermes CLI/TUI or a connected messaging channel. |
| /history | Show conversation history (respects | Type in the Hermes CLI/TUI or a connected messaging channel. |
| /save | Save the current conversation | Type in the Hermes CLI/TUI or a connected messaging channel. |
| /prompt | Compose your next prompt in $EDITOR (markdown) instead of the inline input — useful for long, multi-line, or... | Alias: /compose. |
| /retry | Retry the last message (resend to agent) | Type in the Hermes CLI/TUI or a connected messaging channel. |
| /undo | Remove the last user/assistant exchange | Type in the Hermes CLI/TUI or a connected messaging channel. |
MCP (Model Context Protocol) — first 15 of 30, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| claude mcp add <name> ... | Register an MCP server with Claude Code | Local stdio by default; --transport http or sse for remote servers, with -- separating the launch command for stdio. |
| claude mcp add-json <name> '{...}' | Register a server from a JSON definition | Paste the same JSON shape used in .mcp.json. |
| claude mcp list | List all configured servers | Shows every server visible in the current scope hierarchy. |
| claude mcp get <name> | Show details for one server | Includes transport, scope, and status. |
| claude mcp remove <name> | Remove a configured server | Takes the server name shown by claude mcp list. |
| claude mcp login <name> / logout <name> | Authenticate or sign out of a remote server from the command line | OAuth flow runs in the browser unless --no-browser is set. |
| claude mcp reset-project-choices | Reset approval choices for project-scoped .mcp.json servers | Claude prompts again before using project-scoped servers. |
| claude mcp serve | Run Claude Code itself as a stdio MCP server | Prints nothing on start; other applications connect to it as a server. |
| mcpServers | Top-level object in .mcp.json holding all server definitions | Each key is a server name mapping to its config object. |
| command / args | Launch command and arguments for a local stdio server | Example: "command": "npx", "args": ["-y", "@modelcontextprotocol/server-github"]. |
| env | Environment variables passed to a stdio server | Object of KEY: value pairs; supports expansion like ${VAR} and ${VAR:-default}. |
| type / url | Transport type and endpoint for a remote server | "type": "http" or "sse" with the server URL. |
| headers | Custom HTTP headers sent to a remote server | Used for API keys or bearer tokens on http/sse transports. |
| ${VAR} / ${VAR:-default} | Environment variable expansion inside .mcp.json | Expands in command, args, env, url, and headers; the :- form supplies a default. |
| .mcp.json | Project-scope server file committed at the repository root | Claude prompts for approval before using servers from it; reset with claude mcp reset-project-choices. |
Agent Instruction Files — 11 entries, full reference
| Command / Syntax | What it does | Notes |
|---|---|---|
| AGENTS.md | Open cross-tool instruction file: a README for agents | Read by Codex, Cursor, Gemini CLI, Aider, Zed, Warp, Devin, Copilot coding agent, Factory, Jules, opencode, Windsurf and more. Plain Markdown, no required fields. |
| AGENTS.md (nested) | Per-package instruction files in a monorepo | Agents read the nearest AGENTS.md up the directory tree; the closest one takes precedence, so each subproject can ship its own. |
| CLAUDE.md | Claude Code project memory file | Loaded at session start from the project root and parent directories; edit in-session with the /memory command documented on our Claude Code page. |
| ~/.claude/CLAUDE.md | User-level Claude Code memory | Applies across all your projects; project files add to it. |
| .cursor/rules/*.mdc | Cursor project rules (current format) | Rule files with metadata controlling when each rule applies. |
| .cursorrules | Cursor legacy single-file rules | Still read for backwards compatibility; new projects should use .cursor/rules/. |
| .github/copilot-instructions.md | GitHub Copilot repository-wide custom instructions | Applies to Copilot Chat and the coding agent for that repository. |
| *.instructions.md | Copilot scoped instruction files | Per-path instructions with applyTo front matter, alongside the repository-wide file. |
| GEMINI.md | Gemini CLI context file | Project instructions for Gemini CLI; it also reads AGENTS.md. |
| CONVENTIONS.md | Aider coding conventions file | Loaded with --read or listed in .aider.conf.yml so it is marked read-only for the LLM. |
| ln -s AGENTS.md CLAUDE.md | Symlink pattern: keep one instruction source for tools with their own filename | A single AGENTS.md stays canonical while filename-specific tools follow the link. |
Rows on this page are identical to the per-tool reference pages; the per-tool pages carry source links and category notes. Other bundles: CLI Essentials · AI Coding Tools · Cloud & DevOps · Design Tools · Office & Productivity · all bundles.