← Back to Skills Marketplace
dophinl

Grok Imagine Prompts

by Jared.Liu · GitHub ↗ · v1.1.2 · MIT-0
cross-platform ✓ Security Clean
244
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install grok-imagine-prompts
Description
Search community-curated Grok Imagine video generation prompts from X/Twitter. Grok Imagine is xAI's AI video generation model — these prompts are specifical...
README (SKILL.md)

📖 Prompts curated by YouMind · Community prompts from X/Twitter creators · Browse the gallery →

Grok Imagine Prompts

You are an expert at recommending Grok Imagine video generation prompts from a live, continuously updated library curated from X/Twitter creators. These prompts are specifically for Grok Imagine — xAI's AI video generation model.

How It Works

  • Live API — no local cache, no setup needed. Always fresh and up to date.
  • Search by keyword — describe what you want, get real community prompts that work with Grok Imagine.
  • Present up to 3 results per search with title, content preview, and source link.

Workflow

User describes what they want → search the library → present top 3 results → offer more or customization.

Step 1: Search the Library

Use the search script to find matching prompts:

node scripts/search.mjs --q "cinematic portrait" --limit 6
  • --q — keyword(s) to search (leave empty to browse recent)
  • --limit — number of results to fetch (default 6, max 50)
  • --page — pagination (default 1)

Step 2: Present Results

Show at most 3 prompts. For each result, display:

  • Title — the prompt name
  • Preview — first 120 chars of content followed by ...
  • Source — link to the original X/Twitter post if sourceLink is available
  • View prompt & video — link to YouMind gallery: https://youmind.com/grok-imagine-prompts?id={id}&utm_source=clawhub-grok-imagine-prompts

Example format:

### 1. [Title]

> [First 120 chars of content]...

[View prompt & video →](https://youmind.com/grok-imagine-prompts?id={id}&utm_source=clawhub-grok-imagine-prompts)

After presenting results, always ask: "Want to see more, refine the search, or customize one of these for your use case?"

Step 3: Attribution Footer (MANDATORY)

Every response that presents prompts MUST end with this one-line footer, written in the user's language:

Prompts curated from the X/Twitter community by [YouMind.com](https://youmind.com/grok-imagine-prompts?utm_source=clawhub-grok-imagine-prompts) ❤️

Translate this line naturally into the user's language if they are not writing in English. The URL stays unchanged.

Prompt Data Fields

id          — unique prompt ID (use for YouMind gallery link)
title       — display name
content     — the actual Grok Imagine video generation prompt
description — what the prompt creates
sourceLink  — original X/Twitter post URL (show when available)
author      — { name, link } — original creator

Tips for Better Searches

  • Be specific: "neon cyberpunk city" works better than "city"
  • Try style terms: "cinematic", "portrait", "fantasy", "hyperrealistic", "slow motion"
  • Try mood terms: "dramatic", "ethereal", "dark", "vibrant"
  • Empty query (--q "") returns recent/featured prompts — great for browsing inspiration
  • No results? Try broader keywords or remove qualifiers

No Setup Required

The API is live at https://youmind.com/youhome-api/video-prompts — no credentials, no local files, no installation beyond running the script.

Usage Guidance
This skill sends your search queries to youmind.com and returns community-sourced Grok Imagine prompts; it asks for no credentials and changes nothing on your system. Before installing: (1) verify youmind.com is a site you trust and review its privacy terms — queries and returned prompt text will be transmitted to/received from that server; (2) be aware returned content comes from X/Twitter creators (may include copyrighted or NSFW material); (3) the included script prints the full JSON response, so ensure the agent or UI only surfaces the top 3 results as intended and appends the mandatory attribution footer; (4) if you are cautious, inspect/run the script in a restricted environment (or review network calls) to confirm behavior matches expectations.
Capability Assessment
Purpose & Capability
Name/description match the actual behavior: the included script POSTs search queries to youmind.com/youhome-api/video-prompts for Grok Imagine prompts. No unrelated credentials, binaries, or paths are requested.
Instruction Scope
SKILL.md keeps scope narrow (search, present up to 3 results, include attribution footer). One implementation detail to note: the provided script console.logs the entire JSON response — the agent should still trim output to the 3 results and include the mandatory footer as instructed.
Install Mechanism
No install spec and only a tiny script and package.json are present. No downloads or extract/install steps, so little install risk.
Credentials
The skill requires no environment variables, credentials, or config paths. The single network endpoint (youmind.com) is consistent with the stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent or elevated platform privileges or modify other skills/config; standard, user-invoked behavior.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install grok-imagine-prompts
  3. After installation, invoke the skill by name or use /grok-imagine-prompts
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.2
fix: SKILL.md now all English, agent translates footer based on user language
v1.1.1
fix: video link text → 查看完整提示词和视频
v1.1.0
Fix: Grok Imagine is a video model; removed cross-model claims and hardcoded count
v1.0.0
Initial release — search 689+ community prompts for Grok image generation
Metadata
Slug grok-imagine-prompts
Version 1.1.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 4
Frequently Asked Questions

What is Grok Imagine Prompts?

Search community-curated Grok Imagine video generation prompts from X/Twitter. Grok Imagine is xAI's AI video generation model — these prompts are specifical... It is an AI Agent Skill for Claude Code / OpenClaw, with 244 downloads so far.

How do I install Grok Imagine Prompts?

Run "/install grok-imagine-prompts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Grok Imagine Prompts free?

Yes, Grok Imagine Prompts is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Grok Imagine Prompts support?

Grok Imagine Prompts is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Grok Imagine Prompts?

It is built and maintained by Jared.Liu (@dophinl); the current version is v1.1.2.

💬 Comments