second-state/market-research-grok/skill
Claude Code and agent skill by second-state/market-research-grok
- community
Checking that the SKILL.md file is still in the repository.
Install
npx vskill@latest install second-state/market-research-grok/skillSKILL.md
Market Research via Grok — X/Web Sentiment Analysis + Product Visuals
Analyze market demand for a product idea by searching X (Twitter) and the web for real user opinions, pain points, and competitive signals. Generates an honest market assessment plus 5 AI-rendered product concept images and 5 animated videos.
Binary
{baseDir}/scripts/market_research— Market research CLI.
Prerequisites
GROK_API_KEYenvironment variable set with a valid xAI API key.
Usage
Full run (research + images + videos)
Research only (skip media generation)
Parameters
| Parameter | Required | Description | |
|---|---|---|---|
--product | Yes | Product description: features, user profiles, price points, use cases | |
--output | No | Output file path (defaults to stdout) | |
--terms | No | Number of search terms to generate, 10-20 (default: 15) | |
--skip-media | No | Skip image and video generation (research only) |
Output
A JSON report containing:
product_summary— The input product descriptionsearch_terms— Generated multi-dimensional search termsfindings[]— Per-term analysis with positive/negative signals, quotes, and sentimentsynthesis— Final assessment with market need score (1-10), pain points, risks, and opportunitiesmedia[]— 5 product concept images and 5 animated videos (unless--skip-media)
Each media entry contains:
description— What the image/video showsimage_prompt/video_prompt— The prompts used for generationimage_url— URL to the generated product concept imagevideo_url— URL to the 5-second animated video
⚠️ Image and video URLs are temporary. Download or present them immediately.
Workflow
1. Gather the Product Description
Ask the user to describe their product idea. Encourage them to include:
- Key features and differentiators
- Target user profiles / personas
- Proposed price points
- Example use cases or problem scenarios
2. Run the Analysis
For a full analysis with visuals:
For quick research without media (faster, cheaper):
The CLI runs six phases:
- Term Generation — Grok generates 10-20 search terms covering features, competitors, personas, pricing, and pain points.
- Market Research — Each term is searched on X and the web via Grok with live search enabled.
- Synthesis — All findings are synthesized into an honest market assessment.
- Image Prompts — Grok creates 5 polished image concepts based on the product and synthesis.
- Image Generation — Each concept is rendered via grok-imagine-image-pro.
- Video Generation — Each image is animated into a 5-second video via grok-imagine-video.
3. Present the Results
Read the JSON output and present a summary to the user:
Key sections to highlight:
- Market Need Score (1-10) and description
- Pain Points Solved vs Pain Points Missed
- Competitive Landscape
- Honest Assessment — the frank "would you invest?" verdict
- Risks and Opportunities
- Product Visuals — Share the image and video URLs with the user
4. Download Media (Important)
Image and video URLs are temporary. If the user wants to keep them:
How It Works
- Uses Grok (grok-4-0709) for research/synthesis — most advanced model, always reasons at maximum effort
- Uses grok-imagine-image-pro for images — highest quality ($0.07/image)
- Uses grok-imagine-video for videos — 5 seconds, 16:9, 720p, image-to-video animation
- All research calls have X search, web search, and news search enabled
- The synthesis is designed to be brutally honest, not a cheerleading exercise
Cost Per Run
- Research only (
--skip-media): ~17 Grok API calls (variable with token usage) - Full run: research + 5 images ($0.35) + 5 videos ($1.25) = ~$1.60 extra for media
Supported Platforms
- macOS Apple Silicon (aarch64)
- macOS Intel (x86_64)
- Linux x86_64 (static musl)
- Linux aarch64 (static musl)
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskill/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/second-state/market-research-grok/skill)