An AI-powered tool that converts video URLs into structured recipes by analyzing captions, comments, and web data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install recipe-video-extractor
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install recipe-video-extractor using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Recipe Video Extractor?
The Recipe Video Extractor is a sophisticated skill designed to bridge the gap between visual cooking content and actionable text instructions. By utilizing browser automation, this tool scrapes video descriptions and comments to reconstruct full recipes without requiring the user to watch the entire video or manually transcribe details. It is an essential addition to the library of Openclaw Skills for users who want to organize their digital cookbooks efficiently.
Built with developer-centric logic, the skill handles complex tasks like expanding hidden text on dynamic pages and normalizing messy social media data into clean Markdown. Whether the recipe is hidden in a caption or buried in a pinned comment, this skill ensures you get the ingredients and steps you need with clear source attribution and confidence levels.
Recipe Video Extractor Use Cases
- Quickly extract ingredients from an Instagram Reel or TikTok while on the go.
- Convert a lengthy YouTube cooking tutorial into a concise, numbered list of steps.
- Capture recipe details from videos where the description is cut off or requires manual expansion.
- Gather cooking measurements from top-rated comments when the video creator omits specific quantities.
How Recipe Video Extractor Works
- The user provides a URL using the trigger command to initiate the extraction process.
- The skill acknowledges the request and launches a browser instance to navigate to the video platform.
- It first analyzes the highest-signal area: the video caption and expanded description.
- If the recipe is incomplete, the automation scrolls to load and inspect pinned and top-rated comments.
- In cases where data is still missing, the skill utilizes a web search fallback to find indexed versions of the recipe elsewhere on the internet.
- Finally, the AI normalizes the data, applying heuristics to identify quantities, units, and cooking verbs, then presents a structured Markdown output.
Recipe Video Extractor Setup
To integrate this skill into your environment, ensure you have the necessary browser automation drivers installed. This skill is optimized for use within the ecosystem of Openclaw Skills.
# Install the browser dependencies
npx playwright install chromium
# Add the skill to your agent configuration
openclaw install recipe-video-extractor
Configure your environment variables to allow for web fetching and search fallbacks if high-level extraction is required.
Recipe Video Extractor Data Schema & Taxonomy
The skill organizes extracted data into a strict schema to ensure consistency across different video platforms. It captures the following metadata and content structure:
| Component | Description | Format |
|---|---|---|
| Dish | The inferred name of the recipe | String |
| Ingredients | Quantities and items | Unordered List |
| Steps | Sequential cooking instructions | Numbered List |
| Metadata | Prep time, servings, and temperature | Key-Value Pairs |
| Source Notes | Attribution (e.g., Description, Pinned Comment) | String |
| Confidence | Reliability rating based on data completeness | High/Medium/Low |
Recipe Video Extractor Advanced Features
- Multi-source conflict handling: Automatically identifies and presents version variants if comments contradict the video description.
- Heuristic unit normalization: Automatically converts informal measurements into standardized culinary units for better readability.
- Dynamic UI expansion: Uses advanced browser automation to interact with 'See More' buttons and hidden DOM elements that traditional scrapers miss.
- Real-time status reporting: Provides granular progress updates such as fetching captions or checking pinned comments to improve user experience.
- Privacy-first extraction: Operates without requiring account credentials for most public video platforms within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Instagram Reel Downloader for WhatsApp
Download Instagram Reels via browser automation and send them as WhatsApp-ready videos using Openclaw Skills.
Tavily AI Search
A specialized search engine skill designed to provide Large Language Models with clean, structured web data and synthesized AI answers.
Trading Coach
An AI trading coach that converts broker CSV exports into professional review reports with 8-dimensional scoring and deep pattern insights.
RSS AI Reader
An intelligent RSS and Atom feed reader that uses LLMs to generate summaries and delivers them through multiple notification channels.
Simplify Code
A specialized skill for refactoring code to improve readability and maintainability without altering functionality.
EvoMap Heartbeat Manager
Automated heartbeat management for EvoMap AI-to-AI network nodes to ensure continuous connectivity and active status.
Featured*
