A sophisticated extraction engine that converts Instagram reels into structured recipes using caption parsing, local audio transcription, and vision analysis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawdbites
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 clawdbites 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 ClawdBites: Instagram Recipe Extractor?
ClawdBites is a technical utility designed for Openclaw Skills that automates the tedious process of manual recipe transcription from social media. It utilizes a multi-layered extraction strategy to ensure no detail is missed, even when creators omit instructions from their captions. By leveraging powerful open-source tools, it transforms ephemeral video content into permanent, structured data for your digital cookbook.
This skill is particularly valuable for users of Openclaw Skills who want to maintain privacy and performance, as it performs heavy-duty tasks like audio transcription locally using Whisper. Whether a creator hides the recipe in a pinned comment or only speaks the instructions, ClawdBites ensures you get a clean, formatted result every time.
ClawdBites: Instagram Recipe Extractor Use Cases
- Automatically extracting full recipe details when a user sends an Instagram reel link.
- Converting spoken video instructions into written, numbered steps using local AI.
- Capturing on-screen recipe cards and text overlays using computer vision.
- Saving extracted culinary data to a persistent wishlist or meal planning system.
How ClawdBites: Instagram Recipe Extractor Works
- The skill extracts metadata and description from the provided Instagram URL using yt-dlp.
- It analyzes the caption for completeness, checking for at least 3 ingredient patterns and sequential instruction verbs.
- If the caption is incomplete, it automatically downloads the reel and extracts the audio track via ffmpeg.
- It runs a local Whisper transcription on the audio to capture spoken measurements and steps.
- If visual data is needed, it extracts key frames and passes them to a vision model to read on-screen text.
- It applies heuristic inference to vague measurements (e.g., converting 'a drizzle' to '1-2 tbsp') and marks them as estimated.
- The final structured recipe is presented or saved to the user's local memory.
ClawdBites: Instagram Recipe Extractor Setup
To enable this capability within your Openclaw Skills environment, ensure the following dependencies are installed:
# Install media extraction and processing tools
brew install yt-dlp ffmpeg
# Install local transcription engine
pip3 install --user openai-whisper
ClawdBites: Instagram Recipe Extractor Data Schema & Taxonomy
The skill maintains a structured taxonomy for recipes, often stored in memory/recipe-wishlist.json. The schema includes the following fields:
| Field | Type | Description |
|---|---|---|
name |
String | Extracted or inferred recipe title |
sourceUrl |
String | The original Instagram reel link |
macros |
Object | Calories, Protein, Carbs, and Fat breakdown |
ingredients |
Array | List of items with quantities (annotated if estimated) |
instructions |
Array | Numbered steps derived from text or audio |
addedDate |
String | ISO timestamp of the extraction |
ClawdBites: Instagram Recipe Extractor Advanced Features
- Context-aware scaling that adjusts quantities based on the number of servings or protein targets.
- Intelligent measurement inference for vague cooking terms and standard package sizes.
- Seamless hand-off to meal-planner skills for automated grocery list integration.
- Automatic detection of 'pinned comment' flags to alert users when manual text input might be superior.
- Multi-modal merging that prioritizes visual text overlays over inferred audio measurements for higher accuracy.
SKILL.md
Loading
Related Openclaw Skills
Security Analysis
A professional security auditing tool designed to identify vulnerabilities, instruction injections, and data exfiltration risks within codebases and agent configurations.
Security Shield: SAST & Privacy Auditor
An automated security and privacy auditing skill that performs deep SAST analysis to identify vulnerabilities and PII leaks in codebases.
Parakeet MLX
A high-performance command-line tool for private, local speech-to-text transcription optimized for Apple Silicon.
EvoAgentX Workflow Integration
A powerful bridge connecting the EvoAgentX framework to Openclaw Skills for creating agentic workflows that automatically improve through evolutionary optimization.
Zocdoc Healthcare Finder & Booking
An AI agent skill that enables real-time search and booking for in-network doctors using the Zocdoc infrastructure.
Feishu Audio
A specialized skill for converting text to speech and sending it as native, playable audio messages in Feishu chats.
Featured*
