Import every saved Instagram food reel into a self-hosted recipe app with a pipeline Codex wrote
- Posted
- by Karan Sharma (@mrkaran_)
- Last checked
- Method:
- How we verify
Evidence: Screenshots or logsThe source shows screenshots, a transcript or the agent's output.
Outcome
Karan Sharma gave Codex access to all their saved Instagram food reels and asked it to import them into their self-hosted Mealie recipe instance. Codex wrote a pipeline on the fly and ran each reel through it: yt-dlp pulls the audio, Whisper transcribes it, Gemini 3.8 Flash formats it as a recipe and it's sent to Mealie. Sharma calls it very useful.
Agent
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Run this task now, exactly as written below. Everything you need is here, so start straight away and only stop if something required is missing or a rule below tells you to. Goal: Turn my saved cooking videos into written recipes in my recipe app. Fill in before running: - Where the saved videos are (list of links or export): [DETAILS] - My recipe app and how to add recipes to it: [APP] - Any format I want (metric, servings): [DETAILS] Rules: - Only process videos I've saved, for my personal use. - For each video, transcribe the audio and turn it into a recipe with ingredients, amounts and steps. - Mark any amount you had to guess, and keep a link to the original video. - Do a test run on three videos and show me before doing the rest. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. Output: Recipes added to my app, and a list of any videos that failed. You'll know it worked when: every saved video is a searchable recipe I can cook from.
Customize this prompt
Answer these questions and we'll put your answers into the prompt for you. You can leave any of them empty.
Your prompt
Run this task now, exactly as written below. Everything you need is here, so start straight away and only stop if something required is missing or a rule below tells you to. Goal: Turn my saved cooking videos into written recipes in my recipe app. Fill in before running: - Where the saved videos are (list of links or export): [DETAILS] - My recipe app and how to add recipes to it: [APP] - Any format I want (metric, servings): [DETAILS] Rules: - Only process videos I've saved, for my personal use. - For each video, transcribe the audio and turn it into a recipe with ingredients, amounts and steps. - Mark any amount you had to guess, and keep a link to the original video. - Do a test run on three videos and show me before doing the rest. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. Output: Recipes added to my app, and a list of any videos that failed. You'll know it worked when: every saved video is a searchable recipe I can cook from.
Scroll to see the whole prompt. Your answers show in green.
3 blanks are still empty: Where the saved videos are (list of links or export); My recipe app and how to add recipes to it; Any format I want (metric, servings). They'll stay in brackets in your prompt, so the chat tool may ask you about them.
What you type stays in this browser tab. We don't send it or save it, and it's gone when you leave the page. If you use a "Try this in" button, your answers go to that tool as part of the prompt.
Try this in:
This prompt has blanks to fill in, like [DETAILS]. We'll copy it instead of filling it in, so you can edit it before you send.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Run this task now, exactly as written below. Everything you need is here, so start straight away and only stop if something required is missing or a rule below tells you to. Goal: Turn my saved cooking videos into written recipes in my recipe app. Fill in before running: - Where the saved videos are (list of links or export): [DETAILS] - My recipe app and how to add recipes to it: [APP] - Any format I want (metric, servings): [DETAILS] Rules: - Only process videos I've saved, for my personal use. - For each video, transcribe the audio and turn it into a recipe with ingredients, amounts and steps. - Mark any amount you had to guess, and keep a link to the original video. - Do a test run on three videos and show me before doing the rest. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. - Skip duplicates and tell me which videos had no usable recipe. Output: Recipes added to my app, and a list of any videos that failed. You'll know it worked when: every saved video is a searchable recipe I can cook from. Before you finish: re-read my goal and constraints, check your answer against each one, and list anything you assumed or couldn't confirm.
Source
https://x.com/mrkaran_/status/2111523597349249308
Related cases
- Port a backend to Convex in four hours with Factory's DroidRecreated promptEvidence: Described by poster
The poster reports that Factory's Droid ported their tRPC/Drizzle custom backend to Convex in about 4 hours, with some bugs left to fix.
Factory Droid · Coding · Source date:
- Migrate a 50-screen app from Firebase to Supabase with Claude CodeRecreated promptEvidence: Described by poster
Going feature by feature, the poster used Claude Code to generate database schemas, write queries and fix daily errors; they report migrating about 85% of a 45–50 screen Flutter app from Firebase to Supabase in 10–20 days.
Poster says:~85% migrated in 10–20 days
Claude Code · Coding · Source date:
- Turn long recipe steps into an importable to-do list with a custom GPT so every Thanksgiving dish is on timeRecreated promptEvidence: Described by poster
Amanda Parsons, who has adult ADHD, finds recipes pack too much into one step. While planning Thanksgiving, Parsons asked ChatGPT for help with the cooking schedule, then found it could turn recipes into CSV files for the Todoist to-do app; for the first time, dinner was ready on time and every dish made it to the table as planned. After a chaotic batch of English muffins without it, Parsons built a custom GPT to do the conversion, going through five rounds of tests over an hour until the CSV imported successfully.
ChatGPT · Personal · Source date: