Paprika Recipe Importer

Convert recipe text (pasted text, video transcript, image description, or any raw content) into a .paprikarecipes file that can be imported directly into the...

Security Scan

The skill's code and instructions match its stated purpose (packaging recipe JSON into a .paprikarecipes file); it has no network calls, no extra credentials, and no surprising behavior.

Purpose & Capability

Name/description promise (convert recipe content into a .paprikarecipes file) aligns with the provided helper script and SKILL.md. The included Python script implements only packaging of JSON to gzipped .paprikarecipe entries in a zip file.

Instruction Scope

Runtime instructions are limited to extracting recipe fields, writing a JSON to a temp path, invoking the local script, and delivering the file. Instructions do not request unrelated files, secrets, or external endpoints. The SKILL.md explicitly forbids fabricating values.

Install Mechanism

No install spec (instruction-only) and a small local Python script are provided. No downloads, third-party package installs, or archive extraction are present.

Credentials

No required env vars, no credentials, and no config paths. The script operates on local files only and does not read environment variables.

Persistence & Privilege

Skill is not always-on and does not request elevated or persistent system privileges, nor does it modify other skills or global agent settings.

Assessment

This skill appears coherent and limited in scope: it converts recipe JSON into a .paprikarecipes zip using a local Python script and does not make network requests or ask for credentials. Before installing/using: (1) ensure python3 is available in the runtime environment, (2) review the included script if you want to double-check behavior (it generates a UID if missing and writes output to the provided path), and (3) be aware that SKILL.md suggests writing temp files (e.g., /tmp/<recipe>.json and the output file) which may contain the recipe text—avoid including sensitive personal information in recipes. If you run this in a multi-tenant environment, consider cleaning up temp files after use.

Convert recipe content (any format/language) into a .paprikarecipes file for Paprika 3.

Workflow

1. Extract recipe fields from the input (text, image, transcript, URL content).
2. Build a JSON recipe object — only include fields actually present in the source; do NOT invent values.
3. Run the packaging script to produce the .paprikarecipes file.
4. Deliver the file to the user.

Step 1 — Extract Fields

Parse the input and populate only the fields that exist in the source:

JSON field	Notes
name	Recipe title. Required.
ingredients	Newline-separated list. Format: quantity unit ingredient.
directions	Newline-separated steps.
description	Intro/summary paragraph, if present.
notes	Tips, variations, author notes.
servings	e.g. "4 porções" or "serves 6"
prep_time	e.g. "15 min"
cook_time	e.g. "30 min"
total_time	e.g. "45 min"
source	Author name, site name, person.
source_url	Original URL, if available.
categories	JSON array of strings, e.g. ["Jantar", "Massas"]
difficulty	"Easy", "Medium", or "Hard" — only if explicitly stated.
rating	Integer 1–5 — only if explicitly stated.
nutritional_info	Any nutritional data present.

Rules:

• Never fabricate values not present in the source.
• Keep the original language (Portuguese, English, mixed — whatever the source uses).
• Ingredients: one per line, preserve quantities and units exactly.
• Directions: one step per line; numbered steps → strip the number (Paprika handles display).

Step 2 — Build JSON

Write the recipe as a JSON file to a temp path, e.g. /tmp/<recipe-name>.json.

Step 3 — Run the Script

python3 ~/.openclaw/skills/paprika-recipe-importer/scripts/build_paprikarecipes.py \
  /tmp/<recipe-name>.json \
  /tmp/<recipe-name>.paprikarecipes

The script accepts a single JSON object or a JSON array (for multiple recipes).

Step 4 — Deliver

Send the .paprikarecipes file to the user. Mention:

• How to import: File → Import in Paprika (or double-click the file on macOS/iOS).
• Which fields were found and which were absent from the source.