Pp Allrecipes logo

Pp Allrecipes

CommunityPopular
mvanhorn
pp-allrecipes

Every Allrecipes recipe in your terminal — cached as data, with pantry-aware search, Bayesian-smoothed ranking, and one-line grocery lists. Trigger phrases: `search Allrecipes for X`, `find a recipe for brownies`, `scale this Allrecipes recipe`, `build a grocery list from these recipes`, `what can I cook with what I have`, `use allrecipes-pp-cli`, `run allrecipes`.

Overview

Publishermvanhorn
Repositoryprinting-press-library
Skill namepp-allrecipes
Stars
2K
Forks
614
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mvanhorn on GitHub. Read the source before you install it.

Installation

Install the Pp Allrecipes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git /tmp/printing-press-library
mkdir -p .claude/skills
cp -r /tmp/printing-press-library/cli-skills/pp-allrecipes .claude/skills/pp-allrecipes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pp Allrecipes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pp Allrecipes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pp Allrecipes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Allrecipes — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the allrecipes-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
    bash
    npx -y @mvanhorn/printing-press-library install allrecipes --cli-only
  2. Verify: allrecipes-pp-cli --version
  3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer):

bash
go install github.com/mvanhorn/printing-press-library/library/food-and-dining/allrecipes/cmd/allrecipes-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

When to Use This CLI

Reach for this CLI when an agent or user needs Allrecipes data as data, not as a webpage: searching for proven recipes, fetching ingredient lists in structured form, building grocery lists across multiple recipes, scaling for different serving counts, or filtering by what's in the pantry. The local SQLite cache makes iterative meal-planning workflows fast — every recipe fetched is queryable forever via pantry, with-ingredient, top-rated, and dietary. Skip this CLI when the user wants a multi-site comparison (different tool) or when they need authenticated features like saved recipes or meal plans (intentionally not supported).

When Not to Use This CLI

Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Local state that compounds

  • pantry — Score Allrecipes recipes against your pantry — see which ones you can actually cook tonight without a grocery run.

    When the user says 'what can I make with what I've got', this is the only command that knows the answer.

    bash
    allrecipes-pp-cli pantry --pantry-file ~/pantry.txt --query brownies --agent
  • with-ingredient — Find every cached recipe that uses a given ingredient — a SQL view across your local corpus.

    Use this when the user starts from an ingredient they want to use up, not a dish name.

    bash
    allrecipes-pp-cli with-ingredient buttermilk --top 10 --agent
  • dietary — Filter cached recipes by gluten-free / vegan / low-carb using JSON-LD keywords plus ingredient-name patterns.

    Use this when dietary restrictions are non-negotiable and the user wants more than what the site's diet category page surfaces.

    bash
    allrecipes-pp-cli dietary --type gluten-free --top 20 --agent

Ranking that beats the website

  • top-rated — Rank recipes by Bayesian-smoothed rating — proven popular wins over 1-review 5-star noise.

    Pick this over raw search when the agent wants proven recipes, not freshly-uploaded 5-star outliers.

    bash
    allrecipes-pp-cli top-rated brownies --smooth-c 200 --limit 10 --agent
  • quick — Top-rated recipes that fit a strict time cap — Allrecipes' UI cannot enforce one, but the local cache can.

    Use this when the user's constraint is time, not dish — 'what can I make in 25 minutes that's actually good'.

    bash
    allrecipes-pp-cli quick --max-minutes 30 --query chicken --agent

Agent-native plumbing

  • cookbook — Compile a top-rated category into a single markdown cookbook with TOC, ingredients, and instructions.

    When the user asks for a curated bundle (gifts, meal-plan packs), this builds it in one command.

    bash
    allrecipes-pp-cli cookbook --category italian --top 20 --output italian-cookbook.md
  • grocery-list — Aggregate ingredients from many recipes into a deduped, agent-readable shopping list.

    Use this at the end of a meal plan — one call replaces five scrolls through ingredient lists.

    bash
    allrecipes-pp-cli grocery-list https://www.allrecipes.com/recipe/9599/quick-and-easy-brownies/ https://www.allrecipes.com/recipe/16354/easy-meatloaf/ --agent

Reachability mitigation

  • doctor — Health check that names the Cloudflare 'Just a moment...' interstitial by inspecting the response body, then advises the browser-chrome transport.

    When the CLI breaks because of bot detection, the agent gets a specific, actionable error rather than a generic timeout.

    bash
    allrecipes-pp-cli doctor

HTTP Transport

This CLI uses Chrome-compatible HTTP transport over HTTP/3 for browser-facing endpoints. It does not require a resident browser process for normal API calls.

Command Reference

recipes — Public Allrecipes recipe pages with Schema.org Recipe JSON-LD markup

  • allrecipes-pp-cli recipes get — Fetch a recipe by ID + slug; returns parsed JSON-LD Recipe. Requires Cloudflare clearance cookie via `auth login...
  • allrecipes-pp-cli recipes search — Search Allrecipes for recipes matching a query (no Cloudflare clearance required).

Hand-written commands

  • allrecipes-pp-cli recipe <url-or-id> — Fetch and render a single recipe by URL or ID
  • allrecipes-pp-cli search <query> — Search Allrecipes for recipes (live + cache)
  • allrecipes-pp-cli top-rated <query> — Search and rank by Bayesian-smoothed rating (prior 4.0, default C=200)
  • allrecipes-pp-cli quick — Recipes from cache that fit a strict time cap and are top-rated
  • allrecipes-pp-cli pantry — Score cached recipes by overlap with a pantry file
  • allrecipes-pp-cli with-ingredient <ingredient> — Reverse index: cached recipes that use a given ingredient
  • allrecipes-pp-cli dietary — Filter cached recipes by gluten-free / vegan / low-carb (strict ingredient blocklist)
  • allrecipes-pp-cli cookbook — Compile a top-rated category or cuisine into a markdown cookbook
  • allrecipes-pp-cli grocery-list <urls...> — Aggregate ingredients across many recipes into a deduped shopping list (subtract --pantry-file if given)
  • allrecipes-pp-cli scale <url> — Rescale a recipe to a target serving count
  • allrecipes-pp-cli nutrition <url> — Show nutrition for a recipe (per serving and total)
  • allrecipes-pp-cli ingredients <url> — Show parsed ingredients for a recipe
  • allrecipes-pp-cli instructions <url> — Show numbered instructions for a recipe
  • allrecipes-pp-cli reviews <url> — Show review summary for a recipe
  • allrecipes-pp-cli category <slug> — Browse recipes in a category (e.g. dessert, weeknight)
  • allrecipes-pp-cli cuisine <slug> — Browse recipes by cuisine
  • allrecipes-pp-cli ingredient <name> — Browse recipes featuring a primary ingredient
  • allrecipes-pp-cli occasion <slug> — Browse recipes by occasion (holiday, weeknight, party)
  • allrecipes-pp-cli article <url> — Extract the body of an Allrecipes article page
  • allrecipes-pp-cli gallery <url> — Extract recipe links from an Allrecipes round-up gallery
  • allrecipes-pp-cli cook <slug> — Show a cook profile and their recipes
  • allrecipes-pp-cli export <url> — Export a recipe as markdown
  • allrecipes-pp-cli sync — Refresh cached recipes that are stale
  • allrecipes-pp-cli cache — Inspect, list, or clear the local recipe cache
  • allrecipes-pp-cli doctor — Diagnose connectivity, Cloudflare clearance state, and cache health

Freshness Contract

This printed CLI owns bounded freshness only for registered store-backed read command paths. In --data-source auto mode, those paths check sync_state and may run a bounded refresh before reading local data. --data-source local never refreshes. --data-source live reads the API and does not mutate the local store. Set ALLRECIPES_NO_AUTO_REFRESH=1 to skip the freshness hook without changing source selection.

When JSON output uses the generated provenance envelope, freshness metadata appears at meta.freshness. Treat it as current-cache freshness for the covered command path, not a guarantee of complete historical backfill or API-specific enrichment.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

bash
allrecipes-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Recipes

Top 5 brownies, narrowed to ranking fields only

bash
allrecipes-pp-cli top-rated brownies --limit 5 --agent --select rank,title,url,rating,reviewCount,madeItCount

Bayesian smoothing kills 1-review 5-star outliers; --select trims the payload to fields agents actually use.

Plan three weeknight dinners and one grocery list

bash
allrecipes-pp-cli quick --max-minutes 30 --query chicken --limit 3 --agent | xargs allrecipes-pp-cli grocery-list --pantry-file ~/pantry.txt --agent

Compose two commands: quick weeknight selection feeds straight into pantry-aware grocery aggregation.

Compile a personal Italian cookbook

bash
allrecipes-pp-cli cookbook --category italian --top 20 --output ~/italian-cookbook.md

Pulls the top-20 by Bayesian rating and writes a markdown cookbook with TOC.

Cook with what's in the pantry

bash
allrecipes-pp-cli pantry --pantry-file ~/pantry.txt --max-missing 2 --agent --select title,url,have,missing

Local index ranks cached recipes by ingredient overlap; --max-missing 2 keeps recipes that need at most two extra ingredients.

Strict gluten-free with field narrowing

bash
allrecipes-pp-cli dietary --type gluten-free --top 20 --agent --select title,url,rating,recipeIngredient

Strict ingredient blocklist + JSON-LD tag filter; --select pulls only the title, url, rating, and ingredients for agent verification.

Auth Setup

Browse and search work without any auth. Recipe detail pages need a Cloudflare clearance cookie — run allrecipes-pp-cli auth login --chrome once to capture one from your browser. This is bot-protection clearance, not an Allrecipes account login: no username, no password, no token tied to a user. The CLI does not support saved-recipes / meal-plan / profile features that require an actual Allrecipes account.

Run allrecipes-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

  • Pipeable — JSON on stdout, errors on stderr

  • Filterable--select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

    bash
    allrecipes-pp-cli recipes get mock-value mock-value --agent --select id,name,status
  • Previewable--dry-run shows the request without sending

  • Offline-friendly — sync/search commands can use the local SQLite store when available

  • Non-interactive — never prompts, every input is a flag

  • Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

json
{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal — piped/agent consumers get pure JSON on stdout.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

allrecipes-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
allrecipes-pp-cli feedback --stdin < notes.txt
allrecipes-pp-cli feedback list --json --limit 10

Entries are stored locally at ~/.allrecipes-pp-cli/feedback.jsonl. They are never POSTed unless ALLRECIPES_FEEDBACK_ENDPOINT is set AND either --send is passed or ALLRECIPES_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

SinkEffect
stdoutDefault; write to stdout only
file:<path>Atomically write output to <path> (tmp + rename)
webhook:<url>POST the output body to the URL (application/json or application/x-ndjson when --compact)

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.

allrecipes-pp-cli profile save briefing --json
allrecipes-pp-cli --profile briefing recipes get mock-value mock-value
allrecipes-pp-cli profile list --json
allrecipes-pp-cli profile show briefing
allrecipes-pp-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

CodeMeaning
0Success
2Usage error (wrong arguments)
3Resource not found
4Authentication required
5API error (upstream issue)
7Rate limited (wait and retry)
10Config error

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show allrecipes-pp-cli --help output
  2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
  3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

  1. Install the MCP server:
    bash
    go install github.com/mvanhorn/printing-press-library/library/food-and-dining/allrecipes/cmd/allrecipes-pp-mcp@latest
  2. Register with Claude Code:
    bash
    claude mcp add allrecipes-pp-mcp -- allrecipes-pp-mcp
  3. Verify: claude mcp list

Direct Use

  1. Check if installed: which allrecipes-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
  2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
  3. Execute with the --agent flag:
    bash
    allrecipes-pp-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help: allrecipes-pp-cli <command> --help.

Frequently asked questions

What does the Pp Allrecipes AI skill do?

Every Allrecipes recipe in your terminal — cached as data, with pantry-aware search, Bayesian-smoothed ranking, and one-line grocery lists. Trigger phrases: `search Allrecipes for X`, `find a recipe for brownies`, `scale this Allrecipes recipe`, `build a grocery list from these recipes`, `what can I cook with what I have`, `use allrecipes-pp-cli`, `run allrecipes`.

Why use Pp Allrecipes on TypingMind?

Because you install it once and use it with any model. Pp Allrecipes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pp Allrecipes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-allrecipes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pp Allrecipes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pp Allrecipes?

As many as you like. As long as a model supports skills, you can use Pp Allrecipes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pp Allrecipes AI skill free?

Yes. It is published on GitHub by mvanhorn under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇