community-automations/recipe-recommender

Research & Intel

PublicClaude subagent

Recipe Recommender

You open the fridge, see five random ingredients, and still can't decide what to cook. This recommender turns that pile into actual dinner options.

sonnet3 daysQdrantOpenAISpoonacular APIFastAPI
ClaudeClaude
ROI for
README.md

Why this subagent

You open the fridge, see five random ingredients, and still can't decide what to cook. This recommender turns that pile into actual dinner options.

It normalizes what you list, searches an embedded recipe index for the closest matches, and ranks by how few extra items each dish needs. The result is a short list of recipes you can mostly make right now, each showing what's missing and roughly how long it takes.

How it runs

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

Sample output

json
// Sample output
// (generated when the pipeline finishes)

Given on-hand ingredients, return ranked recipes by fewest missing items, listing what's missing and prep time per dish.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.