Use a household’s recorded food, drink, and restaurant preferences to recommend a place to eat or dishes to order. Add favorite restaurants over time, keeping unknown details explicit instead of guessing.
The household's food and restaurant preferences, used to recommend where and what to eat. USE WHEN where should we eat, restaurant recommendation, what do we like to eat, our favorite restaurants, pick a place for dinner, date night dinner, find a spot for a cuisine, what beer do we like, food preferences, suggest a restaurant near X, best restaurants in <city>, where to eat on our trip, add a favorite restaurant, remember this place. NOT FOR phoning to book a table, ordering delivery, business search or reviews (a scraping skill or Google Maps), groceries or recipes, business research (an OSINT skill, if installed).
Run score Not tested
See how to installRestaurants uses the household’s recorded preferences for food, drinks, cuisines, and restaurants to suggest where to eat or what to order. When you provide a location or occasion, it considers those details along with the recorded tastes and explains why a suggestion fits. It excludes places that conflict with stated dealbreakers and labels restaurants not in the records as new suggestions. You can also ask it to add a favorite restaurant and update the preference record.
Use it to choose a place for dinner or a date, find somewhere to eat while traveling, or check which foods or beers the household likes. Recorded preferences can inform future recommendations.
Before making recommendations, the skill checks the preference file. If that file is missing, it guides you through setup and does not recommend a restaurant based on assumed default preferences. It does not call to make reservations, place delivery orders, or search for groceries or recipes.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 28, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
Holds the household's food, cuisine, restaurant, and drink taste profile — what they love, what they avoid, where they like to eat, what they drink — and uses it to recommend a place, suggest what to order, or recall their preferences. The data lives in LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Restaurants/Preferences.md, the source of truth; this file only routes and holds no taste rules.
TBD, so later picks never inherit a guess.TBD or missing: a short drink list or cuisine ranking is reported as short, and a place's cuisine, address, or menu is never invented to fill a gap.| Intent | Trigger | File |
|---|---|---|
| Recommend | "where should we eat", "recommend a restaurant", "pick a place", "find a spot for a cuisine", "date night dinner", "what should we order" | Intents/Recommend.md |
| AddPreference | "add a favorite", "remember this place", "we love X now", "log this restaurant", "update our food prefs" | Intents/AddPreference.md |
For a plain "what do they like?" lookup, read the Preferences data file and answer — no intent needed.
| File | Read when |
|---|---|
Setup.md | first-time install: creating the Preferences data file and its sections |
All taste data lives under the USER tree, not in this skill: LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Restaurants/Preferences.md (taste profile, ranked cuisines, favorite restaurants, drinks, and optionally companion restrictions). First-time setup is in Setup.md. Read the file before every recommendation. When the file is missing, stop and point the user at Setup.md; never recommend from a default taste profile.
The file grows through AddPreference, or a direct edit for small fixes.
Example 1: Pick a place
User: "Where should we go for dinner tonight?"
→ Recommend intent
→ One clear pick (or 2-3 ranked), each with a line tying it to the taste profile, no dealbreaker hit, any location or occasion given factored in
Example 2: Capture a new favorite
User: "We tried a new place in town and loved it — add it"
→ AddPreference intent
→ The restaurant is a dated row in Favorite Restaurants with location, cuisine and notes, and the reply says what was added
Example 3: Plain lookup
User: "What beer do we like again?"
→ No intent
→ The answer comes from the file's Drinks → Beer section, with any TBD favorites said plainly
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find and fetch vendor cybersecurity reports, then compare their findings on topics such as ransomware, breaches, cloud security, and AI. Analyses identify the reports consulted and cite each figure by vendor, year, and report, including where sources disagree.
Compare a component's own design needs with the goals of the larger system through three structured passes. The result identifies conflicts, recommends an appropriate scope, and assesses whether the proposed design fits the whole.
Find quotes that fit a text’s themes, with attribution and a short reason for each suggestion. Add sourced quotes, research thinkers, and organize a quote collection by theme and usage history to avoid repetition.
Create blog illustrations, technical diagrams, comparisons, comics, and icons through workflows tailored to each format. The skill guides composition, color, and model selection, then stages generated images for review before they are used in a project.
Assess the visual quality of images, films, slides, and site captures against a brief and craft criteria. Two vision judges score the work and rank defects, guiding bounded revision; delivery is gated on a passing critique, with human calibration labels recorded separately.
Find arXiv papers by topic, research category, or paper ID. Retrieve titles, authors, abstracts, and links, check new submissions, and add AlphaXiv's AI-generated overviews when available to help decide which papers to read.