xiao-fan-ka_skill

This skill acts as a personalized restaurant finder, remembering your tastes and recommending spots across data sources for delightful meals.
  • Python

2.5k

GitHub Stars

4

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill xiao-fan-ka

  • _meta.json275 B
  • AGENT_GUIDE.md1.5 KB
  • README.md699 B
  • SKILL.md560 B

Overview

This skill is a personalized restaurant-finding assistant that builds a flavor profile and recommends eateries tailored to your tastes. It aggregates and cross-checks data from two major social review sources to deliver reliable, customized suggestions. The more you use it, the better it learns your preferences and the more accurate its recommendations become.

How this skill works

The skill collects public review and post data from two complementary sources and performs cross-validation to filter noise and confirm popular signals. It constructs a user taste profile from your explicit preferences and implicit behavior, then ranks candidate restaurants by relevance, reliability, and novelty. Recommendations adapt over time as the profile updates with your feedback and selections.

When to use it

  • When you want personalized restaurant suggestions based on your unique tastes.
  • When planning meals in unfamiliar neighborhoods or cities.
  • When you need curated lists that balance popular opinion and niche discoveries.
  • When you want a tool that refines recommendations as you give feedback.
  • When you prefer cross-verified suggestions rather than single-source reviews.

Best practices

  • Provide explicit taste signals (cuisines, disliked ingredients, ambiance) to jump-start accurate recommendations.
  • Give feedback after visits — thumbs up/down or short notes — so the profile improves quickly.
  • Use the skill across multiple sessions and locations to broaden the profile’s context.
  • Compare a few top suggestions rather than choosing the first result to balance novelty and reliability.
  • Allow location access when possible to enable nearby and context-aware recommendations.

Example use cases

  • Discovering a neighborhood gem for a date night that matches your preferred vibe and cuisine.
  • Finding allergy-safe or ingredient-specific restaurants by filtering based on your profile.
  • Exploring trending dishes validated across two social platforms before trying them.
  • Planning a multi-stop food tour with complementary flavors and reliable ratings.
  • Quickly locating a breakfast spot that fits your morning preferences while traveling.

FAQ

It combines explicit preferences you set with behavioral signals from your choices and feedback, gradually adjusting the taste profile.

What data sources are used?

Recommendations are generated by aggregating and cross-validating public review content and social posts from two major review platforms to reduce noise and increase reliability.

Is my feedback private?

Feedback is used to improve your personal profile and recommendations; review any privacy settings available to control data usage.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational