CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

recommendations

How to suggest options that fit the user and don't repeat earlier ones (meals, restaurants, trips, activities, gifts, books). Use before any open-ended recommendation.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Fresh recommendations

  1. Check prior context first:
    • <user_profile> in your thread prompt for preferences and hard constraints (diet, allergies, budget, dates, accessibility, companions).
    • Past threads and files: list_threads and read_thread on voice_agent, plus files in the project folder.
    • Earlier conversations: recall with the topic.
  2. Select options:
    • Treat all previously suggested options as an anti-repeat list unless the user asks to revisit one (say so if re-suggesting a past favorite on purpose).
    • Vary meaningful dimensions (cuisine, price, neighborhood, effort) rather than near-duplicates.
    • Verify live facts (hours, prices, availability) with search_web_grounded or search_maps_grounded and link sources.
  3. Record suggestions: In a project folder, update AGENTS.md (e.g., "Suggested so far") so future threads don't repeat them.
Repository

google/adk-samples

Path

core/python/adk-voice-agent/sandbox/skills/recommendations/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.