Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
Bot template
Original text · EnglishLost Package Desk for a store: tracks missing, stalled, and delivered-but-not-received shipments, runs carrier playbooks, and never files or refunds
https://botsdots.site/templates/noshipsherlock
https://x.ai/bot/Lll9_CtLlBh_nEOWVQfMY| Description | Lost Package Desk for a store: tracks missing, stalled, and delivered-but-not-received shipments, runs carrier playbooks, and never files or refunds |
|---|---|
| Category | customer-sales |
| Schedule | on-demand |
| Access | None stated |
| Integrations | None stated |
| Creator | @beyrouti |
| First listed | 2026-09-26 |
| Listed in | kydlikebtc/awesome-grokbot, majiayu000/awesome-grok-bot, cs68614-hash/awesome-grokbot-templates, GrokBot HQ (CC BY 4.0) |
| Add to Grok Bot | https://x.ai/bot/Lll9_CtLlBh_nEOWVQfMY |
This is the BotsDots catalog record (CC0-1.0), shown in full. The bot’s instructions, skills and routines belong to its creator and are not republished: open them on x.ai.
The **Retail AI Plugin** bundles two end-to-end Google Cloud retail skills for AI coding assistants (Gemini CLI, Claude Code, Antigravity, Codex) following the [Google Agent Plugins v1.0.0 specification][spec] (`plugin.json` + `skills/<skill-name>/SKILL.md`):
Sourcegithub.com/google/adk-recipes/tree/main/plugins/retail
Creates product search agents with semantic search and RAG on Google Cloud (Vector Search on Gemini Enterprise Agent Platform, BigQuery, embeddings). Use when the user wants to "build a product search agent", "create an e-commerce search", "make a shopping assistant", "set up semantic catalog discov
Sourcegithub.com/google/adk-recipes/blob/main/plugins/retail/skills/product-search/SKILL.md
At the beginning of the conversation, you have to authenticate the user identity by locating their user id via email, or via name + zip code. This has to be done even when the user already provides the user id.
Sourcegithub.com/sierra-research/tau2-bench/blob/main/data/tau2/domains/retail/policy.md
τ-bench family benchmark (MIT) that simulates user–agent conversations in customer-service domains (retail, airline, telecom, banking) with tools, policies and automatic task evaluation.
Sourcegithub.com/sierra-research/tau2-bench
Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image/video generation pipelines, local testing, and evaluation.
Sourcegithub.com/google/adk-recipes/blob/main/plugins/retail/skills/virtual-tryon/SKILL.md
The current time is 2024-05-15 15:00:00 EST.
Sourcegithub.com/sierra-research/tau2-bench/blob/main/data/tau2/domains/airline/policy.md