Kylne700

Tasteloom — DevOps skill for Claude Code

DevOps community

Real gifts for what someone loves, with the reason.

How to install Tasteloom

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Kylne700/tasteloom and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tasteloom does

Real gifts for what someone loves, with the reason. Taste links from Qloo, an agent on Cloudflare Workers AI, real product cards from Channel3, experience links from Tavily, PayPal sandbox guest checkout. Qloo hackathon entry, built by AI agents (Claude Code).

Alternatives in DevOps

  • Cloudflare Deploy — Deploy apps to Cloudflare using Workers, Pages, and platform services 14.6k ★
  • Terraform Skill For Claude — Comprehensive Terraform and OpenTofu guidance covering testing, modules, CI/CD, and production patterns 1.4k ★
  • Workers MCP — Talk to a Cloudflare Worker from Claude Desktop 646 ★

README

Tasteloom

Real gifts for what someone loves, with the reason.

The reason on every gift idea is a contract: it must name the favourite that Qloo links most strongly to the idea, or the server replaces it with a template built from that link. Every live run in which the model takes part lists "N of M reasons kept" in the agent's lookups, so you can check the contract yourself.

Type three to five things a person loves (a book, a band, a shop, a place) and a budget. Qloo reads their taste, an AI agent finds real products with real prices, every idea says "Because they love X", and you can pay in the PayPal sandbox as a guest. No account, and Tasteloom stores nothing you type.

Try it: https://tasteloom.kylne700.workers.dev/?images=on (free, no sign-in; "Try an example" costs no API calls; `?images=on` shows product photos, which load from the shops' own servers and are off by default for privacy).

Project page: https://devpost.com/software/tasteloom. Demo video (1:45): https://youtu.be/iWgkkVTSKYI.

Test logs: [unit tests](evidence/unit.txt), [end-to-end run](evidence/e2e.txt), [Qloo contract check](evidence/contract-qloo.txt).

![The ideas screen on the saved example: the first gift idea, its "Because they love" line and two picked products, with the agent's lookups on the left](evidence/saved-example.png)

The saved example, with product photos off (the default). The page says it itself: the products and prices were live on the day it was recorded, and its taste matches and reasons are stand-ins.

This is an entry to the Qloo hackathon. It was built by AI agents (Claude Code), with a person setting the goals and owning the accounts the app uses.

Who it is for, and who could pay (a hypothesis, untested)

Who it is for: anyone with a budget and no product in mind who knows a person only in fragments: a favourite book, band, shop or place.

Who could pay: the shop, not the gift-giver. A retailer or gifting marketplace with a gift-finder page could add a reason