tasteray-skills marketplace

A TasteRay plugin collection for Claude Code, with tools for learning about people's preferences and making personalised recommendations.

In plain words
What is it for?
Use it when building conversation-based profiling or recommendation features with the TasteRay service.
Why use it?
It provides a consistent way to gather meaningful personal context and use it when recommending films, restaurants, products, travel, or jobs.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add tasteray/skills
agentmods
npx agentmods add plugins/tasteray/skills/marketplace
Clone the repo
git clone --depth 1 https://github.com/tasteray/skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

tasteray-skills marketplace scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 29 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "tasteray-skills",
  "description": "Psychological profiling skills for natural conversation using research-backed techniques",
  "metadata": {
    "description": "Psychological profiling skills for natural conversation using research-backed techniques. Includes elicitation (narrative identity, self-defining memories, Motivational Interviewing) and personalized recommendations across movies, restaurants, products, travel, and jobs."
  },
  "owner": {
    "name": "TasteRay",
    "email": "[email protected]"
  },
  "plugins": [
    {
      "name": "elicitation",
      "description": "Psychological profiling through natural conversation using narrative identity research (McAdams), self-defining memory elicitation (Singer), and Motivational Interviewing (OARS framework). Use when you need to understand core values, discover formative memories, detect emotional schemas, or build psychological profiles through gradual disclosure.",
      "source": "./elicitation",
      "strict": false,
      "category": "learning"
    },
    {
      "name": "recommendations",
      "description": "TasteRay API integration for personalized recommendations across verticals (movies, restaurants, products, travel, jobs). Use when you need to recommend items, answer 'what would I like' questions, provide personalized recommendations, rank items for users, explain why something matches their taste, or integrate psychological profiles with recommendation systems.",
      "source": "./recommendations",
      "strict": false,
      "category": "productivity"
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 29 lines scan A 33ffe880a89a

Subscribe to this mod's changes

tasteray-skills marketplace is a plugin published in the GitHub repository tasteray/skills (23 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.