wine-purchase-evaluator skillA
wine-purchase-evaluator is agent-read markdown (skill) from slavins-co/cellartracker-mcp: Disciplined wine purchase evaluation framework for building a learning-focused cellar with limited storage. Use this skill when evaluating wine purchases from any source (retailers, flash sales, screenshots, PDFs, marathons). Triggers include requests to evaluate/assess/analyze wine purchases, make buy/pass decisions, review flash sales, or compare multiple wine offers. Provides structured BUY/CONSIDER/PASS verdicts with scoring, market analysis, and cellar fit assessment..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Wine Purchase Evaluator This skill uses preferences from `references/preferences.md` if available. If no preferences file exists, apply the framework with reasonable defaults and ask the user about their specific constraints. This skill provides a rigorous, storage-aware framework for evaluating wine purchases with a focus on educational value, quality-to-price ratio (QPR), and cellar discipline. ## Core Philosophy **Default stance: PASS** Every wine must earn its place against: - Limited storage (fridge + cabinet + racks) - Budget constraints - Your learning priorities - Existing cellar inventory **Guiding principles:** - Discipline beats curiosity - Rotation beats accumulation - Learning value trumps status/prestige - True market price matters, not claimed retail - Half bottles are educational dead-ends - Known producers over marketing hype ## Evaluation Workflow ### 1. Auto-Detect Evaluation Type Determine evaluation mode from input: **Single Wine** (most common): - Input: Wine name + price + retailer - Output: Tight format (verdict, bullets, scores) - Example: "Domaine Besson Chablis Vaillons 1er Cru 2022 $30 LastBottle" **Multiple Wines**: …
Read the whole file at its exact version.
How to install
mdr add slavins-co/cellartracker-mcp/wine-purchase-evaluator@git:20260712.da6a62dmdr add slavins-co/cellartracker-mcp/wine-purchase-evaluator@sha256:1b845d3b8e7b4ae4Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_6ewcxa6tbymlhnvh)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260712.da6a62d latest | 2026-07-12 | da6a62d | 10,772 B | A | view · diff |
| git:20260313.14f5bf8 | 2026-03-13 | 14f5bf8 | 10,772 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10772 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
slavins-co/cellartracker-mcp · 6 stars · license MIT · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6ewcxa6tbymlhnvh GET https://markdownregistry.com/api/v1/resolve?ref=slavins-co/cellartracker-mcp/wine-purchase-evaluator GET https://markdownregistry.com/api/v1/blob/1b845d3b8e7b4ae48786c980e406261be36e4d035782eb69e1a6cd3a1b42d7a1
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.