danielrosehill/Claude-Purchasing-Plugin

danielrosehill/Claude-Purchasing-Plugin

Plugin Claude Code

Claude Code plugin: marketplace-agnostic purchasing and procurement process — spec definition from a vague want or a photograph, annotated search vocabulary, intake, research, compare, evaluate, recommend, market-check, spec-driven market landscape surveys, live price/delivery scanning through your own VPN egress…

danielrosehill/Claude-Purchasing-Plugin

Agent

Researches manufacturer reputation, history, support quality, and regional presence. Use before recommending any product from an unfamiliar brand.

danielrosehill/Claude-Purchasing-Plugin

Agent

Interviews the user about their tastes, parses ingested history (OPML, watch history, reading lists), and maintains memory/preferences.md as the canonical preference profile.

danielrosehill/Claude-Purchasing-Plugin

Agent

Compares prices across vendors and markets, calculates markups, and factors in import costs (shipping, VAT, customs). Use when evaluating value across multiple sources or when deciding buy-local vs. import.

danielrosehill/Claude-Purchasing-Plugin

Agent

Extracts structured product data (name, brand, price, SKU, vendor) from screenshots, PDFs, and catalog images. Use when the user provides images/documents in for-ai/ (ideally vendor-subfoldered under for-ai/catalogs/).

danielrosehill/Claude-Purchasing-Plugin

Agent

Gathers and synthesizes reviews from multiple platforms into a weighted score and a short honest summary. Use during research for each serious candidate.

danielrosehill/Claude-Purchasing-Plugin

Agent

Verifies claimed product specs against authoritative manufacturer sources. Use when a claimed spec is load-bearing for the recommendation (e.g., "has USB-C charging", "supports Wi-Fi 6E").

danielrosehill/Claude-Purchasing-Plugin

Command

Apply one or more buyer profiles from buyer-profiles/ to spec.md so the /research and /recommend phases bias toward a named purchasing pattern (BIFL, budget, minimalist, etc.).

danielrosehill/Claude-Purchasing-Plugin

Command

You are running spec definition. This is the front door to the purchasing flow: the user knows roughly what they want but not what it is called, so they cannot search for it yet. Your job is to close that gap and emit two artefacts.

danielrosehill/Claude-Purchasing-Plugin

Command

Quick one-off evaluation of a single product against the current spec.

danielrosehill/Claude-Purchasing-Plugin

Command

Extract product information from screenshots, PDFs, and catalog images in for-ai/ into a structured CSV at data/extracted/products.csv.

danielrosehill/Claude-Purchasing-Plugin

Command

You are running the intake for this purchase. The goal is to populate spec.md at the repo root with the per-purchase brief.

danielrosehill/Claude-Purchasing-Plugin

Command

Load the user's standing shopping preferences (country, currency, trusted/avoided brands, markup threshold, risk tolerance, preferred vendors, etc.) into the current session so they can be applied during /intake, /research, and /recommend.

danielrosehill/Claude-Purchasing-Plugin

Command

Compare local market prices against international RRP with import-cost realism.

danielrosehill/Claude-Purchasing-Plugin

Command

Identify unmet and over-served requirements, the compromise axes, and where the market is thin — the payload of a landscape survey.

danielrosehill/Claude-Purchasing-Plugin

Command

Build the spec-conformance matrix across the whole field — every requirement against every live option, unknowns marked as unknown.

danielrosehill/Claude-Purchasing-Plugin

Command

Re-sweep a previously surveyed market and report what changed since the last survey.

danielrosehill/Claude-Purchasing-Plugin

Command

Write the landscape report — the state of the market against the spec, as markdown and PDF.

danielrosehill/Claude-Purchasing-Plugin

Command

Derive how the market divides — segments and the axes it actually varies along — from the enumerated field.

danielrosehill/Claude-Purchasing-Plugin

Command

Define the requirement envelope and survey scope for a market landscape survey — capability-framed, no candidates.

danielrosehill/Claude-Purchasing-Plugin

Command

Sweep the market and enumerate the full field against the survey spec — breadth first, everything logged and dated.

danielrosehill/Claude-Purchasing-Plugin

Command

List recent recommendations from the recommendations/ folder with their feedback status (liked, disliked, no-response, queued).

danielrosehill/Claude-Purchasing-Plugin

Command

First-run setup for the recommendation workspace — picks format, captures initial preferences, builds the folder structure, and suggests MCPs.

danielrosehill/Claude-Purchasing-Plugin

Command

Parse an OPML file (typically a podcast subscription export) from ingest/opml/ and use it to seed/update the preference profile.