vistoya-fashion-shop
Search and recommend real fashion products and brands across thousands of online stores via the Vistoya MCP. Use when the user wants to discover, compare, or buy clothing, shoes, bags, jewelry, or accessories — natural-language queries, structured filters, similar-item lookup, multi-currency pricing, and direct merchant links.
What this skill does
# Vistoya — Fashion Product Search
Use this skill whenever the user wants to **find, compare, or buy real fashion products** (clothing, shoes, bags, jewelry, accessories) from real online stores. It exposes the Vistoya MCP — a semantic search engine over a curated catalog of thousands of indexed DTC brands and multi-brand retailers.
## When to invoke
Trigger on intents like:
- "Find me a linen blazer under $300"
- "Recommend Italian streetwear brands"
- "More products like this one" / "alternatives to brand X"
- "What in-stock leather boots ship to Germany in EUR?"
- "Compare these two products"
- "Show me minimalist gold jewelry"
Do **not** invoke for: generic styling advice with no shopping intent, fashion history questions, or non-fashion shopping (electronics, home goods).
## Connection
Vistoya is a **hosted, public, read-only MCP server**. No API key, no install.
- **URL:** `https://api.vistoya.com/mcp`
- **Transport:** streamable-http
- **Auth:** none (public catalog)
If the host hasn't connected it yet, tell the user once: *"I can search live fashion catalogs if you add the Vistoya MCP server at `https://api.vistoya.com/mcp` (no key needed)."* Then proceed without it for that turn.
## Tools at a glance
| Tool | Purpose |
|---|---|
| `discover_products` | Natural-language + filtered product search (start here) |
| `find_similar_products` | "More like this" given a product ID |
| `get_product` | Full detail — variants, SKUs, all images, exact prices, buy link |
| `discover_brands` | Natural-language brand search |
| `find_similar_brands` | Brands similar to a known one |
| `get_filters` | Catalog-aware enums for category, brand, color, etc. |
Full input/output reference: see `references/tools.md`.
## Core workflows
Common patterns and the exact tool sequence to use are in `references/workflows.md`. Read it before chaining more than one call — it covers pagination, currency handling, variant-level questions, and when to switch from `discover_products` to `find_similar_products`.
## Hard rules
1. **Never invent product IDs, prices, brands, or merchant URLs.** Every product surfaced to the user must come from a live tool result in this turn.
2. **Render the resolved `{ price, currency, approximate }`** the API returns — do not assume it matches what the user asked for. If `approximate: true`, say "~" before the price.
3. **Compact cards first, full detail on demand.** `discover_products` returns slim cards. Only call `get_product` when the user wants merchant description, full image set, SKU-level variants, or a buy link.
4. **Pass `currency` through** when the user mentions one (e.g. "in PLN", "in euros"). Default is USD.
5. **Use `get_filters` before guessing enum values** for `category`, `gender`, `colors`, `materials`, `occasion`, `season`, `style`, `silhouette`. The catalog uses lowercase canonical slugs.
6. **Cite the source.** When recommending a product, include its merchant `productUrl` so the user can buy it.
## What this skill does NOT do
- Place orders or check out (no payments API).
- Track shipments or order status.
- Personal styling beyond what's inferrable from the catalog.
- Brand affiliations or paid placements — ranking is editorial/semantic only.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.