# Broker Recognize

> Product photo recognition for C2C resale. Use when user uploads a product photo and wants AI to identify the item for resale listing. Extracts brand, product name, model, category, condition grade (A-E), material, color, size, notable features, and visible flaws. Also usable standalone via /broker-recognize. Trigger phrases: "what is this", "identify this", "analyze this item", photo upload for r…

- **Type:** Skill
- **Install:** `agentstack add skill-madguyevans-creator-resale-agent-skill-hub-broker-recognize`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [madguyevans-creator](https://agentstack.voostack.com/s/madguyevans-creator)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [madguyevans-creator](https://github.com/madguyevans-creator)
- **Source:** https://github.com/madguyevans-creator/resale-agent-skill-hub/tree/main/skills/broker-recognize

## Install

```sh
agentstack add skill-madguyevans-creator-resale-agent-skill-hub-broker-recognize
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# broker-recognize: Photo → Product Info

Extracts structured product information from user-uploaded photos for C2C resale listing purposes.

## Prerequisite: ANTHROPIC_API_KEY

This skill uses the **Anthropic API** (Claude Vision) for image analysis. Your current LLM model may not support multimodal vision, so the skill calls the Vision API directly.

```bash
export ANTHROPIC_API_KEY="sk-ant-..."
```

If the key is missing, the skill will output an error instructing the user to set it.

## Workflow

1. User provides 1-3 photos of the item
2. Analyze using vision: brand, product name, model, category, condition (A-E), material, color, size, features, flaws, estimated original retail
3. Present structured card to user for confirmation/correction
4. Save product info to conversation context for next skill in pipeline

## Condition Grade Scale

| Grade | Label | Criteria |
|-------|-------|----------|
| A | Like New | No visible wear, original packaging if applicable |
| B | Excellent | Minor signs of use, no significant flaws |
| C | Good | Visible wear, minor flaws, fully functional |
| D | Fair | Noticeable wear/flaws, may need minor repair |
| E | For Parts | Significant damage, sold as-is |

## Key Rule

Be honest about flaws. Transparency is the foundation of C2C trust. A lost honest sale is better than a return from undisclosed flaws.

## Script

`scripts/recognize.py` provides the structured prompt template and output schema.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [madguyevans-creator](https://github.com/madguyevans-creator)
- **Source:** [madguyevans-creator/resale-agent-skill-hub](https://github.com/madguyevans-creator/resale-agent-skill-hub)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-madguyevans-creator-resale-agent-skill-hub-broker-recognize
- Seller: https://agentstack.voostack.com/s/madguyevans-creator
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.