Personal Broker logo

Personal Broker

Community
evanslyhan
personal-broker

Smart Resale Agent hub. Orchestrates the complete 7-step C2C resale workflow. Use when user wants to sell second-hand items, list goods on resale platforms (Xianyu/闲鱼, Zhuanzhuan/转转, eBay, Depop), needs price research, or says "sell this", "list this", "help me resell", "I want to sell", "我要卖", "闲置出售". This hub chains 7 sub-skills into a complete conversational resale pipeline.

Overview

Publisherevanslyhan
Repositoryresale-agent-skill-hub
Skill namepersonal-broker
Stars
97
Forks
11
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by evanslyhan on GitHub. Read the source before you install it.

Installation

Install the Personal Broker AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/evanslyhan/resale-agent-skill-hub/tree/main/skills/personal-broker
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/evanslyhan/resale-agent-skill-hub.git /tmp/resale-agent-skill-hub
mkdir -p .claude/skills
cp -r /tmp/resale-agent-skill-hub/skills/personal-broker .claude/skills/personal-broker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Personal Broker in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Personal Broker on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Personal Broker is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Smart Resale Agent — Hub

Orchestrates the complete C2C resale workflow: photo recognition → price research → platform auth → listing card & publish → schedule + fuse → auto-delist on sale.

Two Modes

Mode A: MCP Server (v2, recommended for non-Claude-Code clients)

Use broker_core/mcp_server.py — a standard MCP server exposing 7 tools. Any MCP-compatible client (Claude Desktop, Cursor, VS Code) can connect.

Mode B: Claude Code Skills (v1, still supported)

Use the 7 /broker-* slash commands within Claude Code CLI.

For MCP Mode

Load guardrails/Omni-Agent-Guardrails.yaml as the system prompt. This enforces:

  • Tool Routing: Step 1→2→3→4→5 forced order
  • Shield Protocol: blocked=true → all actions cancelled
  • Transparency Schema: Every output carries audit:// reference

MCP tool mapping:

cognitive_intake       → broker-recognize
generate_xai_pricing   → broker-price
fuse_gatekeeper         → broker-fuse (MANDATORY GATE)
execute_platform_action → broker-card + broker-delist
audit_trail_query       → audit_logger
schedule_repricing      → broker-schedule
platform_auth_trigger   → broker-auth

Prerequisites

ANTHROPIC_API_KEY must be set. broker-recognize (Step 1) requires Claude Vision API to analyze product photos. Without this key, photo recognition will fail.

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

7-Skill Pipeline

📷 broker-recognize  →  Photo → structured product info
🔐 broker-auth       →  Bind platform accounts (login once, session persisted)
🔍 broker-price      →  Authenticated price search across platforms
🛡️ broker-fuse       →  ⚠️ GLOBAL INTERCEPTOR — set fuse BEFORE publish/schedule
📋 broker-card       →  Listing card preview → user confirmation → auto-publish
⏰ broker-schedule   →  Set repricing interval → register cron/launchd
✅ broker-delist     →  Auto-detect sale → delist all platforms

broker-fuse is NOT step 6. It is a mandatory interceptor/gate. Before broker-card can publish and before broker-schedule can auto-reprice, broker-fuse MUST be called and set. Every publish and repricing action validates against the fuse.

Orchestration Rules

When user wants to sell (full flow)

Guide the user through skills in this order: recognize → auth → price → fuse → card → schedule. Fuse is set as a gate BEFORE card publishing. Schedule is configured during the card conversation before publishing.

Flow control

  1. Call broker-recognize — user uploads photo, AI extracts product info. User confirms.
  2. Call broker-auth — open browser for each platform user wants to list on. Sessions persist automatically.
  3. Call broker-price — search all bound platforms using stored sessions. Present transparency report. User confirms recommended price.
  4. MANDATORY GATE: Call broker-fuse — set unbreachable floor price. This is NOT optional. No publishing or repricing may proceed without a fuse set.
  5. Call broker-card — generate listing cards. Script validates fuse before publish. Ask user to set repricing interval (default 7 days). User reviews card → says "发布" → script checks fuse → auto-publishes.
  6. broker-schedule registers the cron/launchd task. Daily repricing also validates against fuse. Done automatically after publish.
  7. broker-delist triggers when: (a) user says "卖了", or (b) daily scheduler detects item sold on a platform.

Standalone usage

Each sub-skill can be invoked independently:

  • /broker-recognize — just analyze a product photo
  • /broker-price — just research prices for a described item
  • /broker-fuse — adjust an existing fuse
  • /broker-delist — manually trigger delisting
  • /broker-schedule — change repricing interval

Cross-skill data passing

Skills communicate via ~/.broker/listings.json (state_manager) and conversation context. The item_id links everything.

Frequently asked questions

What does the Personal Broker AI skill do?

Smart Resale Agent hub. Orchestrates the complete 7-step C2C resale workflow. Use when user wants to sell second-hand items, list goods on resale platforms (Xianyu/闲鱼, Zhuanzhuan/转转, eBay, Depop), needs price research, or says "sell this", "list this", "help me resell", "I want to sell", "我要卖", "闲置出售". This hub chains 7 sub-skills into a complete conversational resale pipeline.

Why use Personal Broker on TypingMind?

Because you install it once and use it with any model. Personal Broker is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Personal Broker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/evanslyhan/resale-agent-skill-hub/tree/main/skills/personal-broker. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Personal Broker?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Personal Broker?

As many as you like. As long as a model supports skills, you can use Personal Broker with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Personal Broker AI skill free?

Yes. It is published on GitHub by evanslyhan under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇