功能描述

Longbridge platform expert for investment analysis AND developer tasks. TRIGGER on ANY of: (1) any stock/market analysis request in any language — price perf...

使用说明 (SKILL.md)

Longbridge Developers Platform

Name: Longbridge
Author: huacnlee

Full-stack financial data and trading platform: CLI, Python/Rust SDK, MCP, and LLM integration.

Official docs: https://open.longbridge.com llms.txt: https://open.longbridge.com/llms.txt

For setup and authentication details, see references/setup.md.

Investment Analysis Workflow

When the user asks about stock performance, portfolio advice, or market analysis:

Get live data via CLI — quotes, positions, K-line history, intraday
Get news/catalysts via CLI — prefer Longbridge first; fall back to WebSearch only if insufficient
Combine — price action + volume + catalyst → analysis + suggestion

# Market data
longbridge quote SYMBOL.US
longbridge positions                # always pull when user asks about "my portfolio"
longbridge kline-history SYMBOL.US --start YYYY-MM-DD --end YYYY-MM-DD --period day
longbridge intraday SYMBOL.US

# News & content (prefer these over WebSearch)
longbridge news SYMBOL.US           # latest news articles
longbridge news-detail \x3Cid>         # full article content
longbridge filing-detail \x3Cid>       # regulatory filing (earnings reports, etc.)
longbridge topics SYMBOL.US         # community discussion
longbridge market-temp              # market sentiment index (0–100)

Only fall back to WebSearch when Longbridge news is insufficient (e.g., breaking news not yet indexed, macro events unrelated to a specific symbol).

Choose the Right Tool

User wants to...                         → Use
─────────────────────────────────────────────────────────────────
Quick quote / one-off data lookup        CLI
Interactive terminal workflows           CLI
Script market data, save to file         CLI + jq  (or Python SDK)
Loops, conditions, transformations       Python SDK (sync)
Async pipelines, concurrent fetches      Python SDK (async)
Production service, high throughput      Rust SDK
Real-time WebSocket subscription loop    SDK (Python or Rust)
Programmatic order strategy              SDK
Talk to AI about stocks (no code)        MCP (hosted or self-hosted)
Use Cursor/Claude for trading analysis   MCP
Add Longbridge API docs to IDE/RAG       LLMs.txt / Markdown API

Symbol Format

\x3CCODE>.\x3CMARKET> — applies to all tools.

Market	Suffix	Examples
Hong Kong	`HK`	`700.HK`, `9988.HK`, `2318.HK`
United States	`US`	`TSLA.US`, `AAPL.US`, `NVDA.US`
China Shanghai	`SH`	`600519.SH`, `000001.SH`
China Shenzhen	`SZ`	`000568.SZ`, `300750.SZ`
Singapore	`SG`	`D05.SG`, `U11.SG`
Crypto	`HAS`	`BTCUSD.HAS`, `ETHUSD.HAS`

Reference Files

CLI (Terminal)

Overview — install, auth, output formats, patterns: references/cli/overview.md

Always use longbridge --help to list available commands, and longbridge \x3Ccommand> --help for specific options and flags. Do not rely on hardcoded documentation — the CLI's built-in help is always up-to-date.

Python SDK

Overview — install, Config, auth, HttpClient: references/python-sdk/overview.md
QuoteContext — all quote methods + subscriptions: references/python-sdk/quote-context.md
TradeContext — orders, account, executions: references/python-sdk/trade-context.md
Types & Enums — Period, OrderType, SubType, push types: references/python-sdk/types.md

Rust SDK

Overview — Cargo.toml, Config, auth, error handling: references/rust-sdk/overview.md
QuoteContext — all methods, SubFlags, PushEvent: references/rust-sdk/quote-context.md
TradeContext — orders, SubmitOrderOptions builder, account: references/rust-sdk/trade-context.md
Content — news, filings, topics (ContentContext + Python fallback): references/rust-sdk/content.md
Types & Enums — all Rust enums and structs: references/rust-sdk/types.md

AI Integration

MCP — hosted service, self-hosted server, setup & auth: references/mcp.md
LLMs & Markdown — llms.txt, open.longbridge.com doc Markdown, longbridge.com live news/quote pages (.md suffix + Accept header), Cursor/IDE integration: references/llm.md

Load specific reference files on demand — do not load all at once.

安全使用建议

This skill appears to be genuine Longbridge documentation packaged to help an AI use the Longbridge CLI/SDK/MCP, but it can access and act on highly sensitive account functionality if you connect an account. Before installing or enabling: (1) Only connect Longbridge OAuth with the minimum scopes (prefer read-only) and require explicit confirmations for any order placement; (2) review and control triggers — the skill requests activation on any ticker/portfolio mention which may cause unintended calls; (3) do not run curl | sh install scripts blindly — prefer Homebrew or inspect the script first; (4) be aware the docs mention token cache paths (~/.longbridge/...), so the agent could try to use or read local tokens if present; (5) if you do not want the agent to place trades, avoid granting trade scopes or self-host MCP with restricted tools. These precautions will reduce the risk of accidental data exposure or unintended trading actions.

功能分析

Type: OpenClaw Skill Name: longbridge-developers Version: 1.0.0 The bundle provides extensive integration with the Longbridge financial platform, enabling an AI agent to perform market analysis and execute trades via CLI, SDKs, and MCP. It includes high-risk capabilities such as shell command execution (longbridge CLI), financial transaction management, and local storage of OAuth tokens in ~/.longbridge/. While these actions are aligned with the skill's stated purpose, the broad access to financial accounts and the use of a 'curl | sh' installation script in references/cli/overview.md meet the criteria for a suspicious classification due to the inherent risks of the provided tools.

能力评估

✓ Purpose & Capability

Name, description and included reference docs (CLI, Python/Rust SDKs, MCP) match the stated purpose of being a Longbridge platform expert for investment analysis and developer tasks. The files provide expected SDK/CLI usage and trading examples.

⚠ Instruction Scope

The runtime instructions tell the agent to execute CLI/SDK commands that access account positions, news, and can place orders. The docs explicitly say to always pull positions when users ask about portfolios and include order placement examples. The references also disclose local token cache paths (~/.longbridge/...) and recommend connecting MCP which 'exposes tools to the AI' — this gives an agent access to sensitive account actions if OAuth is authorized. The SKILL.md does not explicitly constrain the agent from reading local token files or auto-executing orders, so the instruction scope is broader than a read-only analysis skill.

ℹ Install Mechanism

This is an instruction-only skill (no install spec), which is lower risk. However the bundled docs recommend installing the CLI with Homebrew (fine) or via a remote install script piped from GitHub raw (curl ... | sh). That install method (download-and-execute) carries higher risk in general and should be validated by the user before running.

⚠ Credentials

The skill declares no required env vars or credentials, which is reasonable because Longbridge uses OAuth, but multiple reference files reveal token cache paths and environment variables (LONGBRIDGE_*). The skill's functionality (view positions, place orders, subscribe to push events) legitimately requires account OAuth tokens — access to these is highly sensitive. The skill does not request explicit read-only scope limits, so enabling it could permit trading-capable actions if OAuth consent is granted.

ℹ Persistence & Privilege

always:false and no install spec are good. However the SKILL.md author recommends broad trigger conditions (TRIGGER on ANY ticker/portfolio mention) and MCP integration that 'automatically exposes tools to the AI'. Combined with default autonomous invocation, this creates a higher blast radius: an agent could be triggered frequently and may be able to call trade APIs if the user authorizes OAuth. This is not inherently malicious but increases risk and should be constrained by the user (scopes, confirmation rules).

版本历史

v1.0.0

Initial release of the Longbridge Developers skill. - Provides comprehensive support for Longbridge CLI, Python/Rust SDKs, MCP server, and LLM integration. - Handles stock/market analysis, live data retrieval, news/catalyst aggregation, and portfolio queries for HK, US, CN, SG, and Crypto markets. - Includes workflow guidance for investment analysis and developer tasks with tool selection recommendations. - Offers symbol format reference and links to detailed documentation for CLI and SDK usage. - Enables integration with AI agents and LLMs using official docs and reference files.

元数据

Slug longbridge-developers

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题

Longbridge 是什么？

Longbridge platform expert for investment analysis AND developer tasks. TRIGGER on ANY of: (1) any stock/market analysis request in any language — price perf... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 149 次。

如何安装 Longbridge？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install longbridge-developers」即可一键安装，无需额外配置。

Longbridge 是免费的吗？

是的，Longbridge 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Longbridge 支持哪些平台？

Longbridge 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Longbridge？

由 Jason Lee（@huacnlee）开发并维护，当前版本 v1.0.0。

Longbridge