← 返回 Skills 市场
Panda Data Skill
作者
PandaAI-Tech
· GitHub ↗
· v3.0.0
· MIT-0
201
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install panda-data-skill
功能描述
PandaAI 金融数据 API 的 LLM Tool 封装多个数据查询方法,支持A股行情、A股基本面,期货,指数等
安全使用建议
This skill looks like a legitimate PandaAI data wrapper, but there are documentation/metadata mismatches you should resolve before installing. Specifically: SKILL.md and INSTALL_GUIDE require PANDA_DATA_USERNAME and PANDA_DATA_PASSWORD (sensitive credentials) and pip installation of panda_data / panda-data-tools, yet the registry metadata lists no required env vars. Before you proceed: 1) Confirm with the publisher (or PyPI project page) that the required env vars are correct and whether an API key/token alternative exists (prefer tokens over account passwords). 2) Inspect the panda_data and panda-data-tools PyPI packages and source repositories (verify maintainers, recent releases, and code) before running pip install. 3) If you must use credentials, create a least-privilege account (or limited/test account) and avoid sharing credentials in public chats. 4) Run the package in an isolated environment (virtualenv/container) and check network activity if you need higher assurance. 5) Ask the skill owner to update registry metadata to declare the required env vars (so the platform can surface the need for credentials). If you cannot verify the external packages or the publisher, treat this skill as higher risk and avoid supplying real credentials.
功能分析
Type: OpenClaw Skill
Name: panda-data-skill
Version: 3.0.0
The panda-data-skill bundle is a legitimate wrapper for the PandaAI financial data API, providing 61 tools for querying A-share market data, financial reports, and futures. The bundle includes a helper script (scripts/call_tool.py) for the agent to execute API calls and comprehensive documentation (SKILL.md, api_reference.md) for tool usage. It requires standard authentication via environment variables (PANDA_DATA_USERNAME/PASSWORD) and relies on external PyPI packages (panda_data and panda-data-tools). No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
The name/description (PandaAI financial data wrapper) match the SKILL.md and example code: the skill is a thin LLM-tool wrapper that requires the external panda_data / panda-data-tools Python packages. That is coherent. However, the skill docs require PANDA_DATA_USERNAME and PANDA_DATA_PASSWORD for API access while the registry metadata lists no required env vars or primary credential — this mismatch is unexpected and reduces trust.
Instruction Scope
SKILL.md and INSTALL_GUIDE explicitly instruct the agent/developer to initialize credentials from environment or `.env`, to install pip packages, and even suggest asking the assistant to help write env/config in OpenClaw. Those runtime actions involve handling sensitive secrets and creating/updating config files; the skill instructions reference reading environment and upward-searching `.env` files even though the skill metadata did not declare those env vars. The included script (scripts/call_tool.py) is simple and only calls CredentialManager.init_from_env() and ToolRegistry.call_tool(), which is expected.
Install Mechanism
There is no install spec in the registry (instruction-only skill). The docs require installing external PyPI packages (panda_data, panda-data-tools) — normal for this purpose but increases risk because the actual executable code lives in separately installed packages. Verify the PyPI packages and their source repositories before installation.
Credentials
The documentation requires two sensitive env vars (PANDA_DATA_USERNAME, PANDA_DATA_PASSWORD) which are proportional to the stated purpose (API authentication). The problem: the skill registry metadata does not declare these required env vars or a primary credential, so the skill package omits declaring it will need secrets. This mismatch is a red flag for oversight or misconfiguration and should be clarified.
Persistence & Privilege
always: false and no install-time steps that modify other skills or global agent settings are present. The skill does not request permanent presence or elevated platform privileges. Autonomous invocation (model-invocation enabled) is the platform default; combined with credentials it increases blast radius but this skill does not request 'always: true'.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install panda-data-skill - 安装完成后,直接呼叫该 Skill 的名称或使用
/panda-data-skill触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.0.0
Version 3.0.0
- 更新描述,强调支持A股行情/基本面、期货、指数等多种数据类型
- homepage 链接更新为 PyPI(https://pypi.org/project/panda-data-tools/)
- 新增安装说明:需分别安装 panda_data 和 panda-data-tools
- 简化并调整描述和安装引导,更突出 Skill 特性及工具集成要求
- 其余 API 工具、用法和内容保持一致
v2.0.0
**Major update with expanded API coverage and installation guidance.**
- API 方法列表扩展至 61 个,新增港股/美股、分红、增发、期货资金流等数据查询接口
- 新增 INSTALL_GUIDE.md,提供完整安装与环境配置说明
- 文档强调需通过 pip 安装 panda_data,可选本地 whl
- 说明信息更加完善细致,便于快速上手和排查问题
v1.0.0
Initial release of panda-data-skill.
- Provides 35 LLM-compatible financial data tools for market, fundamental, derivatives, and institutional data.
- Supports queries such as daily/minute market data, concept & industry constituents, margin, repurchase, block trades, financial reports, factors, trading calendar, and more.
- Requires environment variables for API credentials and a separate whl package install.
- Includes detailed method reference and code examples for easy integration.
元数据
常见问题
Panda Data Skill 是什么?
PandaAI 金融数据 API 的 LLM Tool 封装多个数据查询方法,支持A股行情、A股基本面,期货,指数等. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 201 次。
如何安装 Panda Data Skill?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install panda-data-skill」即可一键安装,无需额外配置。
Panda Data Skill 是免费的吗?
是的,Panda Data Skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Panda Data Skill 支持哪些平台?
Panda Data Skill 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 Panda Data Skill?
由 PandaAI-Tech(@pandaai-tech)开发并维护,当前版本 v3.0.0。
推荐 Skills