← 返回 Skills 市场
2008
总下载
2
收藏
7
当前安装
32
版本数
在 OpenClaw 中安装
/install stocks
功能描述
56+ financial data tools via Yahoo Finance. Auto-routes stock prices, fundamentals, earnings, dividends, options, crypto, forex, commodities, news, and more.
安全使用建议
What to consider before installing:
- Verify upstream: SKILL metadata omitted a homepage, but the script header references a GitHub repo; visit and inspect that repository to confirm provenance and check recent commits/issues.
- Inspect the full scripts/yfinance_ai.py file yourself (or have a trusted reviewer do so) before running — the truncated preview looked consistent with yfinance usage but full inspection will reveal any unexpected network endpoints or data handling.
- Install inside an isolated virtual environment (as the SKILL.md recommends) and do not run as root.
- Be aware pip will pull packages from PyPI (yfinance, pandas, pydantic, requests); if you have policies about third-party packages, review those packages' reputations or pin versions.
- Adding the invocation snippet to a global TOOLS.md (or otherwise giving the agent persistent access) makes the skill easier to use but also means the agent can call it more readily; only add if you trust the skill and the agent's permissions.
- If you need higher assurance, run the skill in an isolated environment/network and use network monitoring the first time to confirm it only talks to expected endpoints (Yahoo Finance / yfinance-related endpoints).
功能分析
Type: OpenClaw Skill
Name: stocks
Version: 4.1.8
The OpenClaw Stocks skill is benign. Its purpose is to provide financial data via Yahoo Finance, which is consistently reflected across all files. The `SKILL.md` provides clear, standard instructions for the AI agent to execute the `yfinance_ai.py` script using a virtual environment and Python's `-c` flag, which is a robust method against shell injection. The core `yfinance_ai.py` script uses `pydantic` for input validation (e.g., `TickerValidator`, `PeriodValidator`) and a `safe_ticker_call` decorator to sanitize user-provided parameters before interacting with the `yfinance` library. There is no evidence of malicious intent, data exfiltration, persistence mechanisms, or unauthorized network activity; all network calls are to Yahoo Finance as expected. The `__event_emitter__` is a standard OpenClaw mechanism for status updates, not a malicious channel.
能力评估
Purpose & Capability
Name/description (56+ Yahoo Finance tools) aligns with the provided code and SKILL.md. The included script imports yfinance, pandas, pydantic, and requests — all expected. Small inconsistency: registry metadata lists source/homepage as 'unknown'/'none' while the script header includes a repository URL and author info; this is explainable but worth verifying.
Instruction Scope
SKILL.md instructions are narrowly scoped to creating a virtualenv, installing requirements, and running the library's async functions. It does not direct the agent to read unrelated system files, harvest credentials, or post data to unexpected endpoints. It does encourage adding invocation templates into the agent's TOOLS.md so the agent can call functions — that is expected for tool integration but gives the agent a persistent way to invoke the skill if the user chooses to add it.
Install Mechanism
No platform install spec; installation is via a local virtualenv and pip install -r requirements.txt (PyPI packages). This is normal for a Python skill but carries the usual risks of pulling third-party packages from PyPI. No downloads from arbitrary URLs or archive extraction were specified.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The libraries used operate without secrets for public market data, so the lack of requested secrets is appropriate.
Persistence & Privilege
Skill flags are default (always: false, agent-invocable: true, model invocation allowed) which is normal. SKILL.md recommends injecting invocation patterns into the agent's TOOLS.md so the agent can call functions reliably — this is optional but would make the skill easy to invoke repeatedly. If you allow autonomous agent actions, consider whether you want that agent to call these methods without explicit confirmation.
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 stocks - 安装完成后，直接呼叫该 Skill 的名称或使用
/stocks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
v4.1.8
- Added open-source and OpenWebUI availability info, including a link to the GitHub repository.
- No changes to features or function signatures.
- No impact on core logic; this is a documentation update only.
- Cleaned up files a bit.
v4.1.7
- Added open-source and OpenWebUI availability info, including a link to the GitHub repository.
- No changes to features or function signatures.
- No impact on core logic; this is a documentation update only.
- Cleaned up files a bit.
v4.1.6
- Improved documentation for Python virtual environment usage, emphasizing the need to use the venv’s Python interpreter and correct pip installation for dependencies.
- Added guidance to avoid `ModuleNotFoundError` by not relying on system Python and always using the skill’s dedicated venv path.
- New example shell snippet demonstrates robust command execution using absolute venv paths.
- Added a new helper script: `scripts/retry_msft_ratios.py`.
v4.1.5
- Added reliability notes for shell quoting and Python command execution in SKILL.md, including here-doc and script-based invocation tips.
- New script scripts/retry_unh_ratios.py was added.
- Improved setup and usage documentation to help avoid common shell and virtual environment pitfalls.
v4.1.4
- Removed the file references/REFERENCE.md.
- No changes to functionality or documentation other than cleanup.
v4.1.3
- Expanded and clarified documentation in references and skill metadata.
- No changes to user-facing features or functionality.
- Internal improvements to yfinance_ai.py for maintainability.
v4.1.2
- Renamed skill to "stocks" and updated description for clarity and brevity.
- Removed TOOLS.md and scripts/__init__.py files for cleanup.
- SKILL.md is now shorter and has a more concise description line.
- Functionality and usage instructions remain unchanged.
v4.1.1
- Added TOOLS.md file to provide standalone documentation or usage patterns for skill tools.
- Added scripts/__init__.py to initialize the scripts module.
v4.1.0
- Fixed the Agent Quick-Start bash example to correctly invoke the async main function.
- No other functionality changes; documentation clarity improved.
v4.0.9
- Improved the agent invocation code example for clarity and robustness in the Agent Quick-Start section.
- Wrapped the async function call in a main guard (`if __name__ == '__main__':`) to ensure proper execution.
- No changes to logic, features, or function signatures. Documentation update only.
v4.0.8
- Expanded the skill description to highlight real-time data access, broader market coverage, and depth of tools available.
- Updated the `name` and `description` fields for greater clarity on capabilities (SKILL.md).
- No changes to code or function signatures—documentation only.
v4.0.7
Added YAML frontmatter, improved SKILL.md for OS-agnostic one-shot reliability, KISS cleanup
v4.0.5
- Updated documentation in SKILL.md for improved clarity and structure.
- Separated instructions for AI agents and human users into dedicated sections.
- Provided more general and adaptable guidance for command-line usage, emphasizing reference to local configuration (skill.json) instead of hardcoded example paths.
- Streamlined example commands to make them easier to adapt to various environments.
- Clarified available functions and where to find the full, up-to-date list.
v4.0.4
- Added prerequisite note for agents: the virtual environment path from skill.json must be set up and accessible.
- Clarified that invocation examples use paths dependent on skill.json and may need adjustment based on your environment.
- No functional or interface changes; documentation improved for easier integration and usage by developers.
v4.0.3
No changes detected in this version.
- No updates or modifications were made to the skill or its documentation.
v4.0.2
Version 4.0.2 — No file changes detected.
- No updates or modifications were made in this version.
- All features and functionality remain unchanged from the previous release.
v4.0.1
**Summary:** Major documentation rewrite for clarity and ease-of-use, now with distinct guidance for both AI agents and human users.
- Simplified and reorganized the SKILL.md, splitting instructions for AI agents and human users.
- Added concise "how to use" sections with clear command examples.
- Streamlined function list, providing triggers and example calls for core tools.
- Improved onboarding, feature highlights, and answered common user questions.
- Updated formatting for readability, removed redundant technical details, and clarified usage patterns.
v4.0.0
v4.0.0: Added AI invocation guide to SKILL.md (async pattern from skill.json), moved links above install note, corrected wrong CLI-arg invocation instructions
v3.1.6
Version 3.1.6
- Documentation cleanup: redundant section listing links at the top of SKILL.md has been removed.
- No code or functional changes; skill operation remains the same.
v3.1.5
Reorder: move links to top of SKILL.md and remove bottom links; keep stocks data
元数据
常见问题
Stocks and Financial Data Pull 是什么？
56+ financial data tools via Yahoo Finance. Auto-routes stock prices, fundamentals, earnings, dividends, options, crypto, forex, commodities, news, and more. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2008 次。
如何安装 Stocks and Financial Data Pull？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install stocks」即可一键安装，无需额外配置。
Stocks and Financial Data Pull 是免费的吗？
是的，Stocks and Financial Data Pull 完全免费（开源免费），可自由下载、安装和使用。
Stocks and Financial Data Pull 支持哪些平台？
Stocks and Financial Data Pull 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 Stocks and Financial Data Pull？
由 lkcair（@lkcair）开发并维护，当前版本 v4.1.8。
推荐 Skills