← 返回 Skills 市场
Our world in data
作者
rachmann-alexander
· GitHub ↗
· v0.1.3
732
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install owid-oc
功能描述
searches, retrieves, and summarizes content from Our World in Data using the `owid-catalog` Python module. Developed under Ubuntu. The developer would apprec...
安全使用建议
This skill is coherent but you should: (1) install the owid-catalog package in a controlled environment (use a virtualenv or sandbox), because SKILL.md asks you to pip-install a pre-release version (1.0.0rc2) from PyPI; (2) review the package on PyPI/GitHub to confirm authorship and readme/changelog before trusting it; (3) ensure the runtime has pip/network access and that installing third-party packages is acceptable in your environment; (4) be aware the skill will query OWID's public API (subject to rate limits) and will return translated summaries if requested — verify translations for fidelity; and (5) if you require higher assurance, ask for a stable release (non-rc) or a pinned commit/OSS source link before installing.
功能分析
Type: OpenClaw Skill
Name: owid-oc
Version: 0.1.3
The skill bundle is designed to interact with Our World in Data using the `owid-catalog` Python module. All instructions in `SKILL.md` are focused on the stated purpose of searching, retrieving, and summarizing data, with clear guidance for the AI agent on transparency and post-processing. There is no evidence of malicious intent, data exfiltration, unauthorized execution, persistence mechanisms, or prompt injection attempts against the agent. The use of a release candidate version (`1.0.0rc2`) for the `owid-catalog` dependency is noted but does not indicate malice.
能力评估
Purpose & Capability
The name/description match the SKILL.md: it documents use of the owid-catalog Python module to search, fetch, and summarize Our World in Data charts. No unrelated environment variables, binaries, or config paths are requested, and the actions described (search, fetch, summarize, include URL) are proportional to the stated purpose.
Instruction Scope
SKILL.md contains concrete Python usage (client.charts.search, fetch, produce structured JSON) and error handling. It does not instruct the agent to read arbitrary files, access unrelated credentials, or exfiltrate data to unexpected endpoints. It does require searching in English and post-processing translations, and mandates disclosure of OWID as the source.
Install Mechanism
There is no formal install spec in the registry, but the SKILL.md recommends running `pip install owid-catalog==1.0.0rc2`. This is a PyPI pre-release version (rc), which is moderate risk compared with stable releases: it requires network access and will write packages to disk. The skill does not declare that pip is required in metadata, so the environment may need pip/virtualenv to be present or an operator should install the package in a controlled environment.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate — fetching public OWID data does not require secrets.
Persistence & Privilege
The skill is not marked always:true and does not request persistent elevated privileges or to modify other skills or system-wide agent settings. Normal autonomous invocation (disable-model-invocation:false) is the platform default and not a red flag here.
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 owid-oc - 安装完成后，直接呼叫该 Skill 的名称或使用
/owid-oc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
v0.1.3
- Removed requirement to check and announce newer owid-catalog versions on each invocation.
- Updated documentation to no longer instruct users to notify about newer owid-catalog releases.
- No functional or code changes; content transparency and attribution practices remain.
- Version updated from 0.1.2 to 0.1.3.
v0.1.2
- Updated skill name and functionality from Wikipedia (wikipedia-oc) to Our World in Data (owid-oc), now using the owid-catalog Python module.
- Replaced SKILL.md file content to reflect searching, retrieving, and summarizing data from OWID charts instead of Wikipedia articles.
- Added installation, version-checking, and client initialization instructions for owid-catalog.
- Detailed new search, retrieval, error handling, and structured output practices for OWID chart data.
- Outlined new language policy and post-processing requirements for OWID content.
- Removed all Wikipedia-related documentation and replaced it with corresponding OWID guidance.
v0.1.4
- Skill renamed from "owid-oc" (Our World in Data) to "wikipedia-oc" (English Wikipedia).
- Now searches, retrieves, and summarizes content from English Wikipedia using the `wikipedia` Python module instead of OWID data.
- Version updated to 0.1.4.
- All searches explicitly performed in English Wikipedia for consistency.
- Skill usage disclosure and update notification best practices added.
- Example code and error handling revised for Wikipedia queries.
v0.1.0
- Initial release of the OWID-OC skill for retrieving and summarizing content from Our World in Data using the `owid-catalog` Python module.
- Supports chart search, selection, data retrieval, and structured summary output.
- Includes guidance for error handling and recommended best practices.
- Encourages searches in English and post-processing translation to the user's language when necessary.
- Mandates transparency by always attributing information to OWID (Our World in Data).
- Provides installation, initialization, and example workflow instructions.
元数据
常见问题
Our world in data 是什么？
searches, retrieves, and summarizes content from Our World in Data using the `owid-catalog` Python module. Developed under Ubuntu. The developer would apprec... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 732 次。
如何安装 Our world in data？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install owid-oc」即可一键安装，无需额外配置。
Our world in data 是免费的吗？
是的，Our world in data 完全免费（开源免费），可自由下载、安装和使用。
Our world in data 支持哪些平台？
Our world in data 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 Our world in data？
由 rachmann-alexander（@rachmann-alexander）开发并维护，当前版本 v0.1.3。
推荐 Skills