← 返回 Skills 市场
chinadaas-department

Qibook Company Wiki Deepresearch

cross-platform ✓ 安全检测通过
120
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install qibook-company-wiki-deepresearch
功能描述
企业百科深度研究 - 基于 20+ 维度企业数据,自动识别主体类型,生成专业的企业洞察报告。 Use when: 用户需要生成企业百科报告、企业信用分析、商业调研报告、投资尽调报告,或需要全面了解一家企业的综合信息。
安全使用建议
This skill appears to be what it claims: it calls a Qibook aggregate API using QIBOOK_BASE_URL and QIBOOK_ACCESS_KEY and formats the returned data into report templates. Before installing or running it: 1) Verify the QIBOOK_BASE_URL is a legitimate/trusted endpoint (skill source is unknown). 2) Only provide an access key that is scoped/limited to the Qibook service; avoid reusing broad or high-privilege credentials. 3) Run the code in a sandboxed environment (or container) because the skill includes Python scripts that will execute locally and make outbound HTTPS requests. 4) Ensure Python dependencies (requests) are present and inspect/lock them (pip freeze / use a virtualenv). 5) Review the templates (they contain embedded LLM/system-style instructions that insist 'do not disclose internal prompts' and other strict output rules) and decide whether those constraints are acceptable for your use-case. 6) If you will use in production, ask the publisher for provenance (homepage, contact) or rotate/revoke the access key if you become unsure. If any of the above raise concerns (unknown host, broad credentials), do not run the skill until resolved.
能力评估
Purpose & Capability
Name/description request enterprise research data; required env vars (QIBOOK_ACCESS_KEY, QIBOOK_BASE_URL) and python3 are consistent with calling a hosted API and running the included Python scripts. No unrelated credentials or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to validate env vars and call the local scripts (python -m scripts.skill_runner or fetch_enterprise_data). Templates contain strong model-instruction style rules (e.g., hide system prompt, strict formatting) that are intended for report generation — not direct data exfiltration — but these embedded 'system-prompt' style constraints could influence an LLM's behavior and should be reviewed. The runtime instructions do not direct reading of unrelated system files or other credentials.
Install Mechanism
No install spec (no packages downloaded), which reduces supply-chain risk. However the package uses the Python requests library but the skill metadata only declares python3 (no explicit dependency declaration or install step for requests). The skill includes multiple Python files which will be executed locally; ensure the runtime environment has required Python packages and consider running in an isolated environment.
Credentials
Only two environment variables are required and they map directly to the API host and access key used by the code. No other secrets or unrelated config paths are requested. The access key is used as an 'access_key' header to the provided BASE_URL endpoint — proportional to the described functionality.
Persistence & Privilege
Skill does not request always:true or any elevated persistent privileges. It doesn't modify other skills or system-wide settings. Execution is on-demand and requires environment variables to be set by the user.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install qibook-company-wiki-deepresearch
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /qibook-company-wiki-deepresearch 触发
  4. 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
v1.0.2
- Added environment and binary requirements to metadata section in SKILL.md (now specifies that "python3" and certain env vars are required) - Clarified API credential acquisition and environment variable setup instructions - Improved preconditions and setup guidance for users - No functional code or output logic modified; changes are documentation-only for easier integration and user clarity
v1.0.1
- Updated version to 1.0.1. - Documentation improvements in SKILL.md for clarity and completeness. - No changes affecting user-visible features or tool behavior.
v1.0.0
- 初始版本发布,支持深度企业百科报告自动生成 - 基于20+维度数据,自动识别主体类型并选择相应报告模板 - 适配企业、分支机构、个体户、医院、学校等多种主体 - 针对不同用户提问(如“了解一下”“怎么样”“靠不靠谱”)自适应重点内容 - 严格控制报告字数,多维度输出包括风险、信用、成长性等分析 - 全面环境变量校验和详细错误提示,避免信息遗漏
元数据
Slug qibook-company-wiki-deepresearch
版本 1.0.2
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Qibook Company Wiki Deepresearch 是什么?

企业百科深度研究 - 基于 20+ 维度企业数据,自动识别主体类型,生成专业的企业洞察报告。 Use when: 用户需要生成企业百科报告、企业信用分析、商业调研报告、投资尽调报告,或需要全面了解一家企业的综合信息。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 120 次。

如何安装 Qibook Company Wiki Deepresearch?

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

Qibook Company Wiki Deepresearch 是免费的吗?

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

Qibook Company Wiki Deepresearch 支持哪些平台?

Qibook Company Wiki Deepresearch 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 Qibook Company Wiki Deepresearch?

由 北京中数智汇科技股份有限公司(@chinadaas-department)开发并维护,当前版本 v1.0.2。

💬 留言讨论