What is qibook-company-profile?

A Chinese-language lookup procedure for company registration details and links between companies and people, using the Qibook API. It can identify companies and look up items such as legal representatives, shareholders, executives, investments, and related businesses.

It is for checking a company's official identity, registration information, owners, executives, investments, or a person's associated companies and roles.

It helps answer common questions about who owns, runs, or is connected to a company without requiring you to know formal business-record terms.

qibook-company-profile — Skill for Claude Code by ChinaDaaS-Department

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add ChinaDaaS-Department/qibook-skills --skill qibook-company-profile

Clone the repo

git clone --depth 1 https://github.com/ChinaDaaS-Department/qibook-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chinadaas-department/qibook-skills/qibook-company-profile/github.svg)](https://agentmods.dev/skills/chinadaas-department/qibook-skills/qibook-company-profile)

Your own site

<a href="https://agentmods.dev/skills/chinadaas-department/qibook-skills/qibook-company-profile"><img src="https://agentmods.dev/badge/skills/chinadaas-department/qibook-skills/qibook-company-profile/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chinadaas-department/qibook-skills/qibook-company-profile"><img src="https://agentmods.dev/badge/skills/chinadaas-department/qibook-skills/qibook-company-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.01326
Opus 5.5	$0.00025	$0.00530
Sonnet 5.5	$0.00012	$0.00265
Haiku 4.5	$0.00006	$0.00133

Measured 2mo ago against content hash e4be63a60bc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qibook-company-profile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/__init__.py, scripts/base.py, scripts/combined_query.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

qibook-company-profile/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

查企业查老板

基于企百科 API，快速查询企业工商信息和人员关联信息，将结果转为中文 Markdown 后回答用户。

先理解用户想查什么（企业还是人、要哪些信息），再选择正确的查询路径，不要随意升级查询范围。

不适合深度企业分析（企业画像、信用评估、竞争力分析），这类需求应引导使用 qibook-company-wiki-deepresearch skill。

When to use

用户不说"工商"、"照面"这些术语也要触发。以下口语都属于本 skill 范围：

帮我查一下华为 / 美团的全称是什么 / XX 是哪家公司
XX 的法人是谁 / 注册资本多少 / 什么时候成立的
XX 的股东有哪些 / 高管是谁 / 对外投资 / 谁是大股东
XX 是谁开的 / 这家公司老板是谁
查一下张三 / 张三名下有几家公司 / 张三在 XX 公司担任什么
查张三在北京的情况

口语理解优先：

"查一下 XX 公司" → 主体识别，返回全称 + 信用代码
"XX 的老板" / "谁开的" → 查法人代表
"XX 名下有几家公司" → 查人员关联企业统计
"XX 的股东" → 查股东及出资信息

Environment check

调用前先校验 QIBOOK_ACCESS_KEY 和 QIBOOK_BASE_URL 环境变量是否存在。缺失则提示：

export QIBOOK_ACCESS_KEY=your_key
export QIBOOK_BASE_URL=your_url

不要等到跑失败才暴露环境问题。

功能路由

重要：根据用户意图选择正确的功能，不要随意升级查询范围。

1. 主体识别

触发： 用户给了企业简称/别名想知道全称，或只提到公司名没要求具体信息。

python3 -m scripts.combined_query --entmark "华为"

只返回企业全称 + 统一社会信用代码，不要额外展开。

2. 查企业详细信息

触发： 用户明确要查照面/股东/高管/对外投资等具体信息。

python3 -m scripts.combined_query --entmark "天津测试有限公司"

用户没指定模块 → 默认只返回照面，提示"还可以进一步查看股东、高管、对外投资"。

3. 查人

仅人名 → 人员统计汇总：

python3 -m scripts.combined_query --name "张三"

人名+省份 → 该省份下的统计：

python3 -m scripts.combined_query --name "张三" --province "天津"

人名+企业 → 担任法人、高管、投资详情：

python3 -m scripts.combined_query --entmark "天津测试有限公司" --name "张三"

路由判断

用户提问
  ├── 只提到公司名/简称，没要求具体信息 → 功能1（主体识别）
  ├── 明确要查照面/股东/高管/对外投资   → 功能2（查企业）
  ├── 提到人名，没提公司               → 功能3（查人汇总）
  ├── 提到人名+省份                    → 功能3（查人+省份）
  └── 提到人名+公司                    → 功能3（查人+企业详情）

回答规范

使用脚本返回的中文 Markdown 作为数据来源，不要暴露英文字段
数组数据（股东、高管等）用表格展示
空值字段脚本已自动过滤，无需额外处理
某模块数据为空 → 告知"暂无该项信息"
金额字段保留两位小数
查询为空时区分原因（名称不对 / 权限不足 / 网络异常），不要统一说"查询失败"

脚本说明

脚本	功能
`scripts/base.py`	API 认证、调用、字段映射(英→中)、空值过滤、Markdown 格式化
`scripts/combined_query.py`	三个功能的 fetch 函数，根据入参自动判断场景，返回 Markdown 字符串
`scripts/__init__.py`	统一入口，导出 fetch / fetch_entity_id / fetch_enterprise / fetch_person_summary / fetch_person_detail

Read the full file on GitHub · 151 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 151 lines · 62 tokens per session scan A e4be63a60bc0

Subscribe to this mod's changes

qibook-company-profile is a skill published in the GitHub repository ChinaDaaS-Department/qibook-skills (17 stars, last pushed 7mo ago), licensed MIT. It adds 62 tokens to every session and 1,326 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Research agent-skills claude-skills openclaw-skills skillsmp

qibook-company-profile next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
qibook-company-profileChinaDaaS-Department/qibook-skills	Skill	17	7mo ago	MIT	A	62	Claude Code
baoyu-youtube-transcriptJimLiu/baoyu-skills	Skill	27k	today	MIT	A	107	Claude Code
baoyu-comicJimLiu/baoyu-skills	Skill	27k	today	MIT	A	61	Claude Code
baoyu-diagramJimLiu/baoyu-skills	Skill	27k	today	MIT	A	133	Claude Code
baoyu-danger-gemini-webJimLiu/baoyu-skills	Skill	27k	today	MIT	A	74	Claude Code
vastai-sdkvast-ai/vast-cli	Skill	230	2d ago	MIT	A	26	Claude Code
diagram-designanbeime/skill	Skill	9.3k	today	none	A	211	Claude Code