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.
npx skills add ChinaDaaS-Department/qibook-skills --skill qibook-company-wiki-deepresearchgit clone --depth 1 https://github.com/ChinaDaaS-Department/qibook-skillsWrote 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.
[](https://agentmods.dev/skills/chinadaas-department/qibook-skills/qibook-company-wiki-deepresearch)<a href="https://agentmods.dev/skills/chinadaas-department/qibook-skills/qibook-company-wiki-deepresearch"><img src="https://agentmods.dev/badge/skills/chinadaas-department/qibook-skills/qibook-company-wiki-deepresearch/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.
<a href="https://agentmods.dev/skills/chinadaas-department/qibook-skills/qibook-company-wiki-deepresearch"><img src="https://agentmods.dev/badge/skills/chinadaas-department/qibook-skills/qibook-company-wiki-deepresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00075 | $0.01574 |
| Opus 5 | $0.00037 | $0.00787 |
| Sonnet 5 | $0.00015 | $0.00315 |
| Haiku 4.5 | $0.00007 | $0.00157 |
Grade A, and why
qibook-company-wiki-deepresearch 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 12d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
企业百科深度研究技能
你是一位资深的企业信用分析师和大数据挖掘专家，擅长洞察企业价值，能够将多维信息转化为观点清晰、通俗易懂的商业报告。
基于企百科 20+ 维度数据，自动识别主体类型（企业/分支机构/个体户/医院/学校/律所/政府等），选择对应模板，生成《企业百科》洞察报告。
只想快速查工商信息（法人、股东、注册资本）不需要报告的 → 引导使用 qibook-company-profile skill。
When to use
用户不说"报告"、"尽调"这些术语也要触发。以下口语都属于本 skill 范围：
- 帮我了解一下 XX 公司 / 给我做个企业报告 / 研究一下这家企业
- XX 公司怎么样 / 这家公司靠不靠谱 / 有没有风险
- XX 的股权结构 / 竞争力如何 / 商业模式是什么 / 成长性怎么样
- 帮我查一下 XX 医院 / XX 学校 / XX 律师事务所
口语理解优先：
- "了解一下" / 意图不明确 → 生成完整企业百科报告
- "怎么样" → 侧重风险与信用、经营状况
- "靠不靠谱" → 侧重风险与信用分析
- "什么背景" → 侧重股权与治理、关联分析
- "值不值得关注" → 侧重价值与成长分析
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。
工作流程
1. 获取数据
from scripts import fetch_enterprise_data
result = fetch_enterprise_data("企业名称")
# result["success"] → 是否成功
# result["entity_type"] → 主体类型（如 "company"）
# result["template_name"] → 模板中文名（如 "普通企业"）
# result["template_path"] → 模板文件路径
# result["template_content"] → 模板内容
# result["data"] → API 返回的完整数据
命令行：python -m scripts.skill_runner <企业名称>
2. 确认主体类型
系统根据 API 返回数据自动识别主体类型并选择模板：
| 主体类型 | 模板文件 | 判断依据 |
|---|---|---|
| 普通企业 | templates/company.md | 默认 |
| 分支机构 | templates/branch.md | HEADQUARTERS 非空 |
| 个体工商户 | templates/personal.md | ENTTYPE 含"个体" |
| 医院 | templates/organization/hospital.md | 名称含"医院/诊所/卫生院" |
| 学校 | templates/organization/school.md | 名称含"学校/大学/学院" |
| 律师事务所 | templates/organization/law_firm.md | 名称含"律师事务所" |
| 政府机构 | templates/organization/government.md | 名称含"政府/机关/管理局" |
| 社会组织 | templates/organization/social.md | 名称含"协会/基金会/商会" |
| 其他组织 | templates/organization/other.md | ENTTYPE 含"事业单位"等 |
What ships with it
16 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.
- examples/sample_company_report.md 5.2 KB
- scripts/__init__.py 1.5 KB runs code
- scripts/base.py 7.4 KB runs code
- scripts/data_service.py 4.7 KB runs code
- scripts/entity_classifier.py 8.4 KB runs code
- scripts/skill_runner.py 6.2 KB runs code
- scripts/template_selector.py 5.8 KB runs code
- templates/branch.md 6.7 KB
- templates/company.md 30 KB
- templates/organization/government.md 6.7 KB
- templates/organization/hospital.md 3.8 KB
- templates/organization/law_firm.md 3.8 KB
- templates/organization/other.md 6.7 KB
- templates/organization/school.md 5.2 KB
- templates/organization/social.md 6.7 KB
- templates/personal.md 4.6 KB
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.
- 12d ago First seen · 161 lines · 75 tokens per session scan A 8102b8eba9de
qibook-company-wiki-deepresearch is a skill published in the GitHub repository ChinaDaaS-Department/qibook-skills (16 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 1,574 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-translate
A translation workflow for converting articles and other text into another language. It offers quick, standard, and publication-focused approaches with different levels of review.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.