← 返回 Skills 市场
elijah-pi

China company search fengniao

作者 Elijah-Pi · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
143
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install china-company-search-fengniao
功能描述
China company search and business registry skill by Fengniao (Riskbird). Supports KYB, supplier verification, company due diligence, corporate risk screening...
使用说明 (SKILL.md)

China Company Search | Fengniao by Riskbird

Fengniao is a China company intelligence skill backed by Riskbird commercial data. It covers business registration, shareholders, executives, outbound investments, registry changes, and a full suite of risk signals — enforcement records, dishonest debtor lists, consumption restrictions, abnormal operations, serious violations, and administrative penalties.

Use discover to find the right data tool, call to retrieve structured data.

Setup: Works out of the box — no configuration needed. A built-in public API key is included. If you have a paid account, set FN_API_KEY as an environment variable and it will take priority. API credentials are passed via URL parameter apikey, not HTTP headers.

Quota: The built-in public key has a daily usage limit (200 calls). Check remaining quota at https://www.riskbird.com/skills. When the API returns code=9999 with a message containing "访问已达上限", the daily quota is exhausted — configure a private key or retry the next day.

Note on search: The fuzzy search endpoint only matches Chinese company names. If the user provides an English name or translation, convert it to the Chinese official name before calling biz_fuzzy_search.

Supported Data Dimensions

  • Company fuzzy search: Match by short name or full name, returns entid
  • Basic info: Legal rep, registered capital, incorporation date, unified social credit code, address, business scope, industry
  • Shareholders: Names, shareholding ratios, contribution amounts, types
  • Executives: Directors, supervisors, senior management, legal representative
  • Outbound investments: Portfolio companies with shareholding and status
  • Registry changes: Historical changes to legal rep, address, capital, etc.
  • Court enforcement (被执行人): Forced execution records
  • Dishonest debtors (失信被执行人): Blacklist records
  • Consumption restrictions (限制高消费): Court-ordered consumption bans
  • Abnormal operations (经营异常): Regulatory abnormal operation listings
  • Serious violations (严重违法): Serious illegal conduct records
  • Administrative penalties (行政处罚): Regulatory fines and penalties
  • Due diligence report: Structured report synthesizing all available dimensions

Current capabilities are defined in tools.json; field details in references/field_definitions_*.md.

Discovery Scope

This skill covers any China company search or risk check need. If a user asks about a dimension not yet supported (e.g., patents, tenders, job listings), still trigger this skill — but clearly state "this dimension is not yet supported" during execution. Do not fabricate results.

Usage Workflow

  1. Identify what dimension the user needs before searching for the company.
  2. Use discover to find the relevant tool (e.g., "shareholder structure", "administrative penalty").
  3. Confirm the tool exists, then call biz_fuzzy_search to get the entid.
  4. Entity disambiguation (required): If the company name is ambiguous or abbreviated, ask the user to confirm which company before proceeding. Never assume uniqueness.
  5. All dimension queries use entid — do not pass company names or credit codes directly.
  6. For multi-dimension requests (due diligence, risk screening), resolve the entity once and reuse the same entid.
  7. Person-to-company lookup: If the user provides a person's name (e.g., "what companies does Elon Musk own"), interpret it as "companies where this person is the legal representative." Clarify if there are multiple people with the same name.

Output Rules

  • Only show real data returned by the API — never fabricate
  • Do not expose entid to the user — it is an internal query ID
  • Always use the full official registered company name, not abbreviations
  • Clearly separate Fengniao structured data from any WebSearch supplementary content
  • If a dimension has no records, state "no records found" explicitly
  • If a dimension is not yet supported, state "not supported in the current version"

Error Recovery

  • code=9999, not quota-related: check if the built-in key is valid, or configure a private FN_API_KEY
  • code=9999 + "访问已达上限": daily public quota exhausted — use a private key or retry tomorrow
  • code=8888: usually invalid entid or params — re-fetch the company entity and retry
  • code=20000 + no records: this company has no records for this dimension
  • discover no match: try synonyms; if still no match, the dimension is not yet supported

Troubleshooting priority: API key / quota / network → entity resolution (entid) → update skill (openclaw skills update china-company-search-fengniao-en).

Quick Start

# 1. Discover tools by dimension
node scripts/tool.mjs discover "shareholder structure"

# 2. Fuzzy search for a company (must use Chinese name)
node scripts/tool.mjs call biz_fuzzy_search --params '{"key":"腾讯"}'

# 3. Query a dimension using entid
node scripts/tool.mjs call biz_shareholders --params '{"entid":"AerjZTfkSh0"}'
安全使用建议
This package appears to implement the advertised China company search functionality and only asks for one optional environment variable (FN_API_KEY). Before installing: (1) be aware a built-in public API key is hard-coded — usage will hit a shared daily quota and may be visible to the service operator; prefer setting your private FN_API_KEY if you have one. (2) The runtime client returns raw API responses (including internal entid values) but SKILL.md requires entid be hidden — ensure the agent or calling code will redact entid before showing output. (3) The skill instructs converting English names to Chinese but provides no automatic translation — expect fuzzy search failures if you pass English names. (4) Running the skill executes Node scripts (Node 18+); review code and test in a controlled environment. These mismatches are likely sloppy design rather than malicious, but they create a risk of accidental data exposure or unexpected quota usage — proceed only after addressing the redaction and key-management points.
能力评估
Purpose & Capability
Name/description match the included tools.json, reference docs, and client code: the package calls Riskbird/Fengniao endpoints for company search and risk dimensions. Declared capabilities (fuzzy search, B1–D11 etc.) align with the endpoints listed in tools.json and the reference field documents.
Instruction Scope
SKILL.md and SETUP.md instruct the agent to use discover/call and to avoid exposing internal entid. However, the runtime client.call() returns the raw API JSON (which includes entid and other internal IDs) — the code does not enforce the SKILL.md rule to redact entid. Also SKILL.md asks the agent to 'convert English names to Chinese' before using biz_fuzzy_search, but no translation step is implemented in the code. These are functional/instruction mismatches that could lead to unintended data exposure or incorrect queries.
Install Mechanism
No install spec is present; the package is instruction+scripts only. Code is plain JS (Node 18+). There are no remote downloads or archive extracts. Risk from installation is low, but the runtime will execute bundled Node code if the agent runs it.
Credentials
Only one optional env var (FN_API_KEY) is referenced. The package contains a hard-coded built-in public API key (BUILTIN_KEY) used as fallback; this matches SKILL.md. Hardcoding a public key is not necessarily malicious but means requests will run under a shared key (quota, tracking). The client sends credentials as a URL parameter (apikey), which is consistent with the docs but can be observable in logs/refs — worth noting.
Persistence & Privilege
Registry flags show no always:true, and the skill is user-invocable with normal autonomous invocation allowed. The skill does not request to modify other skills, system config, or persist its own settings beyond reading environment and package files.
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 china-company-search-fengniao
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /china-company-search-fengniao 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
v1.0.0
Initial release of China Company Search | Fengniao by Riskbird - Provides China company search and business registry lookup, including KYB, risk screening, due diligence, and supplier verification. - Retrieves core information: business registration, shareholders, executives, outbound investments, legal issues, administrative penalties, and more. - Supports fuzzy name search (Chinese only), structured due diligence reports, and full compliance checks using public or private API keys. - Includes detailed usage, error handling, and dimension coverage guidelines. - Designed for onboarding, compliance, and risk checks of Chinese counterparties.
元数据
Slug china-company-search-fengniao
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

China company search fengniao 是什么?

China company search and business registry skill by Fengniao (Riskbird). Supports KYB, supplier verification, company due diligence, corporate risk screening... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 143 次。

如何安装 China company search fengniao?

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

China company search fengniao 是免费的吗?

是的,China company search fengniao 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

China company search fengniao 支持哪些平台?

China company search fengniao 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 China company search fengniao?

由 Elijah-Pi(@elijah-pi)开发并维护,当前版本 v1.0.0。

💬 留言讨论