Best use case
company-scan is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
企业扫描助手：快速筛选出符合特定条件的企业并返回结构化列表。
Teams using company-scan should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/company-scan-iyiou/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How company-scan Compares
| Feature / Agent | company-scan | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
企业扫描助手：快速筛选出符合特定条件的企业并返回结构化列表。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# 企业扫描 (Company Scan)
从亿欧数据库批量检索企业，输出结构化 Markdown 列表。
---
## 处理流程
### 第一步：意图解析 & 关键词拆解
分析用户请求，提取以下维度：
| 维度 | 示例 | 对应参数 |
|------|------|----------|
| 行业/赛道 | "生物医药"、"脑机接口" | `concepts` |
| 融资轮次下限 | "B轮以上" | `min_invest_round` |
| 融资轮次上限 | "早期/初创" | `max_invest_round` |
| 融资金额下限 | "融资超过1亿" | `min_invest_amount_wan` |
| 最近融资时间 | "最近融资"、"去年以来" | `latest_invest_after` |
| 省份 | "上海"、"长三角" | `--provinces` |
| 城市 | "合肥"、"杭州" | `--cities` |
**行业/赛道关键词拆解规则（重要）：**
若用户给出领域/赛道词（如"生物医药"、"算力基础设施"、"脑机接口"），须先拆解为搜索关键词：
- 分析该领域产业上中下游的**核心技术关键词**，不超过 5 个
- 分析该领域的**核心产品/应用关键词**，不超过 5 个
- 合计不超过 10 个关键词，作为 `concepts` 数组传入
示例拆解（生物医药）：
> 技术关键词：基因工程、细胞治疗、抗体药物、生物制剂、靶向治疗
> 产品关键词：创新药、医疗器械、体外诊断、疫苗、CRO/CDMO
**地区映射规则：**
- "长三角" → `--provinces "上海,江苏,浙江"`
- "京津冀" → `--provinces "北京,天津,河北"`
- 具体城市 → 优先用 `--cities`
- 未指定地区 → 默认 `--country 44`（中国大陆）
**融资轮次说明：**
```
种子轮 → 天使轮 → Pre-A轮 → A轮 → A+轮 → Pre-B轮 → B轮 → B+轮
→ Pre-C轮 → C轮 → C+轮 → D轮 → E轮 → F轮 ... → 战略投资 → Pre-IPO → 已上市
```
- "B轮以上" → `--min-invest-round "B轮"`
- "早期/初创" → `--max-invest-round "Pre-B轮"`
- "1亿以上" → `--min-invest-amount-wan 10000`（单位：万元）
- "最近融资" → `--latest-invest-after <当前日期减1年>`
---
### 第二步：调用搜索脚本
使用 `bash_tool` 执行以下脚本，**必须加 `--output-temp`**，由脚本自动选择系统临时目录（跨平台兼容 macOS / Linux / Windows），将结果写入文件以避免终端输出截断：
```bash
python {skill_dir}/scripts/search_companies.py \
--concepts "关键词1,关键词2,关键词3" \
[--min-invest-round "B轮"] \
[--max-invest-round "Pre-B轮"] \
[--min-invest-amount-wan 10000] \
[--latest-invest-after "2024-01-01"] \
[--provinces "上海,江苏,浙江"] \
[--cities "合肥"] \
[--country 44] \
[--max-results 50] \
[--output-format markdown] \
--output-temp
```
**参数说明：**
- `--concepts`：逗号分隔的关键词列表（第一步拆解出的所有关键词）
- `--max-results`：默认 50，用户明确要"全部"时可设 100
- 未指定地区时必须加 `--country 44`
- `--output-temp`：**必填**，让脚本自动写入系统临时目录（`tempfile.gettempdir()`），stdout 仅输出一行含路径的确认消息
**脚本位置：** `{skill_dir}/scripts/search_companies.py`
---
### 第三步：读取并展示结果
bash 命令执行成功后，stdout 会输出一行确认消息，其中包含实际写入的文件路径，例如：
```
✅ 结果已写入：/tmp/company_scan_result.md（共 50 家企业）
# 或 Windows 下：
✅ 结果已写入：C:\Users\xxx\AppData\Local\Temp\company_scan_result.md（共 50 家企业）
```
从该消息中提取路径，使用 `Read` 工具读取文件，将内容完整展示给用户。
> ⚠️ **不要直接把 bash stdout 当输出** — bash 工具有输出字符上限，50 条数据会被截断；
> 通过 `Read` 工具读取文件可获得完整内容。
文件内容包含：
- 查询条件摘要
- 企业总数 & 展示数量
- 完整字段表格（简称、全称、简介、行业、融资轮次、投资方、融资时间、估值、省份、链接）
- 亿欧数据链接提示
---
## 完整示例
**用户：** "帮我找找上海市融资到B轮以上的生物医药公司"
**第一步拆解：**
- 地区：上海 → `--cities "上海"`
- 融资：B轮以上 → `--min-invest-round "B轮"`
- 领域：生物医药 →
- 技术：基因工程、细胞治疗、抗体药物、生物制剂、靶向治疗
- 产品：创新药、医疗器械、体外诊断、疫苗、CRO
**第二步命令：**
```bash
python scripts/search_companies.py \
--concepts "基因工程,细胞治疗,抗体药物,生物制剂,靶向治疗,创新药,医疗器械,体外诊断,疫苗,CRO" \
--min-invest-round "B轮" \
--cities "上海" \
--max-results 50 \
--output-temp
```
**第三步：** 从 stdout 确认消息中提取文件路径，使用 `Read` 工具读取该文件并展示给用户。
---
## 注意事项
- 若脚本报错"API 调用失败"，检查网络连通性后重试，或提示用户稍后再试
- 若返回 0 条结果，建议放宽筛选条件（减少关键词、放宽融资轮次或取消地区限制）后重新搜索
- 不要将 `concepts` 关键词设得过于宽泛（如"科技"），应保持领域精准度Related Skills
Moving Company Operations
Complete operations assistant for residential and commercial moving companies. Covers pricing, DOT/FMCSA compliance, crew management, claims handling, and growth strategy.
etherscan
Query EVM chain data via Etherscan API v2. Use for on-chain lookups where Etherscan v2 applies: balances, transactions, token transfers (ERC-20/721/1155), contract source/ABI, gas prices, event logs, and verification of transaction completion. Also trigger when another tool submits a transaction and you need to confirm it finalized on-chain.
isnad-scan
Scan AI agent skills for security vulnerabilities — detects code injection, prompt injection, credential exfiltration, supply chain attacks, and 69+ threat patterns. Use when installing new skills, auditing existing ones, reviewing untrusted code, or validating packages before publishing.
nmap-pentest-scans
Plan and orchestrate authorized Nmap host discovery, port and service enumeration, NSE profiling, and reporting artifacts for in-scope targets.
linkedin-company-scout
Collect company intelligence for sourcing or research by automating Google Chrome against LinkedIn, company websites, and Google Maps. Use when Codex needs to gather non-China companies for one or more industry keywords, extract a strict set of company profile fields, find contact email addresses with source attribution, enforce per-keyword quotas, and keep long-running collection work observable with OpenClaw heartbeat monitoring.
sds-msds-risk-scanner
Extract hazard codes and safety info from chemical safety datasheets.
feishu-group-company
Configure a Feishu multi-bot company group so one coordinator bot, for example `company-ceo`, handles normal group messages, while specialist bots reply only when explicitly @mentioned. Use when setting up or fixing a shared company/work group with multiple Feishu bot accounts, especially for patterns like: normal messages then CEO replies; at UI then UI replies; at dev then dev replies; and CEO stays silent when another bot is explicitly mentioned.
employment-company
就业导向公司调研工具 — 从求职者视角分析目标公司，输出经营稳定性、舆论评价、岗位匹配度等与就业决策相关的分析报告。by Barry
Contract Reviewer - AI Legal Document Risk Scanner
Upload any contract or legal document and get a structured risk analysis with flagged clauses, plain-language explanations, and negotiation suggestions.
quickintel-scan
Scan any token for security risks, honeypots, and scams using Quick Intel's contract analysis API. Use when: checking if a token is safe to buy, detecting honeypots, analyzing contract ownership and permissions, finding hidden mint/blacklist functions, or evaluating token risk before trading. Triggers: 'is this token safe', 'scan token', 'check for honeypot', 'audit contract', 'rug pull check', 'token security', 'safe to buy', 'scam check'. Supports 63 chains including Base, Ethereum, Solana, Sui, Tron. Costs $0.03 USDC per scan via x402 payment protocol. Requires an x402-compatible wallet — recommended: managed wallet service (Sponge, AgentWallet) with no raw key exposure. Programmatic signing with dedicated hot wallet also supported. This skill is read-only and never accesses your tokens or assets.
AURA Security Scanner
Scan AI agent skills for malware, credential theft, prompt injection, and dangerous permissions before installing them
lora-cad-scanner
LoRa Channel Activity Detection (CAD) scanner for LilyGo T3 v1.6 (ESP32-PICO-D4 + SX1276) with HackRF One support. Scans a configurable frequency range using multiple BW/SF combinations, displays live progress on the SSD1306 OLED, stores detected channels in device RAM, emits structured 15-minute reports over Serial, and sends Telegram notifications for new detections via an OpenClaw cron pipeline. Use when scanning for LoRa devices in a frequency band, setting up a LilyGo T3 as a LoRa scanner/sniffer, building RF monitoring pipelines with Telegram alerting, or doing RF reconnaissance with HackRF + LilyGo together.