Pans Lead Miner

AI算力销售线索挖掘器。输入行业关键词，自动搜索筛选潜在客户，识别算力需求信号。 通过SearXNG聚合多数据源（Crunchbase/GitHub/LinkedIn/新闻），按融资和算力需求排序。 触发词：线索挖掘, 客户发现, AI公司搜索, 融资动态, 算力需求, lead generation, pros...

Security Scan

The skill's code, requirements, and instructions are coherent with a lead‑mining tool that queries a local SearXNG instance; no unexpected credential requests, external endpoints, or install steps were found, though there are small documentation inconsistencies to check.

Purpose & Capability

Name/description match the implementation: the script queries a local SearXNG instance, parses search results for funding/compute signals, scores and exports leads. The declared data sources (Crunchbase/GitHub/LinkedIn/news) are used via SearXNG aggregation, which fits the stated purpose.

Instruction Scope

SKILL.md restricts network access to a local SearXNG (127.0.0.1:8888) and the Python script only makes HTTP requests to that URL; it does not read unrelated system files or request credentials. Two inconsistencies: CLI examples reference 'mine.py' but the included script is 'miner.py', and the dependencies list mentions 'requests' and 'beautifulsoup4' while the shipped script uses urllib and does not import requests/bs4. These look like documentation drift rather than malicious behavior, but you should confirm filenames and required packages before running.

Install Mechanism

No install spec — instruction-only with an included Python script. Nothing is downloaded or written to disk by an install step, so installation risk is low. The tool expects Python 3.11+ present on the host.

Credentials

No environment variables, credentials, or config paths are requested. The script only contacts a local SearXNG endpoint; no external hardcoded remote endpoints or secret exfiltration mechanisms were observed.

Persistence & Privilege

always:false and no code indicates the skill attempts to persist itself or modify other skills or system-wide agent settings. Normal runtime autonomy is allowed, but the skill itself does not request elevated persistence.

Assessment

This skill appears to do what it says: it queries a local SearXNG instance to gather and score leads. Before installing/running: (1) confirm you have a local SearXNG instance at http://127.0.0.1:8888 and are comfortable with its configured data sources (LinkedIn/Crunchbase crawling may have legal/privacy implications); (2) fix the documentation mismatch (SKILL examples use 'mine.py' but the included file is 'miner.py') and verify required Python packages (the script uses urllib, not requests/bs4 — install any needed libraries); (3) run the script in an isolated environment first to validate behavior and outputs; (4) if you rely on third‑party SearXNG instances, be cautious — that could expose queries externally. If you want higher assurance, request the full, untruncated miner.py for review and confirm there are no hidden network calls beyond the local SearXNG endpoint.

AI算力销售线索挖掘器

功能

输入行业关键词，自动搜索并筛选潜在客户列表，识别算力需求信号。

数据源

• Crunchbase RSS：公开融资新闻
• GitHub Trending：AI 项目检测
• LinkedIn 公开搜索：通过 SearXNG 聚合
• 新闻聚合：通过 SearXNG 搜索融资动态

搜索逻辑

1. 输入关键词（如 "AI infrastructure", "LLM startup"）
2. 通过本地 SearXNG 实例搜索（http://127.0.0.1:8888/search?format=json）
3. 解析结果，提取公司名、人名、融资信息
4. 按算力需求信号排序（融资轮次、模型训练关键词、招聘GPU工程师等）

CLI 参数

• --keyword：搜索关键词（必填）
• --source：数据源（crunchbase/github/linkedin/news/all）
• --limit：结果数量（默认 20）
• --region：地区（us/cn/eu/global）
• --stage：融资阶段（seed/series-a/series-b/later/all）
• --json：JSON 输出
• --export：导出 CSV 文件路径

输出格式

| 公司 | 融资轮次 | 金额 | 关键人 | 算力信号 | 来源 |

示例

python3.11 ~/.qclaw/skills/pans-lead-miner/scripts/mine.py --keyword "AI infrastructure" --limit 5
python3.11 ~/.qclaw/skills/pans-lead-miner/scripts/mine.py --keyword "LLM startup" --source github --limit 10
python3.11 ~/.qclaw/skills/pans-lead-miner/scripts/mine.py --keyword "AI" --stage series-a --export leads.csv

依赖

• Python 3.11+
• SearXNG 本地实例（http://127.0.0.1:8888）
• requests
• beautifulsoup4