/SKILL.md
Use when user wants to analyze China stock reports (A-share or Hong Kong), upload annual/quarterly reports to NotebookLM, or research a Chinese listed company's financials
npx skillsauth add jarodise/cninfo2notebookllm cninfo-to-notebooklmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Download annual and periodic reports for China A-share and Hong Kong stocks from cninfo.com.cn and upload them to NotebookLM for AI-powered analysis with a specialized "Financial Analyst" persona.
| Market | Code Pattern | Examples | | :--- | :--- | :--- | | A-share | 6-digit codes (0xxxxx, 3xxxxx, 6xxxxx) | 600519 (贵州茅台), 000001 (平安银行) | | Hong Kong | 5-digit codes (00xxx, 01xxx, 02xxx, 09xxx) | 00700 (腾讯控股), 09988 (阿里巴巴) |
User provides stock name/code
↓
1. Look up stock in database (auto-detect market)
↓
2. Download reports from cninfo:
- Last 5 years annual reports (年度报告)
- Current year: Q1, semi-annual, Q3 reports
↓
3. Create NotebookLM notebook
↓
4. Configure "Financial Analyst" persona with custom prompt
↓
5. Upload all PDFs as sources
↓
6. Return notebook ID ✅
Crucial: Before running the script, verify the environment is ready.
Check Dependencies: Verify if the dependencies are installed (specifically notebooklm and playwright).
Install: If dependencies are missing or this is the first run, execute the installation script:
chmod +x install.sh && ./install.sh
Authenticate: Ensure the user has authenticated with NotebookLM (notebooklm login). If not, ask them to do so.
Run the script from the skill directory:
python3 scripts/run.py <stock_code_or_name>
Examples:
python3 scripts/run.py 600350 - A-share stockpython3 scripts/run.py 山东高速 - A-share by namepython3 scripts/run.py 00700 - Hong Kong stock (Tencent)python3 scripts/run.py 腾讯控股 - Hong Kong by nameThis script handles everything:
assets/financial_analyst_prompt.txt.Provide:
The skill uses a custom system prompt located at:
assets/financial_analyst_prompt.txt
This prompt configures NotebookLM to act as a "Financial Report Analyst" based on "Hand-holding Financial Reporting" methodology.
| Error | Solution |
| :--- | :--- |
| Stock not found | Check if code is valid A-share or Hong Kong stock |
| NotebookLM CLI not found | Ensure notebooklm-py matches requirements.txt and is in PATH |
| Auth missing | Run notebooklm login to authenticate via browser |
| Upload failed | Check network connection and NotebookLM service status |
httpx packagenotebooklm-py packageplaywright (for authentication)| Report Type | Category Code | Period |
| :--- | :--- | :--- |
| Annual | category_ndbg_szsh | Previous 5 years |
| Semi-Annual | category_bndbg_szsh | Current year |
| Q1 Report | category_yjdbg_szsh | Current year |
| Q3 Report | category_sjdbg_szsh | Current year |
| Aspect | A-share | Hong Kong |
| :--- | :--- | :--- |
| Market code | szse | hke |
| Categories | Uses category codes | Empty categories |
| Search key | Uses Chinese search terms | Empty search key |
| Report naming | YYYY年年度报告 | May use Arabic/Chinese numerals |
| Search period | Following year (March-June) | Same year or following year |
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
testing
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).