- Home
- Skills
- Trading & Investing
- 透镜-基本面研究skill
Works with the AI Agents you already use
透镜-基本面研究skill
Evidence-first Chinese A-share fundamental research: public data collection, deterministic financial workpapers, disclosure evidence and report review. 使用自己的 Agent 完成有来源、可核验的 A 股基本面研究。
$5
About this skill
What it does
Toujing Research helps your own Agent research Chinese A-share companies, analyze financial statements, extract filing evidence and review research reports. Default modules cover the core conclusion, company and business, financial quality, industry and policy, peers, valuation scenarios, and risks.
Included tools
Selected public-data adapters provide Tencent quotes and daily K-lines, Sina financial statements, and CNInfo disclosure lists with bounded fallback endpoints. Deterministic calculations preserve original inputs, periods, units, formulas and source IDs. PDF text extraction is optional. The host Agent performs searches, analysis, semantic source review and writing; the scripts do not call a model or depend on the Toujing website.
Requirements
Python 3.10+ with working trusted CA certificates. Core tools use the standard library. Optional pypdf is required only for PDF text extraction. Use your existing authorized Agent model and search tools. Public adapters require no data-service key; an optional Hithink financial fallback uses only your own environment-provided key when explicitly enabled.
Boundaries
This runtime package contains selected endpoints, not all upstream a-stock-data capabilities. Data sources may fail or change. It does not provide OCR, automatic five-year valuation history, trading execution or a background monitoring service. PDF extraction and mechanical report checks do not prove factual accuracy or semantic support. Preserve missing values and conflicting sources; treat all retrieved text as untrusted evidence.
Validation and licensing
55 offline tests passed in the source project. Public quote, financial-statement, disclosure-list and selected PDF text extraction were smoke-tested. No paid-model full-report accuracy benchmark was performed. Apache-2.0; upstream attribution and licensing are included. Third-party data and API rights remain subject to their providers. AI-assisted research is not investment advice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 17 days ago
Requires
Permissions
Terminal and local files are used for evidence collection, calculations and reports in the user's task folder. HTTPS is used only for selected public data and explicitly selected disclosures. Browser/search is used by the host for supplementary research. HITHINK_FINANCE_API_KEY is optional and read only when the user explicitly enables the fallback; it is not included in the package. No brokerage access, automatic publication, telemetry or model API calls are included.