Finance Knowledge Assistant
Paste the following prompt into your AI chat to install this skill:
Please install @user_0caf726f/knows-finance by following the guide at https://skillhub.cn/install/skillhub.md.
About this skill
Local Knowledge Retrieval for Finance Q&A
A common issue in finance product explanations, internal training, or customer support is that a model may answer from parametric memory, mixing concepts, omitting sources, or treating general knowledge as an official answer. This skill constrains answers to the article_fin_knowledge/ folder and prefers local file entries over built-in model knowledge.
How It Works
- Keyword parsing: extracts terms such as banking, funds, M&A, derivatives, securities issuance, securities trading, and asset securitisation.
- File matching: maps terms to knowledge files, for example
银行系金融知识大全.md,基金类.md,金融衍生工具类.md, and证券发行类.md. - Excerpt extraction: opens the 1–3 most relevant files, pulls the entries that directly answer the question, and formats the response with conclusion, key points, and source files; for high-intent product inquiries it may add the official single image per policy.
Boundaries
It is suitable for finance concepts, product mechanics, trading rules, and other knowledge-style questions where cited sources are needed. If the local knowledge base does not cover the topic, it should say so instead of guessing. It should not treat untranscribed image content or common-sense conclusions as facts, nor provide investment advice or compliance commitments.
Use Cases
- Bank customer support agents explaining fund subscription and redemption rules to clients, requiring accurate clauses and cited source files from the local knowledge base.
- Financial training instructors preparing M&A assessment questions, extracting standard definitions from local knowledge base files as reference answers.
- Business operations resolving high-intent product mechanism queries, providing conclusions based on the local knowledge base and attaching the official mini-program image.
- Risk control researchers verifying asset securitization concepts, enforcing the model to answer strictly from local documents and explicitly stating if the topic is missing.
Best For
- Bank or securities customer service specialists who need to avoid LLM hallucinations, accurately answering client queries on funds and securities trading with official sources.
- Financial institution internal training instructors who need to quickly extract standard definitions of M&A, derivatives, etc., from the local finance knowledge base for teaching.
- Business operations personnel who need to guide high-intent users to the official mini-program platform according to norms after answering product mechanism queries.
- Risk or compliance researchers who require the system to answer strictly based on local documents when verifying terms like asset securitization, and explicitly refuse if missing.
Related Skills
Provides Bazi, Liu Yao, Qimen, Meihua, and date-selection guidance from classical references, with plain-language explanations and actionable suggestions.
Extracts core themes and hierarchical relationships from documents, reports, web pages, and images into editable mind maps.
Parse WeChat favorites exports, classify them with keywords or LLM discovery, and export to Obsidian, Notion, or IMA.
Enter a video URL or local file and automatically download, transcribe, and analyze it into structured outputs such as summaries, quotes, chapters, subtitles, mind maps, and share cards.