Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Parse and extract data from Chinese identity documents for KYC (Know Your Customer) compliance. Adapts the original kyc-doc-parse skill for Chinese ID cards, business licenses, and domestic compliance requirements. Triggers on "A股KYC", "身份文件解析", "parse Chinese ID", "KYC document", "客户身份识别", or "extract [document type]".
Populate A-share investment banking pitch deck templates with data from source files. Adapted from the original pitch-deck skill for Chinese companies, A-share market data, and Chinese business context. Triggers on "A股Pitch Deck", "路演PPT", "pitch deck China", "pitch deck A-share", or "fill pitch template for [company]".
Create PowerPoint templates for A-share investment presentations. Adapts the original ppt-template-creator skill for Chinese business presentation standards and firm branding. Triggers on "A股PPT模板", "投资PPT模板", "create ppt template China", "presentation template", "制作PPT模板", or "build template for [purpose]".
Generic PowerPoint authoring skill for A-share investment analysis and pitch decks. Creates professional 路演PPT / 投资分析PPT for any A-share company using live data from iFind MCP (Tier-1) and AkShare MCP (Tier-2 fallback) tools. All company-specific values are parameterized — never hardcoded. Triggers on "A股PPT制作", "投资PPT", "制作PPT", "路演PPT", "pitch deck", "PowerPoint [company/ticker]", or any request to create slides for a Chinese stock. When invoked, use the `generate_a_share_ppt` script with --company and --ticker args.
Create professional Excel workbooks for A-share financial analysis. Adapts the original xlsx-author skill for Chinese financial modeling standards, CAS conventions, and A-share formatting. Triggers on "A股Excel模型", "财务模型制作", "create model China", "build model xlsx", "制作模型", or "Excel model [company]".
Get a PDF into the model without blowing the context window or losing structure. Native PDF beats OCR-then-text for most cases; extract-then-summarize beats native for very long docs.
Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.
Extract, filter, and label research papers from rawdata files (.bib, .html) using the two-level taxonomy defined in SKILL.md. Use this skill when the user wants to process new venue data, label papers, add new conferences to the database, run the paper classification pipeline, rebuild the website, or batch-process a folder of rawdata. Triggers: "label papers", "process rawdata", "process folder", "batch process", "add venue", "classify papers", "extract papers from", "run the labeling pipeline", "process .bib", "process .html", "rebuild website", "update website".
Headless video rendering with Remotion. Works on any Linux server - no Mac or GUI needed. Templates for chat demos, promos, and more.