AI Agent Skills

Read, create, or edit PowerPoint .pptx decks — build slides from an outline,

Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day one.

Fast quantitative research and backtesting workflows for financial agents.

Research a companys valuation, growth, profitability, balance sheet, competitive moat, and management quality.

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

Estimate a public companys intrinsic value through DCF, relative, and sum-of-the-parts valuation methods.

Open football event data for match analysis, xG research, scouting, and World Cup-style dashboards.

Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.

Prepare a pre-earnings briefing with consensus estimates, beat-miss history, and current market context.

Rank recent market-moving news and explain likely effects on equities, commodities, monetary policy, and earnings.

Build an upcoming US earnings calendar with dates, timing, consensus estimates, and market-impact context.

Autonomously improve a generated paper via GPT-5.6-Sol xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\…

DeepPaperNote is an agent skill for deep-reading a single paper and generating high-quality Obsidian-style research notes. Works with Claude Code, Codex, Cursor, Copilot…

Look up A-share, Hong Kong, and US stock tickers and retrieve historical OHLCV price data for research.

Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. Use when des…