Automate Google Sheets interactions through browser automation - create spreadsheets, enter data, apply formulas, and format cells.

Download files in Chrome on Windows and macOS. Handles triggering downloads, detecting and resolving popups, verifying completion, and locating files.

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.

Profound LLM citation tracker (extension). Time-series brand citation rates across ChatGPT, Perplexity, and other LLMs. Pairs with seo-seranking for triangulated AI visibility coverage.

Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation.

Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.

小说改写为格式化剧本的方法论和规范

AI Berkshire skill: 行业漏斗筛选：从全市场到 3 家的价值投资精选流程. Source: skills/industry-funnel.md.

AI Berkshire skill: Income Investment: Durable and Opportunistic Distribution Analysis. Source: skills/income-investment.md.

AI Berkshire skill: 财务数据获取与交叉验证规范. Source: skills/financial-data.md.

How to scope, draft, and revise a Markdown report artifact via generate_report

Strict Python TDD workflow using pytest (Red-Green-Refactor).

Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability. Use after implementing features or when performance concerns arise.

Pre-commit/ship code review: Codex default; optional Claude, Pi, Droid, Copilot, or OpenCode.

OAuth 2.0 and OpenID Connect expert for authorization flows, PKCE, and token management

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization