AI & ML

Rate Limiting — Agent Arena

Error Handling — Agent Arena

Agent Roster

TypeScript Patterns — Agent Arena

Capacity Planning — Real-Time Agent Workload Tracking

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

SNLI-VE: Visual Entailment Dataset

Pixtral 12B: A Frontier Multimodal Model

TRAK: Attributing Model Behavior at Scale

Idefics2: An 8B Parameters Multimodal Model

SA-1B: Segment Anything 1 Billion Masks Dataset

WebVid-10M: A Large-Scale Video-Text Dataset

Dolphins: Multimodal Language Model for Driving

Kinetics-400: A Large Video Understanding Dataset

Donut: Document Understanding Transformer without OCR

nuScenes: A Multimodal Dataset for Autonomous Driving

Flamingo: A Visual Language Model for Few-Shot Learning

No Robots: A Dataset of Personally Written Instructions

3D-LLM: Injecting the 3D World into Large Language Models

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

Give your AI agents something more useful than a prompt. Velocity through clarity.

Control Adobe desktop apps - Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition - from the shell via Flue, without an MCP server.

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.

Mcp Vods

Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.

飞书视频会议：搜索历史会议记录、查询会议纪要（总结/待办/章节/逐字稿）、查询参会人快照。当用户查询已结束的会议、获取会议产物（纪要/妙记）、查看参会人时使用；查询未来日程走 lark-calendar。不负责：Agent 真实入会/离会、会中实时事件（走 lark-vc-agent）。

Control Blender from the shell via Flue - a Python bridge to bpy without an MCP server.

RAG Architect - POWERFUL

Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes /cs:board, calls a board meeting, or wants structured multi-perspective executive deliberation on a strategic question.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/. Use when a query is fuzzy or cross-file ("how did we fix X", "what did we decide about Y", "which skill handles Z"). Complements grep (exact) and Serena (code symbols). If the user asks a recall question that doesn't map to a specific known file, reach here first.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Route a task to the most fitting skill or agent. Parses user intent, checks installed-skill inventory, and picks the best match (single skill or chain).