This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context...
执行完整的 7 阶段深度研究流程。接收结构化研究任务，自动部署多个并行研究智能体，生成带完整引用的综合研究报告。当用户有结构化的研究提示词时使用此技能。
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search,...
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or...
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring...
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or...
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive...
Quality control, citation validation, fact-checking before human review
Consult Gemini CLI, Codex CLI, Mistral Vibe, Kilo CLI, Cursor, Claude, Amp, Qwen, and Ollama as external experts for coding questions. Automatically excludes the invoking agent from the panel to...
Malware analysis, CVEs, attribution reports, hacker communities
Project histories, changelogs, developer interviews, open source
Use when about to ask the user a factual question, propose a solution, diagnose an error, or choose between approaches. Triggers on: 'Do you have X installed?', 'What version?', 'Is X...
Archives, contemporary accounts, timeline reconstruction
Personal backgrounds, interviews, motivations, humanizing details
The meta-skill that powers all other AI tools. Prompt engineering for creative applications is the art and science of communicating with AI models to produce exactly what you envision—in images,...
SEC filings, earnings calls, analyst reports, market data
DOJ/FBI/SEC press releases, agency statements, government sources
Investigative articles, interviews, news coverage
Court documents, indictments, plea agreements, sentencing records
Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data,...