全部能力

Generate a pedagogically-grounded study guide for learning an unfamiliar codebase. Use when the user wants to onboard onto a codebase, understand a project's…

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID,…

MemPalace — mine projects and conversations into a searchable memory palace. Use when asked about mempalace, memory palace, mining memories, searching…

当用户明确要求"写/改研究基础""研究基础+工作条件+风险应对编排"时使用。为 NSFC 正文"（三）研究基础"写作/重构，并同步编排"工作条件"和"研究风险应对"，用证据链证明项目可行、资源条件对位研究内容、风险预案可执行。

Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline…

Read research outline, launch independent agent for each item for deep research. Disable task output.

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning…

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running…

Comprehensive job search strategy skill for analyzing job postings, discovering non-obvious insights, conducting conversational skills-matching interviews,…

Project development lifecycle management with a strict three-phase workflow (investigate, proposal, implement), file-based plan tracking in docs/plan/, task…

Trusted-lane analysis skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and…

Market salary research, accomplishment quantification, negotiation scripts, total compensation analysis, timing strategy.

Search for tokens or entities by name. Use when you have a token name and need the full address, or want to find an entity.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1)…

Draft and revise ML, CV, NLP, and systems research papers with strong claim-evidence flow, reviewer-aware structure, and submission-ready section planning. Use when the user needs help with an abstract, introduction, related work, method, experiments, ablations, discussion, figures/tables, checklist coverage, or rebuttal / response-letter writing for a paper. Triggers on: research paper, academic paper, ML paper, NeurIPS paper, ICLR paper, CVPR paper, experiments section, ablation plan, related work, contribution framing, reviewer response, rebuttal, camera-ready revision.

DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.

Build interactive chat agents for exploring and discussing academic research papers from ArXiv. Covers paper retrieval, content processing, question-answering,…

Search the web using Perplexity AI. Use when needing to search, look up, research, find current information, best practices, compare technologies, or answer…

Generate publication-quality figures and tables from experiment results. Use when user says \"画图\", \"作图\", \"generate figures\", \"paper figures\", or needs…

This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition…