全部能力

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

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.

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

Draft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTeX content…

Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or…

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea…

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → figure-spec/paper-illustration/mermaid-diagram → paper-write → paper-compile…

This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality…

Analyzes community health and delegates engagement tasks. Use when managing GitHub issues, discussions, and announcements.

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when…

Async deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context), preview costs (--dry-run),…

Extracts procedural content from project docs into slash commands. Use when docs contain deploy, test, or troubleshoot procedures.

Launches RFC and debate discussions on GitHub. Use when proposing changes that need community input or voting.

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a…

Produces prioritized triage report from open GitHub issues, PRs, and discussions. Use when reviewing community backlog.

Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\",…

Search, summarize, and synthesize economics literature

Creates slash commands from procedural doc sections. Use when transforming documentation prose into executable commands.

Composes and publishes announcements to GitHub Discussions. Use when sharing releases, updates, or news with the community.