Loading...
Loading...
Found 137 Skills
Write Related Work sections that compare and contrast prior work with your approach. Organize by theme, cite broadly, and explain how your work differs. Use when writing or improving the Related Work section of a paper.
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.
Discover scientific equations from data using LLM-guided evolutionary search (LLM-SR). Multi-island algorithm with softmax-based cluster sampling, island reset, and LLM-proposed equation mutations. Use for symbolic regression and equation discovery.
Add field definitions to existing research outline.
Submit or run an ML experiment on a compute environment (local, SLURM HPC, RunAI/Kubernetes). Use when the user wants to launch a training run, submit a job, run ablations, or execute an experiment script on any compute cluster.
Audit a skill repository or installed skill collection for global consistency, lifecycle coverage, routing quality, documentation drift, memory writeback coverage, stale future-skill references, broken helper paths, and validation readiness. Use this skill whenever the user asks for a global consistency audit, skill taxonomy review, lifecycle audit, cross-skill routing audit, README or AGENTS inventory consistency check, or maintenance pass over a collection of agent skills.
Initialize a full ML research project control root with independent paper, code, and optional slide repositories, shared project memory, root-level agent guidance, code-owned worktree policy, and component handoffs. Use when starting a new research project, setting up a project root for agents, connecting paper/code/slides repos, or replacing a simple paper+code workspace with a lifecycle-aware research project structure.
Summarize deep research results into markdown report, cover all fields, skip uncertain values.
Use when planning, running, comparing, or recording computational experiments, benchmarks, ablations, autonomous research loops, overnight runs, training runs, or exploratory variants.
Use when converting PDFs, DOCX, HTML, scanned papers, reports, proposals, tables, or figures into Markdown, text, extracted assets, or quality reports for an academic research repository.
Literature Scout — Responsible for multi-source literature retrieval, screening, and classification, and constructing literature matrices. Activated when assigned by research supervisors to collect literature. Conduct systematic literature retrieval using tools such as Exa, ArXiv API, Semantic Scholar, etc.
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention