Litian Gong
Community@gonglitian · United States
EE master student at University of California, Riverside.
Agent Skills by Litian Gong
Showing 39 vetted skills indexed across 1 GitHub repositories.
planning-with-files
Maintain plan, findings, and progress in on-disk files for long-running projects.
gpu-train-monitor
Monitors GPU health and summarizes training progress from live system data.
ucr_hpcc_cluster
Connect to the UCR HPCC cluster and submit SLURM jobs.
paper_related_works
Extract references and citations from scholarly papers into a structured graph.
paper-discovery-sources
Consolidate local vec-db, Semantic Scholar, and AlphaXiv paper discovery into one reference framework.
research-refine-pipeline
Chain research-refine and experiment-plan workflows into a final proposal and experiment roadmap.
isaaclab-dev
Consolidate Isaac Lab robot simulation documentation and API references.
create_skill_with_paper
Generate a Claude Code skill scaffold from a paper and code repository.
comprehensive-survey
Coordinate parallel academic, social, and reference searches into structured literature survey reports.
audio-transcribe
Transcribe audio and video files into txt, json, and srt transcripts.
experiment-plan
Convert refined research proposals into claim-driven experiment roadmaps with phases and budgets.
find-skills
Discover agent-skills and provide install commands via the Skills CLI.
gap-to-method
Construct a multi-dimensional literature matrix to identify research gaps and propose methods.
data-pipeline-check
Validate dataset formats, schema consistency, and data quality for ML pipelines.
marp-slide
Transforms user content into polished Marp slide decks with built-in themes and layouts.
research-refine
Refine vague research directions into anchored method plans with Codex MCP review.
notion-paper-table
Extract literature metadata from local documents into a Notion database.
research-survey
Search local vec-db and arXiv, read papers in parallel, and generate structured markdown reports.
git-pushing
Stage changes, create conventional commits, and push to the remote.
review-pr
Fetch GitHub PR data from a URL and verify compliance with CONTRIBUTING.md.
project-init
Automate new research project setup with conda environment and standardized directory structure.
multi-platform-search
Coordinate parallel crawlers across Xiaohongshu, Bilibili, Zhihu, and X/Twitter to gather discussions.
train-debug
Diagnose ML training issues from symptom to root cause across GPU setups.
auto_experiment
Automate end-to-end ML experiment workflows from setup to reporting.