JunCheng Wan avatar

JunCheng Wan

Community

@satsuki-64

3Followers
|
5Public Repos
|
42Published Skills

I am a first-year graduate student majoring in Software Engineering at Zhejiang University of Technology. My main research interests include computer graphics a

Agent Skills by JunCheng Wan

Showing 42 vetted skills indexed across 1 GitHub repositories.

satsuki-64satsuki-64
2

paper-write

Draft LaTeX paper sections from outlines and narrative inputs.

Community
Advanced
satsuki-64satsuki-64
2

paper-poster

Extract paper content and generate LaTeX posters, PPTX assets, and SVGs.

Community
Advanced
satsuki-64satsuki-64
2

proof-writer

Draft rigorous mathematical proofs for ML/AI theory from formal claims and assumptions.

Community
Advanced
satsuki-64satsuki-64
2

formula-derivation

Structure research formula derivations into a Derivation Package scaffold.

Community
Advanced
satsuki-64satsuki-64
2

training-check

Monitor WandB metrics during training to detect anomalies and decide whether to continue or halt.

Community
Advanced
satsuki-64satsuki-64
2

result-to-claim

Judges experimental results from multiple sources and routes the next actions via Codex.

Community
Advanced
satsuki-64satsuki-64
2

mermaid-diagram

Convert natural language requirements into Mermaid diagrams and verify syntax with Mermaid CLI.

Community
Advanced
satsuki-64satsuki-64
2

semantic-scholar

Retrieve venue papers with citation data via the Semantic Scholar API.

Community
Advanced
satsuki-64satsuki-64
2

system-profile

Profile scripts, processes, GPUs, memory, or interconnects to identify performance bottlenecks.

Community
Intermediate
satsuki-64satsuki-64
2

research-refine-pipeline

Chain research refinement and experiment planning into a single pipeline.

Community
Advanced
satsuki-64satsuki-64
2

auto-review-loop-llm

Automates iterative multi-round review of research outputs using OpenAI-compatible LLM APIs with scoring and logging.

Community
Advanced
satsuki-64satsuki-64
2

experiment-plan

Convert research proposals into claim-driven experiment roadmaps with run orders and budgets.

Community
Advanced
satsuki-64satsuki-64
2

idea-creator

Generate and rank publishable research ideas from a broad direction.

Community
Advanced
satsuki-64satsuki-64
2

grant-proposal

Draft grant proposals from research ideas across major funding agencies.

Community
Advanced
satsuki-64satsuki-64
2

monitor-experiment

Monitor experiment progress via SSH and parse JSON results from remote servers.

Community
Advanced
satsuki-64satsuki-64
2

research-pipeline

Automate research workflows from idea discovery to submission-ready papers.

Community
Advanced
satsuki-64satsuki-64
2

research-refine

Convert vague research directions into concrete problem anchors and method plans.

Community
Advanced
satsuki-64satsuki-64
2

ablation-planner

Designs ablation studies with defined tests, expected outcomes, and run order.

Community
Advanced
satsuki-64satsuki-64
2

idea-discovery

Automate multi-phase idea discovery from literature survey to validated experiment planning.

Community
Advanced
satsuki-64satsuki-64
2

paper-compile

Compile LaTeX papers to PDF with latexmk and verify output.

Community
Intermediate
satsuki-64satsuki-64
2

paper-slides

Generate Beamer slides from a compiled paper with venue-specific styling.

Community
Advanced
satsuki-64satsuki-64
2

analyze-results

Compute statistics and generate comparison tables from ML experiment results.

Community
Advanced
satsuki-64satsuki-64
2

paper-figure

Generate publication-quality figures and LaTeX-ready tables from structured experiment results.

Community
Advanced
satsuki-64satsuki-64
2

run-experiment

Deploy and execute ML experiments on local or remote GPU servers via SSH.

Community
Advanced