Agent Skills by Jun MA
Showing 44 vetted skills indexed across 1 GitHub repositories.
JunMA98networkx
Construct and analyze graph structures with NetworkX algorithms in Python.
JunMA98shap
Compute SHAP values and visualize feature attributions for model predictions.
JunMA98repo-cleanup
Generate a prioritized repository cleanup plan for structure, naming, and documentation.
JunMA98umap-learn
Reduce high-dimensional embeddings to 2D or 3D with UMAP for visualization.
JunMA98sympy
Perform symbolic algebra, calculus, and equation solving with SymPy in Python.
JunMA98vaex
Process and analyze large tabular datasets with lazy evaluation and out-of-core processing.
JunMA98code-reproduction
Reproduce reported results with a structured plan and execution trace.
JunMA98dask
Distribute and parallelize Python computations for datasets larger than memory using Dask.
JunMA98get-available-resources
Detect CPU, memory, disk, and GPU metrics and generate a JSON report.
JunMA98exploratory-data-analysis
Analyze CS data files and generate a structured Markdown report.
JunMA98scientific-schematics
Generate publication-ready scientific schematics from natural-language prompts.
JunMA98pyzotero
Manage Zotero libraries programmatically via the Zotero API using Python.
JunMA98seaborn
Generate publication-quality statistical visualizations from DataFrames using seaborn APIs.
JunMA98citation-management
Clean and standardize CS references with canonical metadata and BibTeX formatting.
JunMA98scientific-critical-thinking
Critique computer science claims for confounders, causal leaps, and missing controls.
JunMA98agent-coding
Design tool-using agent architectures with contracts and evaluation plans.
JunMA98markitdown
Convert PDF, Word, PowerPoint, and HTML documents into Markdown with YAML frontmatter.
JunMA98reviewer-response
Convert reviewer comments into structured rebuttal and revision workflows.
JunMA98paper-to-code
Translate papers into implementation roadmaps with modules, data flows, and interfaces.
JunMA98plotly
Create interactive Python visualizations with hover, zoom, and pan.
JunMA98statistical-analysis
Plan and interpret statistical analyses for computer science experiments.
JunMA98scientific-writing
Draft computer science manuscripts with structured sections and citation guidance.
JunMA98torch-geometric
Coordinate end-to-end graph neural network experiments using PyTorch Geometric.
JunMA98github-release-prep
Audit GitHub repositories for release-readiness by validating documentation, licenses, notices, and packaging.