Academic Figure Assistant
Paste the following prompt into your AI chat to install this skill:
Please install @user_1570b1d3/cjs-test1 according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Scientific plotting is often less about producing a figure and more about getting the details right: the code needs to run locally, comments should explain each step, and the color scheme should be suitable for academic publication. This skill targets data-analysis figures and converts natural-language requirements into Python matplotlib code, reducing repeated fixes between idea and reproducible script.
How It Works
- Input:
textis required and can describe chart type, data relationship, axis meaning, title, legend, and color scheme;session_idis optional. - Output:
contentreturns Python plotting code and explanation. - Core constraint: the code should be directly runnable, with clear comments and a color scheme suitable for academic papers.
- Usage: describe the data meaning and chart requirements clearly, such as trend lines, bar comparisons, scatter distributions, or grouped comparisons, then run the generated code locally.
Boundaries and Notes
- It focuses on
matplotlibdata-analysis plotting, not full statistical modeling, interactive visualization, or a complete graphics engineering workflow. - After generation, verify local dependencies such as
matplotlibandnumpy, and confirm that data file paths and column names match the request. - For journal submission, fonts, font sizes, legend placement, axis ranges, and file resolution may still need final adjustment.
Use Cases
- Before writing methods, describe two experimental datasets as a trend line and generate matplotlib code.
- During a lab meeting, quickly turn category-level metric comparisons into a bar chart with axis comments.
- For reviewer response, convert a scatter-plot requirement into runnable Python plotting code.
- After cleaning data, describe grouped trends in one sentence and get commented matplotlib code.
Best For
- Graduate students preparing journal papers: need experiment results turned into runnable, well-commented matplotlib figures.
- Researchers doing data analysis: want quick Python plotting code from chart descriptions with publication-ready colors.
- Lab mentors guiding students: need clear data-trend explanations and reusable plotting code for the group.
- Technical writers: generating figure code for methods sections and checking local dependencies and run results.
Related Skills
Automatically indexes Gradle-cached AAR/JAR dependency classes and returns library coordinates, versions, and public APIs by fully qualified name, using only the Python standard library.
Codifies AMT and YourMT3 training conventions, script patterns, hyperparameters, precision, checkpoints, and NaN safeguards.
Retrieve relevant chunks from a customer-managed PKM dataset by dataset_id and return concise, source-annotated answers.
Convert PRDs, user stories, or functional specs into prioritized test-point checklists covering functional, business-rule, boundary, exception, and non-functional dimensions.