菜单
Seaborn statistical plots for exploratory analysis via agent_generated_code. Use for quick relational/distribution/categorical charts. Do NOT use for submission-grade Nature figures (nature_figure) or low-level artists control (matplotlib).
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ai4protein/VenusFactory2 --skill seaborn命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Fine-tune and run custom protein models on VenusFactory (CSV/HF → config → train → predict). Use when the user brings labeled sequences, wants adapter training (ProtT5/ESM2/Ankh/QLoRA notes), or batch inference with a trained config. Do NOT use for zero-shot mutation without labels (zero_shot_mutation_workflow) or built-in function heads already covered by predict_protein_function.
AlphaFold DB structures and confidence analytics via VenusFactory tools. Use when the user needs predicted structures by UniProt ID, pLDDT/PAE analysis, or PDB/mmCIF download. Do NOT use for experimental PDB (rcsb_database), local ESMFold without UniProt (predict_structure_esmfold / protein_structure_pipeline), or sequence annotation (uniprot_database).
arXiv preprint server — keyword search the official API and download papers as PDF / HTML / source tarball. Use whenever the user mentions an arXiv ID (e.g. 2106.04559) or wants preprints on a topic in CS / physics / math / quantitative biology. For biomedical preprints specifically, prefer biorxiv skill.
基于 SOC 职业分类
正在显示 SKILL.md
| name | seaborn |
| description | Seaborn statistical plots for exploratory analysis via agent_generated_code. Use for quick relational/distribution/categorical charts. Do NOT use for submission-grade Nature figures (nature_figure) or low-level artists control (matplotlib). |
| license | Unknown |
| metadata | {"version":"1.2","skill-author":"VenusFactory2"} |
High-level statistical viz on top of matplotlib. In VenusFactory, plots run through agent_generated_code / python_repl. Publication figures must load nature_figure first.
seaborn_* @tool. Optional helpers: src/tools/visualize/matplotlib/plot_template.py, style_configurator.py.read_skill("seaborn", relative_path="references/function_reference.md") or references/legacy_guide.md.| Use seaborn | Prefer instead |
|---|---|
| EDA bar/box/violin/heatmap | — |
| Publication multi-panel Nature style | nature_figure |
| Pixel-perfect artists / custom projections | matplotlib |
import seaborn as sns
import matplotlib.pyplot as plt
sns.set_theme(style="whitegrid")
ax = sns.barplot(data=df, x="mutation", y="score")
fig = ax.get_figure()
fig.savefig(out_png, dpi=300, bbox_inches="tight")
scatterplot, lineplot, relplothistplot, kdeplot, ecdfplotboxplot, violinplot, barplot, stripplotheatmap, clustermapseaborn.objects — see references/objects_interface.md if present / legacy guidenature_figure for manuscript figuresoutput_dir at dpi≥300Trust order: SKILL.md (hub tools & envelopes) → topic refs → references/legacy_guide.md (archived; may be outdated).
read_skill(skill_id="seaborn", relative_path="references/legacy_guide.md")
Load legacy only after the hub workflow in this file is insufficient.