Agent skill
slides-as-code
Build research slides with text-first source (Slidev/Marp/Reveal/Quarto) and reproducible export (PDF). Includes structure, figure reuse rules, and quality checklist for top-tier scientific presentations.
Install this agent skill to your Project
npx add-skill https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/main/bundled/skills/slides-as-code
SKILL.md
Slides as Code(顶级科研汇报的可复现幻灯片)
目标
解决常见问题:
- PPT 版本失控(final_v7)
- 图表重复截图、清晰度崩坏
- 汇报结构不稳定(信息密度失衡)
本 skill 让 slides 拥有:
- 文本源(Markdown / Quarto / LaTeX Beamer)
- 可复现导出(PDF、可选 PPTX)
- 图表复用(直接引用
figures/最终导出,不截图)
技术路线(按约束选)
- Slidev:开发者友好,组件化,适合组会/技术分享
- Marp:排版可控,适合快速生成简洁风格
- Reveal.js:网页交互强,适合 demo/交互展示
- Quarto slides:报告/论文/幻灯片一体化(推荐用于报告+slides联动)
内容结构建议使用
scientific-slides;本 skill 更偏“工程化与导出管线”。
元规则(幻灯片质量的 80/20)
1) 一页一结论
- 标题就是结论,不是主题
- 每页只服务一个问题:What / Why / How / So what
2) 图不截图
- 图只从
figures/**/out/引用(PDF/SVG/PNG) - 禁止从论文 PDF 截图再贴回 PPT
3) 讲述顺序固定
推荐骨架:
- 背景与缺口(1–2 页)
- 方法直觉(1–2 页示意图)
- 核心结果(3–6 页,每页一图一结论)
- 局限与下一步(1–2 页)
模板
参考:templates/slidev-structure.md
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
pufferlib
This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.
fluidsim
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.
metabolomics-workbench-database
Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.
build-error-resolver
Compatibility alias for build-specific error resolution. Use this when VCO routes to build-error-resolver but the upstream agent is unavailable in the current runtime.
geniml
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
Didn't find tool you were looking for?