Agent skill · Design & Presentation

chinese-ppt2

Upgrade of chinese-ppt for Chinese Beamer decks (xelatex + ctex + fandol, CUFE template). Same 7-section outline and X→M→Y framework, but adds (a) mandatory 1.3 line-spacing + 3pt paragraph spacing, (b) overflow-prevention line budget + balanced split-frame rules, (c) prose rewrites that strip AI-ish "关键比较/理论映射" labels and redundant 章节括号注释, (d) stricter CJK-space + middle-dot rules, (e) retrofit workflow for existing chinese-ppt decks, (f) mandatory local linespread reset inside TikZ / table / fixed-geometry frames. Use for "做中文学术PPT 2 版"、"中文 Beamer 改进版"、"答辩 PPT chinese-ppt2"、"防越界 PPT"等请求。用户在

brycew6m878★ · +32/wk · 1 repos on radarProfile →
claude-codeNOASSERTION
Install
npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill chinese-ppt --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 4
SKILL.md size: 22 KB
Bundled scripts: none
Path: skills/67-econfin-workflow-toolkit/chinese-ppt/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 3,244
Language: Stata
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Upgrades an existing chinese-ppt deck to chinese-ppt2, applying a comprehensive set of stricter typography and layout rules for Chinese Beamer decks (xelatex + ctex + fandol, CUFE template). It preserves the original 7-section outline and X→M→Y framework but enforces several new constraints designed to prevent overflow and improve readability. It introduces mandatory global line spacing of 1.3 with 3pt paragraph spacing, plus a line-budget based frame splitting strategy when content overflows. It mandates prose rewrites to remove AI-like labels and redundant annotations, tightens CJK spacing and middle-dot handling, and provides a retrofit workflow to adapt existing decks. It also requires a local linespread reset inside TikZ, table, and fixed-geometry frames and restricts the Overleaf output to .tex and figures/. outputs only. It includes explicit guidance on how to structure and render §7 with policy suggestions, and establishes rules to avoid AI-flavored phrasing, hard-coded frame numbering, and verbose framing. Use for requests like 做中文学术PPT 2 版, 中文 Beamer 改进版, 答辩 PPT chinese-ppt2, 防越界 PPT, etc.

How it works

The skill inherits the base rules from chinese-ppt and adds 7 primary upgrades, each with explicit LaTeX-level directives and frame-structure guidance:

  • Upgrade 1: In the preamble, enable enumitem and etoolbox, set linespread to 1.3, set parskip to 3pt, configure enumerate labels for top-level and sub-items, and install hooks to reset linespread to 1.0 inside tabular and tikzpicture environments to prevent overflow. Do not use \selectfont inside these hooks.
  • Upgrade 2–7: Define frame content budgets and overflow handling, introduce half-frame splitting when overflow exceeds thresholds, rewrite AI-labeled prose to natural phrasing, enforce CJK spacing rules, tighten middle-dot usage, and ensure TikZ/table frames reset linespread to 1.0. Implement explicit guidelines for sectioning and labeling (e.g., avoid AI-tag phrases, keep natural framing, maintain proper frame separation).
  • Upgrade 8–11: Ensure Section 7 contains policy suggestions and practical implications with a strict list format, enforce non-use of AI-flavored prefixes (F1, C1, etc.), ensure theory foundations have at least two frames with explicit literature references and X→Y transmission chains, and maintain the X→M→Y framework placement after literature/theory sections.
  • Output rules: Deliver only .tex and figures/ folders; compile on Overleaf with XeLaTeX, twice for directory alignment; avoid extra scripts.
  • Usage triggers: invoked by requests like 做一份中文 PPT / Beamer (新版), 中文 Beamer 改进版 / chinese-ppt2, Retrofits, 防越界, etc.

When to use it

Use when you need a retrofit or new-generation Chinese Beamer deck aligned to the chinese-ppt2 rules, especially for academic presentations requiring strict typography and overflow control. Suitable for Overleaf compilation requirements mentioned above.

What it can touch

The skill touches LaTeX source files (.tex) and figures/ folders, and relies on tools: claude-code.

Caveats

The upgrade requires the use of xelatex with ctex and fandol fonts, specific CUFE template conventions, and careful preamble setup; it warns against inserting \selectfont within hooks due to known compilation issues. It mandates explicit label settings for enumerate and strict frame content budgeting to avoid overflow. No outcomes are promised beyond adherence to described steps and structure.

From the SKILL.md

# chinese-ppt2 ## 相对 chinese-ppt 的升级点(先读这一节) 本 skill 继承 chinese-ppt 的全部硬规则,并追加 7 项一级强规则。新规则均来自 实践中发现的排版问题与用户反馈,**不得关闭**。 ### 升级 1 — 全局行距与段距(强制) 导言区必须包含: ```latex \usepackage{enumitem} \usepackage{etoolbox} % 行距 1.3 + 段前/段后 3pt(对应 Word "多倍行距 1.3") \linespread{1.3} \setlength{\parskip}{3pt plus 1pt minus 0pt} \setlist[itemize]{topsep=3pt, itemsep=3pt, parsep=3pt, partopsep=0pt} % enumerate 必须显式指定 la

More from Auto-Empirical-Research-Skills
All skills →
About this skill
What does the chinese-ppt2 skill do?

Upgrade of chinese-ppt for Chinese Beamer decks (xelatex + ctex + fandol, CUFE template). Same 7-section outline and X→M→Y framework, but adds (a) mandatory 1.3 line-spacing + 3pt paragraph spacing, (b) overflow-prevention line budget + balanced split-frame rules, (c) prose rewrites that strip AI-ish "关键比较/理论映射" labels and redundant 章节括号注释, (d) stricter CJK-space + middle-dot rules, (e) retrofit workflow for existing chinese-ppt decks, (f) mandatory local linespread reset inside TikZ / table / fixed-geometry frames. Use for "做中文学术PPT 2 版"、"中文 Beamer 改进版"、"答辩 PPT chinese-ppt2"、"防越界 PPT"等请求。用户在

How do I install it?

Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill chinese-ppt --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going