ljg-present

ljg-present is a skill for Claude Code from lijigang/ljg-skills. It costs 144 tokens per session (3,777 once invoked), scanned A, original, MIT.

A presentation generator that turns an Org-mode, Markdown, or plain-text outline into a single offline HTML slide deck. Org-mode is a plain-text format for structured notes and documents.

In plain words
What is it for?
Use it to make presentations with cover and section pages, large text, tables, code, ASCII diagrams, LaTeX, page numbers, and offline viewing.
Why use it?
It preserves the outline's wording and order while controlling pagination, layout, spacing, themes, and readability for projected slides.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the ljg-skills plugin — 22 skills shipped together

Good fit Use it to make presentations with cover and section pages, large text, tables, code, ASCII diagrams, LaTeX, page numbers, and offline viewing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lijigang/ljg-skills/ljg-present
About the project

ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.

lijigang/ljg-skills · 7,340 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add lijigang/ljg-skills --skill ljg-present
Clone the repo
git clone --depth 1 https://github.com/lijigang/ljg-skills

Made for: Claude Code.

Or install ljg-skills, the plugin that ships this one along with the rest of its 22 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ljg-present

README.md
[![agentmods](https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-present/github.svg)](https://agentmods.dev/skills/lijigang/ljg-skills/ljg-present)
Your own site
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-present"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-present/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ljg-present

Your own site · 80×15
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-present"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-present.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 8 May 2026
  • Snyk warn 8 May 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00144 $0.03777
Opus 5 $0.00072 $0.01888
Sonnet 5 $0.00029 $0.00755
Haiku 4.5 $0.00014 $0.00378

Measured 12d ago against content hash 3101e6725c5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ljg-present scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (Tools/ValidateDeck.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ljg-present/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ljg-present:演讲铸造器

把 outline 铸成舞台。内容由作者决定,skill 只决定它如何被看见。

核心契约

Outline 是真理,Skill 是渲染器。

  • 标题、段落、列表项、引用不改字。
  • 表格不改结构,example/代码块不改空格与换行。
  • 所有源元素按原顺序出现;不抽提、不浓缩、不重排。
  • 唯一允许改变的是物理分页与视觉构图。
  • #+title: 是文档标题,必须先生成独立 cover;第一个 outline 节点仍在下一页。若两者文字完全相同,可合并为 cover,不能重复。

Workflow Routing

Workflow Trigger File
Generate 讲这个、present、做成演讲、slides、按 outline 美化、生成 HTML 演示 Workflows/Generate.md

生成时先读 RenderingSpec.md,再使用根目录 SloganTemplate.html。不要根据记忆重造模板。

Quick Reference

输入与输出

  • 输入:Orgmode、Markdown 或纯文本。
  • 输出:~/Downloads/{title}.html,单文件、离线、无外链资源。
  • 首屏:文档标题 cover。
  • 空间节奏:所有文字页共享稳定中轴;cover 与章节页靠深浅色场、字号和居中短信号线区分。
  • Header:不承载任何信息。
  • Footer:首页显示页码与 subtitle/meta;其他页只显示页码。

Theme

优先级:显式参数 > #+filetags: > 默认 black

参数 theme 调性
-b / --theme=black black 沉思、论证
-r / --theme=red red 宣言、号召
-y / --theme=yellow yellow 反讽、警觉
--hacker hacker 逆向工程实验纸
--cyber hacker 兼容别名;不再生成 CRT/HUD
--theme=hacker-dark hacker-dark 低眩光深色终端;全页暗场、柔和灰绿正文

Hacker 有两个静态阅读变体。二者都拒绝荧光特效堆叠:

--hacker-void:   #07110D;
--hacker-paper:  #EAF4EC;
--hacker-signal: #00C46A;

--hacker-dark-bg:     #06110D;
--hacker-dark-deep:   #020806;
--hacker-dark-panel:  #0A1A13;
--hacker-dark-fg:     #CFE1D5;
--hacker-dark-signal: #25E981;

hacker 的普通页使用浅色实验纸;hacker-dark 的所有页面使用深色场,cover 与一级章节再压深一档。暗色正文不是纯白,而是柔和灰绿;信号绿只承担居中信号轨、重点和表格标签。不要矩阵雨、发光描边、伪 HUD 或闪烁光标。

Outline 映射

Source Page
* 一级标题 独占 emphasis 章节页
** 及更深标题 独占 title 页;深度越高字号越低
段落 theme 文本页;仅在必要时物理拆页
列表 同层级连续 3–4 项优先整组同页;更长列表切成 3–4 项一页且避免单项尾页
表格 table 页;超过 6 行分页并重复表头
引用 quote 页;超过 2 个原始行时续页并记录 sourceParts
#+begin_example / fenced code pre 页,逐字符保留
*强调* / ~code~ / =verbatim= hl: true;emphasis 页忽略 inline hl

多行不是统一降字号

多行页同时看「行数」和「文本密度」,但始终使用单列 rows

  • 2、3、4 行全部沿页面中轴纵向排列,不在翻页时切换左右阅读路径。
  • 字号由「行数 + light/medium/dense」复合规则决定;先拆页、再放大,最后才由 fit guard 微调。
  • 单行、非列表、非整行公式且去空白后 ≤16 个字形的内容先判为「语义原子」:即使 CJK 权重落入 long,也整句单行并进入高桥流。
  • 连续同层级列表先保语义块:3–4 项整组同页;超过 4 项时切成 3–4 项,并避免把最后一项单独遗留。
  • 网格项必须 min-width: 0,正文自然换行;不要把 .line 设成 flex/grid,以免拆散高亮与公式。
  • 单行 single/short/medium 使用「高桥流」:少字就是主视觉,横屏有效字号以 ≥90px 为目标。

Read the full file on GitHub · 205 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 205 lines · 144 tokens per session scan A 3101e6725c5e

Subscribe to this mod's changes

ljg-present is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 3d ago), licensed MIT. It adds 144 tokens to every session and 3,777 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories