Hermes 继续创时代！ literate programming 技能，SRE 事件指挥官、Spotify 原生控制、自主技能市场、Obsidian 身份层……全网程序员把 Hermes 玩成了下一代 Agent 文档神器 + 运维军团 + 音乐管家 + 技能创业平台 + 私人知识大脑。 宝藏干货： litprog-skill（https://github.com/tlehman/litprog-skill…） 代码+散文交织成可执行 notebook，多平台兼容。 “写文档再也不用两套系统”实锤了！ hermes-incident-commander（https://github.com/Lethe044/hermes-incident-commander…） 自主 SRE 指挥官：监控+诊断+自愈+cron。 生产环境 24/7 值班军团上线！ hermes-spotify-skill（https://github.com/Alexeyisme/hermes-spotify-skill…） Linux/Raspberry Pi 原生 Spotify 控制，无 daemon。 Agent 接管你的无头音响了！ hermes-skill-marketplace（https://github.com/Lethe044/hermes-skill-marketplace…） Agent 自己写、测、发技能，全生命周期自动化。 技能也要创业？太 meta 了！ personal-api-skill（https://github.com/beiyuii/personal-api-skill…） 30 秒把 Obsidian vault 变成 Agent 身份层。 私人笔记直接变“自我认知”上下文，隐私党福音！ // 为什么这些新进化体这么炸？ 这些项目全部已验证公开开放，共同点：全吃 Hermes 底层循环当 DNA，社区再疯狂补 literate coding、SRE 自愈、Spotify 集成、自主技能市场、个人身份层……生态卷速肉眼可见。

tlehman/litprog-skill

Source: https://github.com/tlehman/litprog-skill

Literate Programming Skill for Claude Code

A Claude Code skill that transforms codebases into literate programs. These are documents written for human comprehension that also generate the original source code.

What is Literate Programming?

Literate programming was invented by Donald Knuth in 1984. Knuth is the author of The Art of Computer Programming, creator of TeX, and winner of the 1974 Turing Award. He introduced literate programming as a paradigm where programs are written as essays for human readers, with code embedded in a narrative.

A literate program produces two outputs:

• Weave: Produce a readable document (PDF, HTML) with prose, diagrams, and syntax-highlighted code.
• Tangle: Extract runnable source files from the document.

The key insight: present code in psychological order. That is, the order that makes it easiest to understand, not the order the compiler needs.

What This Skill Does

• Installs as a Claude Code skill (via SKILL.md)
• Gives Claude the ability to analyze a codebase and produce a .lit.md file
• The .lit.md file weaves prose, Mermaid diagrams, LaTeX math, and syntax-highlighted code into a narrative
• Includes a tangler (scripts/tangle.ts) that extracts source files back from the .lit.md
• Includes a reverse-sync engine (scripts/untangle.ts) that updates the .lit.md when source files are edited directly
• Includes a PostToolUse hook (scripts/hook-reverse-sync.ts) for automatic reverse-sync in Claude Code
• Running /literate-programming on an existing .lit.md just weaves + tangles (idempotent)
• Supports PDF generation via Pandoc

Installation

Copy SKILL.md into your project’s .claude/skills/ directory:

git clone https://github.com/tlehman/litprog-skill.git
mkdir -p your-project/.claude/skills/
cp litprog-skill/SKILL.md your-project/.claude/skills/literate-programming.md

Claude Code automatically discovers skills from .claude/skills/ in your project root. After copying, the /literate-programming slash command will be available in any Claude Code session within that project.

Usage

Create a literate program

Ask Claude to create a literate program from your codebase:

/literate-programming

Claude will analyze your code, determine the best narrative order, and produce a .lit.md file with prose, diagrams, and named code chunks.

If a .lit.md already exists, running /literate-programming will just tangle and weave the existing file without recreating it.

Reverse-sync (automatic)

After creation, a PostToolUse hook is configured so that when you edit a source file directly, the changes are automatically synced back into the .lit.md and re-tangled. This keeps the .lit.md as the single source of truth.

The hook does NOT regenerate the PDF on every edit. To regenerate the PDF, run /literate-programming again.

Tangle (extract source code)

bun run scripts/tangle.ts project.lit.md --output-dir ./src/

This expands all root chunks and writes the source files. Verify by diffing against the original source.

Weave (generate PDF)

pandoc project.lit.md \
  -o project.pdf \
  --pdf-engine=xelatex \
  --filter mermaid-filter \
  --toc \
  --number-sections

Prerequisites for weave: pandoc, xelatex, mermaid-filter

For setup instructions, see references/pandoc-setup.md.

Why Use This?

• Optimized for reading: Code is read far more often than it is written. Literate programs optimize for reading.
• Explains the why: Forces the author to explain why, not just what. Every code block is preceded by prose that motivates its existence.
• Beautiful PDFs: Produces documents with diagrams and math alongside code.
• Architectural clarity: Reveals architectural decisions that comments and READMEs miss. The narrative structure shows how pieces fit together.
• Knowledge transfer: Useful for onboarding, code reviews, and preserving institutional knowledge. A new team member can read the literate program start to finish and understand the system.