caveman-compress：AI 文本压缩工具，优化 Claude 输入令牌，提升效率

caveman-compress by juliusbrussee/caveman

1,500 周安装量

5,300 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/juliusbrussee/caveman --skill caveman-compress

命令行工具生产力自然语言处理

🇨🇳中文介绍

原始人压缩

目的

将自然语言文件（CLAUDE.md、待办事项、偏好设置）压缩成原始人语言，以减少输入令牌数。压缩版本会覆盖原始文件。人类可读的备份保存为 <文件名>.original.md。

触发方式

/caveman-compress <文件路径> 或当用户要求压缩记忆文件时。

处理流程

此 SKILL.md 文件与 memory/ 目录位于同一目录中。找到该目录。
运行：

cd <包含此_SKILL.md_的目录> && python3 -m scripts <绝对文件路径>
CLI 将执行以下操作：
- 检测文件类型（不消耗令牌）
- 调用 Claude 进行压缩
- 验证输出（不消耗令牌）
- 如果出错：使用 Claude 进行针对性修复（仅进行针对性修复，不重新压缩）
- 最多重试 2 次
将结果返回给用户

压缩规则

移除

冠词：a, an, the
填充词：just, really, basically, actually, simply, essentially, generally
客套话："sure", "certainly", "of course", "happy to", "I'd recommend"
模棱两可的表达："it might be worth", "you could consider", "it would be good to"

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

完全保留（绝不修改）

代码块（用 ``` 分隔的代码块和缩进代码块）
行内代码（反引号内容）
URL 和链接（完整 URL，Markdown 链接）
文件路径（/src/components/..., ./config.yaml）
命令（npm install, git commit, docker build）
技术术语（库名、API 名称、协议、算法）
专有名词（项目名称、人名、公司名）
日期、版本号、数值
环境变量（$HOME, NODE_ENV）

所有 Markdown 标题（保持标题文本原样，压缩下方正文）
项目符号层级（保持嵌套级别）
编号列表（保持编号）
表格（压缩单元格文本，保持结构）
Markdown 文件中的 Frontmatter/YAML 头部

使用简短同义词："big" 而不是 "extensive"，"fix" 而不是 "implement a solution for"，"use" 而不是 "utilize"
允许使用片段："Run tests before commit" 而不是 "You should always run tests before committing"
去掉 "you should", "make sure to", "remember to" — 直接陈述动作
合并用不同方式表达相同意思的冗余项目符号
在多个示例展示相同模式时，只保留一个示例

关键规则：... 内的任何内容必须完全复制。不得：

删除注释
删除空格
重新排序行
缩短命令
简化任何内容

行内代码（...）必须完全保留。不要修改反引号内的任何内容。

如果文件包含代码块：

将代码块视为只读区域
仅压缩代码块外的文本
不要合并代码块周围的章节

You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.

Run tests before push to main. Catch bugs early, prevent broken prod deploys.

The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens.

Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens.

仅压缩自然语言文件（.md, .txt, 无扩展名文件）
绝不修改：.py, .js, .ts, .json, .yaml, .yml, .toml, .env, .lock, .css, .html, .xml, .sql, .sh
如果文件包含混合内容（散文 + 代码），仅压缩散文部分
如果不确定某内容是代码还是散文，保持原样不变
原始文件在覆盖前会备份为 FILE.original.md
绝不压缩 FILE.original.md（跳过它）

🇺🇸English

Caveman Compress

Purpose

Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as <filename>.original.md.

Trigger

/caveman-compress <filepath> or when user asks to compress a memory file.

Process

This SKILL.md lives alongside memory/ in the same directory. Find that directory.
Run:

cd <directory_containing_this_SKILL.md> && python3 -m scripts <absolute_filepath>
The CLI will:
- detect file type (no tokens)
- call Claude to compress
- validate output (no tokens)
- if errors: cherry-pick fix with Claude (targeted fixes only, no recompression)
- retry up to 2 times
Return result to user

Compression Rules

Remove

Articles: a, an, the
Filler: just, really, basically, actually, simply, essentially, generally
Pleasantries: "sure", "certainly", "of course", "happy to", "I'd recommend"
Hedging: "it might be worth", "you could consider", "it would be good to"
Redundant phrasing: "in order to" → "to", "make sure to" → "ensure", "the reason is because" → "because"
Connective fluff: "however", "furthermore", "additionally", "in addition"

Preserve EXACTLY (never modify)

Code blocks (fenced ``` and indented)
Inline code (backtick content)
URLs and links (full URLs, markdown links)
File paths (/src/components/..., ./config.yaml)
Commands (npm install, git commit, docker build)
Technical terms (library names, API names, protocols, algorithms)
Proper nouns (project names, people, companies)
Dates, version numbers, numeric values
Environment variables ($HOME, NODE_ENV)

Preserve Structure

All markdown headings (keep exact heading text, compress body below)
Bullet point hierarchy (keep nesting level)
Numbered lists (keep numbering)
Tables (compress cell text, keep structure)
Frontmatter/YAML headers in markdown files

Compress

Use short synonyms: "big" not "extensive", "fix" not "implement a solution for", "use" not "utilize"
Fragments OK: "Run tests before commit" not "You should always run tests before committing"
Drop "you should", "make sure to", "remember to" — just state the action
Merge redundant bullets that say the same thing differently
Keep one example where multiple examples show the same pattern

CRITICAL RULE: Anything inside ... must be copied EXACTLY. Do not:

remove comments
remove spacing
reorder lines
shorten commands
simplify anything

Inline code (...) must be preserved EXACTLY. Do not modify anything inside backticks.

If file contains code blocks:

Treat code blocks as read-only regions
Only compress text outside them
Do not merge sections around code

Pattern

Original:

You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production.

Compressed:

Run tests before push to main. Catch bugs early, prevent broken prod deploys.

Original:

The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens.

Compressed:

Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens.

Boundaries

ONLY compress natural language files (.md, .txt, extensionless)
NEVER modify: .py, .js, .ts, .json, .yaml, .yml, .toml, .env, .lock, .css, .html, .xml, .sql, .sh
If file has mixed content (prose + code), compress ONLY the prose sections
If unsure whether something is code or prose, leave it unchanged
Original file is backed up as FILE.original.md before overwriting
Never compress FILE.original.md (skip it)

Weekly Installs

1.5K

Repository

juliusbrussee/caveman

GitHub Stars

5.3K

First Seen

1 day ago

Security Audits

Gen Agent Trust HubPass SocketPass SnykFail

Installed on

cursor1.3K

github-copilot1.3K

opencode1.3K

codex1.3K

antigravity1.2K

cline1.2K

Python PDF处理教程：合并拆分、提取文本表格、创建PDF文件

65,000 周安装