仓库打包
Repomix
by bytesagain1
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perf repo-bundler, typescript, ai, anthropic.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/bytesagain1/repo-bundler文档
Repo Bundler
📦 Repo Bundler v2.0.0 is a utility toolkit for bundling, analyzing, converting, and managing repository data. It provides a thorough CLI with timestamped logging, data export in multiple formats, and full activity history tracking.
Commands
All commands accept optional <input> arguments. When called without arguments, they display recent entries from their respective logs. When called with input, they record a new timestamped entry.
| Command | Usage | Description |
|---|---|---|
run | repo-bundler run [input] | Run a bundler operation and log the result |
check | repo-bundler check [input] | Check repository state or validate input |
convert | repo-bundler convert [input] | Convert data between formats |
analyze | repo-bundler analyze [input] | Analyze repository structure or content |
generate | repo-bundler generate [input] | Generate output files or reports |
preview | repo-bundler preview [input] | Preview bundler output before committing |
batch | repo-bundler batch [input] | Process multiple items in batch mode |
compare | repo-bundler compare [input] | Compare two repositories or snapshots |
export | repo-bundler export [input] | Log an export operation |
config | repo-bundler config [input] | Manage configuration settings |
status | repo-bundler status [input] | Log or view status entries |
report | repo-bundler report [input] | Generate or log reports |
Utility Commands
| Command | Usage | Description |
|---|---|---|
stats | repo-bundler stats | Show summary statistics across all log files |
export <fmt> | repo-bundler export json|csv|txt | Export all data in JSON, CSV, or plain text format |
search <term> | repo-bundler search <term> | Search across all log entries (case-insensitive) |
recent | repo-bundler recent | Show the 20 most recent activity entries |
status | repo-bundler status | Health check — version, data dir, entry count, disk usage |
help | repo-bundler help | Show full command reference |
version | repo-bundler version | Print version string (repo-bundler v2.0.0) |
Data Storage
All data is stored locally in ~/.local/share/repo-bundler/:
history.log— Master activity log with timestamps for every operationrun.log,check.log,convert.log, etc. — Per-command log files storingtimestamp|inputentriesexport.json,export.csv,export.txt— Generated export files
Each entry is stored in pipe-delimited format: YYYY-MM-DD HH:MM|value. The data directory is created automatically on first use.
Requirements
- Bash 4.0+ (uses
set -euo pipefail,localvariables) - Standard Unix tools:
date,wc,du,tail,grep,sed,basename,cat - No external dependencies, API keys, or network access required
- Works on Linux, macOS, and WSL
When to Use
- Bundling a repository for AI consumption — Use
runto process and pack repo contents into a single file suitable for LLM context windows - Analyzing repository structure — Use
analyzeto examine file counts, directory layout, and content patterns across a codebase - Comparing repository snapshots — Use
compareto track differences between two versions or branches of a repository bundle - Batch processing multiple repos — Use
batchto queue and process several repositories in sequence with logged results - Exporting bundler history for auditing — Use
export jsonto generate a structured record of all bundler operations for compliance or review
Examples
# Bundle a repository and log the operation
repo-bundler run my-project-v2.3
# Analyze repository structure
repo-bundler analyze ./src --depth=3
# Compare two repository snapshots
repo-bundler compare main-branch feature-branch
# Batch process multiple repos
repo-bundler batch repo1 repo2 repo3
# Export all history as JSON
repo-bundler export json
# Search for a specific entry across all logs
repo-bundler search "my-project"
# View summary statistics
repo-bundler stats
# Check system health
repo-bundler status
Output
All commands output structured text to stdout. Use standard shell redirection to capture output:
repo-bundler stats > summary.txt
repo-bundler export json # writes to ~/.local/share/repo-bundler/export.json
Powered by BytesAgain | bytesagain.com | hello@bytesagain.com
相关 Skills
技能工坊
by anthropics
覆盖 Skill 从创建到迭代优化全流程:起草能力、补测试提示、跑评测与基准方差分析,并持续改写内容和描述,提升效果与触发准确率。
✎ 技能工坊把技能从创建、迭代到评测串成闭环,方差分析加描述优化,特别适合把触发准确率打磨得更稳。
PPT处理
by anthropics
处理 .pptx 全流程:创建演示文稿、提取和解析幻灯片内容、批量修改现有文件,支持模板套用、合并拆分、备注评论与版式调整。
✎ 涉及PPTX的创建、解析、修改到合并拆分都能一站搞定,连备注、模板和评论也能处理,做演示文稿特别省心。
PDF处理
by anthropics
遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。
✎ PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。
相关 MCP 服务
文件系统
编辑精选by Anthropic
Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。
✎ 这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。
by wonderwhy-er
Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。
✎ 这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。
EdgarTools
编辑精选by dgunning
EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。
✎ 这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。