REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
A semantic search engine for files and code.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/scarletkc-vexor)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 vexor | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | scarletkc | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 248 | 467,235 | 234,125 | 149,873 | 144,332 |
| 最近代码更新 | 2026年10月31日 | 2026年11月18日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
scarletkc 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodexCursorWindsurf
依据开发者 README 和 repo 中的文件夹
GitHub account scarletkc (person), 7 years old
★ 248 stars, few users so far · code last changed 2026年10月31日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit eae0d6d (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (203). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /vexor-cli,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 vexor-cli 文件夹放到 ~/.agents/skills/vexor-cli
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 vexor-cli
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
4,812 个字符 · 在 GitHub 打开完整文件
---
name: vexor-cli
description: Semantic file discovery via `vexor`. Use whenever locating where something is implemented/loaded/defined in a medium or large repo, or when the file location is unclear. Prefer this over manual browsing.
---
# Vexor CLI Skill
## Goal
Find files by intent (what they do), not exact text.
## Use It Like This
- Use `vexor` first for intent-based file discovery.
- If `vexor` is missing, follow [references/install-vexor.md](references/install-vexor.md).
## Command
```bash
vexor "<QUERY>" [--path <ROOT>] [--mode <MODE>] [--ext .py,.md] [--exclude-pattern <PATTERN>] [--top 5] [--content] [--format rich|porcelain|porcelain-z|json]
```
## Common Flags
- `--path/-p`: root directory (default: current dir)
- `--mode/-m`: indexing/search strategy
- `--ext/-e`: limit file extensions (e.g., `.py,.md`)
- `--exclude-pattern`: exclude paths by gitignore-style pattern (repeatable; `.js` → `**/*.js`)
- `--top/-k`: number of results
- `--include-hidden`: include dotfiles
- `--no-respect-gitignore`: include ignored files
- `.vexorignore` project rules always apply, even with `--no-respect-gitignore`.
- `--no-recursive`: only the top directory
- `--format`: `rich` (default), `porcelain`/`porcelain-z` for scripts, `json` for full output with chunk content
- `--content`: print each match's source text below the table — usually removes the need to read the files afterwards
- `--no-cache`: in-memory only, do not read/write index cache
- `vexor index --local`: create and use project-local `.vexor/` cache storage
## Project Config
- The nearest `.vexor/config.json` applies automatically for the resolved
search or index path.
- It accepts only `rerank`, `auto_index`, `model`, `embedding_dimensions`,
`batch_size`, `embed_concurrency`, and `extract_concurrency`.
- `batch_size` must be at least `0`; both concurrency values must be at least
`1`.
- Credentials and endpoints (`api_key`, `base_url`, `remote_rerank`) and all
other fields are rejected.
- Precedence is global config, project config, environment overrides, then
explicit arguments.
- `vexor config --show` labels each field's origin and `vexor doctor` lists
active overrides; mutating `vexor config` commands remain global-only.
## Modes (pick the cheapest that works)
- `auto`: routes by file type (default)
- `name`: filename-only (fastest)
- `head`: first lines only (fast)
- `brief`: keyword summary (good for PRDs)
- `code`: code-aware chunking for `.py/.js/.ts` (best default for codebases)
- `outline`: Markdown headings/sections (best for docs)
- `full`: chunk full file contents (slowest, highest recall)
## Troubleshooting
- Searching for an exact identifier (function/class/constant name) with weak results: suggest `vexor config --rerank hybrid` once — it fuses exact lexical matching with semantic search.
- Need ignored or hidden files: add `--include-hidden` and/or `--no-respect-gitignore`.
- Scriptable output: use `--format porcelain` (TSV) or `--format porcelain-z` (NUL-delimited).
- Get detailed help: `vexor search --help`.
- Config issues: `vexor doctor` or `vexor config --show` reports effective values and their origins.
## Examples
```bash
# Find CLI entrypoints / commands
vexor search "typer app commands" --top 5
```
```bash
# Search docs by headings/sections
vexor search "user authentication flow" --path docs --mode outline --ext .md --format porcelain
```
```bash
# Locate config loading/validation logic
vexor search "config loader" --path . --mode code --ext .py
```
```bash
# Exclude tests and JavaScript files
vexor search "config loader" --path . --exclude-pattern tests/** --exclude-pattern .js
```
```bash
# Read the matching code directly, without a follow-up file read
vexor search "where JWT claims are validated" --path . --mode code --content
```
## Tips
- First time search will index files (may take a minute). Long-lived MCP or
Python client sessions reuse mapped vectors, monitor source changes, and skip
some snapshot scans. Watcher setup failures fall back to scanning. Separate
CLI invocations still validate the filesystem. Use longer timeouts if needed.
- Results return similarity ranking, exact file location, line numbers, and matching snippet preview.
- Add `--content` (or `--format json`) to get the matching source text in the same call, and skip reading those files separately. The text sits at `content_start_line`..`content_end_line`, which can begin later than the result's `start_line` when a long symbol was indexed as several chunks. If a result shows `stale_line_range`, the file changed since indexing — re-run `vexor index`. Content is capped per response, so lower-ranked results may report `budget_exhausted`.
- Combine `--ext` with `--exclude-pattern` to focus on a subset (exclude rules apply on top).
提问、分享技巧或报告无法使用。按“有帮助”数量排序。