REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
A lightweight desktop app to manage, sync, and organize AI agent skills across 50+ coding tools — Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
作者提供的原文
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/xingkongliang-skills-manager)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 skills-manager | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | xingkongliang | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 7,624 | 468,733 | 234,332 | 150,287 | 144,566 |
| 最近代码更新 | 2026年11月14日 | 2026年11月19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 |
xingkongliang 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 CodeCodexCursorGemini CLIGitHub CopilotWindsurfOpenCodeKiro
依据开发者 README 和 repo 中的文件夹
GitHub 账号 xingkongliang(个人),已创建 12 年
★ 7,624 星 · 代码最近更新 2026年11月14日
没有,都是纯文本文件,由 AI 阅读后照做
没有脚本,所以不会自己联网
没有发现 hook 或写入电脑设置的操作
根据仓库 commit f374817 中的文件自动检查(只读取文件,没有运行任何内容)。这不是安全保证,请自己阅读后再决定
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
无法上传到 claude.ai,因为描述超过 200 个字符(604 个字符)。请改用"让 AI 帮你安装"
复制这句话,粘贴到 Claude Code 的对话中
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
重新打开 Claude Code,输入 /manage-skills,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。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
npx skills add xingkongliang/skills-manager摘自开发者 README,会下载并运行开发者的代码
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
git clone --depth 1 https://github.com/xingkongliang/skills-manager.git /tmp/popnx-skill-xingkongliang-skills-manager-f374817 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-xingkongliang-skills-manager-f374817/skills/manage-skills' ~/.claude/skills/manage-skillsChatGPT 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
AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
把 manage-skills 文件夹放到 ~/.agents/skills/manage-skills
~ 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
git clone --depth 1 https://github.com/xingkongliang/skills-manager.git /tmp/popnx-skill-xingkongliang-skills-manager-f374817 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-xingkongliang-skills-manager-f374817/skills/manage-skills' ~/.agents/skills/manage-skillsChecked 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
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
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
git clone --depth 1 https://github.com/xingkongliang/skills-manager.git /tmp/popnx-skill-xingkongliang-skills-manager-f374817 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-xingkongliang-skills-manager-f374817/skills/manage-skills' ~/.agents/skills/manage-skills复制这句话,粘贴到 Cursor 的对话中
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
在 Cursor 的 Agent 聊天中输入 / 并选择 manage-skills
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
git clone --depth 1 https://github.com/xingkongliang/skills-manager.git /tmp/popnx-skill-xingkongliang-skills-manager-f374817 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-xingkongliang-skills-manager-f374817/skills/manage-skills' ~/.cursor/skills/manage-skills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 · 复制这句话,粘贴到应用的对话中
如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径
AI 会先说明要做什么,每一步都会征求你的同意
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
✓ 命令已检查 2026年11月18日
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: manage-skills
description: Manage the user's shared agent-skill library via skills-manager-cli — install, update, remove, deploy or undeploy skills per agent or into a project's own agent directories, manage presets, organize tags, search, and adopt existing skills. Use this whenever the user wants Claude Code, Codex, Cursor, or another agent to gain or lose a skill (globally or in one repo), wants to organize the central library, or asks what is installed or deployed. Prefer this over direct agent-folder installs because Skills Manager preserves source metadata, preset membership, updates, and cross-agent deployment state.
---
## Before doing anything
1. **Resolve the CLI first, then use the path it prints.** Run this once (POSIX
shell):
```bash
D="$HOME/.skills-manager/bin"
B="$D/skills-manager-cli"; [ -e "$B" ] || B="$B.exe" # .exe on Windows
if [ -s "$D/.version" ] && [ -x "$B" ]; then
echo "$B"
elif [ -s "$D/.version" ] || [ -e "$B" ]; then
echo BRIDGE_BROKEN
else
P="$(command -v skills-manager-cli 2>/dev/null || true)"
[ -x "$P" ] && echo "$P"
fi
```
**Substitute the printed path into every command below**, wherever the
examples write `$SM`. Do not carry `$SM` as a shell variable: each command
you run is a new shell, so an assignment made here is gone by the next one.
The three outcomes:
- **A path under `~/.skills-manager/bin`** — the desktop app published this
copy, and the `.version` stamp appears only after it has been verified, so
it always matches the app the user is running. Use it.
- **`BRIDGE_BROKEN`** — something the app left behind is here but does not
add up: an unstamped binary, or a stamp with no binary beside it. Either is
what a copy that failed half-way leaves. **Stop.** Do not go looking
for another CLI: that binary may predate a safety fix, and the machine has
a desktop app whose version nothing here can match. Ask the user to open
the Skills Manager app once, which republishes it.
- **A path from PATH** — nothing was ever published here, so there is no
stale copy to worry about: this is a CLI-only machine (a server install, a
standalone download, a hand-built binary). Use it, but note it can be
older than a desktop app if one is also installed.
If nothing is printed at all, this skill doesn't apply — fall back to
find-skills, or tell the user to install Skills Manager.
2. **Always pass `--json` when you parse output yourself.** Pretty-printed output is for the user; JSON is for you. Errors include `ok=false`, a stable `code`, and `message` on stderr with a non-zero exit code.
```bash
"$SM" --json skills list
```
### When a deployment is refused
A deploy that would overwrite something that is not ours is refused outright —
nothing at those paths is deleted, and nothing else in the batch is applied.
That failure is machine-readable, so report the actual paths rather than the
sentence:
```json
{"ok": false, "code": "TARGET_CONFLICT", "kind": "target_conflict",
"message": "Refusing to deploy: 1 of 2 target(s) …",
"details": {"conflicts": [{"path": "/Users/me/.claude/skills/db",
"reason": "is not a managed deployment"}]}}
```
Tell the user which path is in the way, that its contents are untouched, and
offer the two ways out: adopt it into the library (`skills adopt`), or move it
aside and retry. Never delete it for them.
The project commands refuse the same way, with these `reason`s:
| reason | from | what to tell the user |
|---|---|---|
| `exists and is not this library skill` | `projects deploy` | that directory holds something else; it was left alone and nothing in the batch was written |
| `skills "…" (…) and "…" (…) would both be written here` | `projects deploy` | two library skills have the same directory name and only one can live there; ask the user which one, then deploy just that one |
| `has content not in the library (…)` | `projects undeploy` | the project copy may have edits, extra files (`.gitignore`, `.git`, links) or be a link the user made to somewhere else; `projects import` it first, or remove it with `--force` only if they say it can go |
| `library copy differs from the project copy` | `projects import` | importing would overwrite the library version; `--force` only if they want the project version to win |
| `another copy of this skill also differs from the library` | `projects import` | several agents' copies were edited differently; they must pick one by hand |
Never add `--force` on your own.
## Mental model
There's **one central library** at `~/.skills-manager/skills/` that all agents share. Each skill has source metadata, preset membership, tags, and zero or more real deployments in agent directories. A **preset** is a reusable group; several presets may be deployed at the same time.
Keep these three states separate:
- **Library**: install/remove controls whether Skills Manager owns the skill.
- **Preset membership**: `presets add-skill/remove-skill` organizes the library only.
- **Deployment**: `skills deploy/undeploy` and `presets deploy/undeploy` control what an agent can actually see.
**Project deployments are a separate thing.** `projects deploy` puts a library skill into one project's agent directory (e.g. `<repo>/.claude/skills`). It is not recorded as a deployment: `skills status` and `deployed_to` never show it; read it with `projects show`. Deploying a preset into a project copies its current members once and makes no lasting link.
Internally, presets are still stored as scenarios for backward-compatible Git Backup. The CLI and UI call them presets.
## Install
```bash
# From skills.sh marketplace
"$SM" skills install vercel-labs/agent-skills@react-best-practices
# Any git URL (use /tree/branch/subpath form when the skill lives in a sub-directory)
"$SM" skills install https://github.com/anthropics/skills.git
"$SM" skills install https://github.com/foo/bar/tree/main/skills/baz
# Local folder
"$SM" skills install ./my-skill
# Force a source type when the ref is ambiguous
"$SM" skills install foo/bar --skillssh
"$SM" skills install ./looks-like/owner-repo --local
```
**Default is library-only** — the skill enters the DB but doesn't appear in any agent yet. Prefer an explicit follow-up deployment so scope is unambiguous:
```bash
"$SM" skills deploy <skill> --agent claude_code --agent codex
```
`--sync` and `--sync-preset` remain legacy shortcuts for the exclusive active-preset workflow.
**Ref resolution** is deterministic, no path-existence guessing:
1. Starts with `./`, `../`, `/`, or `~/` → local path
2. Contains `://`, ends in `.git`, or starts with `git@` → git URL
3. Matches `owner/repo`, `owner/repo/skill`, or `owner/repo@skill` → skillssh
4. Otherwise → error; pass `--local` / `--git` / `--skillssh` to disambiguate
**Always verify after install** with `skills list` or `skills show <name>` so you can confirm the skill landed and report the preset / sync state back to the user.
## Search
```bash
"$SM" --json skills search "react performance" --limit 5
```
Each result has `install_ref` (paste straight into `skills install`), `installs` (popularity proxy), and `skills_sh_url`. Show the top 1–3 with install counts before installing — anything with 10K+ installs is battle-tested; anything under 100 needs a careful look at the source repo.
## Update / Check
```bash
# Re-fetch one skill (git/skillssh re-clones, local/import re-imports source dir)
"$SM" skills update <skill-name-or-id>
# Re-fetch all eligible skills
"$SM" skills update --all
# Just probe remote revisions, don't touch files
"$SM" skills check --all
```
`check` is the dry-run partner of `update`. A skill installed from a local folder is compared with that folder, not with any Git remote: `update_available` means the folder changed since it was imported, and `source_missing` means the folder is gone. This check always runs; the cac提问、分享技巧或报告无法使用。按“有帮助”数量排序。