Token导航 LogoToken导航

Agent Skill · 研究检索

skills-manager(技能经理)

skills-manager 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

skills-manager 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 59,464。

总安装 388周安装 16GitHub Stars 6下载 127核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skills-manager(技能经理)
来源仓库:https://github.com/tc9011/skills-manager
仓库路径:skills/skills-manager
安装命令:
npx skills add https://github.com/tc9011/skills-manager --skill skills-manager
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/tc9011/skills-manager --skill skills-manager

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,支持技能管理与内容定位。适合在 Codex、Claude、Cursor、Gemini CLI 中进行技能相关信息的快速检索。通过 npx skills add 命令从 GitHub 仓库安装。使用前需确认权限范围、维护状态及是否触发联网或文件操作。

skills-manager 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/skills-manager

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/tc9011/skills-manager --skill skills-manager;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

skills-manager 怎么安装?

在终端执行 npx skills add https://github.com/tc9011/skills-manager --skill skills-manager。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

skills-manager 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

skills-manager 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

skills-manager 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

skills-manager 用的人多吗?

公开数据是累计安装 388 次,近一周安装 16 次,下载 127 次,GitHub 6 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

skills-manager 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
skills-manager

技能经理 · 本页

3886接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

skills-manager CLI

CLI companion to vercel-labs/skills — backup, restore, and symlink AI agent skills via GitHub.

Scope boundary: This tool backs up and syncs skills you already have. It does NOT install new skills from the registry — that's npx skills add. If the user wants to install a new skill, point them to npx skills add <repo> instead.

Quick Reference

GoalCommand
Backup skills to GitHubsm push
Restore skills on new machinesm pull --repo owner/name
Re-link skills to agentssm link
Link skills to a projectsm link --project

Invocation

# If globally installed
sm push          # short alias
skills-manager push  # full name

# Without installing — use the bundled wrapper script
export SM="$HOME/.agents/skills/skills-manager/scripts/sm.sh"
"$SM" push

Requires Node.js >= 20. GitHub CLI (gh) recommended for auth.

If neither sm nor skills-manager is found, install first:

npm install -g @tc9011/skills-manager

Key Paths

PathPurpose
~/.agents/Git repo root (push/pull target)
~/.agents/skills/Canonical skills directory
~/.agents/.skill-lock.jsonLock file (READ ONLY — owned by vercel-labs/skills)

Authentication

Auth is optional. If git already has credentials configured (SSH keys, macOS Keychain, credential manager, etc.), push/pull work without any extra setup.

When git cannot authenticate on its own, the CLI looks for a token in this order:

  1. gh auth token — GitHub CLI (recommended)
  2. $GITHUB_TOKEN — environment variable
  3. $GH_TOKEN — environment variable

If none are found, git attempts the operation without a token — this works for public repos but fails for private ones.

The link command never requires authentication.

Fixing Auth Failures

If push/pull fails with a permission or authentication error:

  1. Check if gh is installed: run gh --version
  2. If gh exists: run gh auth login to authenticate, then retry
  3. If gh missing: set a token: export GITHUB_TOKEN=ghp_your_token_here, then retry
  4. If using SSH: ensure ~/.ssh/ has a valid key added to GitHub and origin uses the git@github.com: URL format

Tokens are used transiently in-memory — they are never persisted to .git/config.

Commands

push

Commit and push ~/.agents/ to GitHub.

sm push                    # auto-generated commit message
sm push -m "add new skill" # custom message

First-time behavior:

  1. If ~/.agents/ is not a git repo, auto-runs git init
  2. If no origin remote exists, prompts for owner/name
  3. If gh CLI is installed, offers to create the repo on GitHub automatically
  4. If gh is not installed, shows a note telling the user to create the repo manually at https://github.com/new

Possible outcomes:

  • Skills pushed successfully! — new commit created and pushed
  • Unpushed commits pushed successfully! — working tree clean, but local was ahead
  • No changes to push — already up to date. — nothing new
  • Push rejected — see Troubleshooting below

pull

Pull from GitHub. Auto-runs link afterward unless --skip-link is passed.

sm pull --repo owner/name  # first time — specify repo
sm pull                    # subsequent runs — uses existing remote
sm pull --skip-link        # pull only, don't re-link

First-time behavior:

  • If no --repo and no existing origin remote, prompts for owner/name
  • If ~/.agents/ doesn't exist yet, clones into it

Possible outcomes:

  • Skills cloned successfully! — fresh clone on new machine, auto-runs link
  • Skills updated from remote. — pulled new changes, auto-runs link
  • Already up to date. — no new changes, skips link
  • Rebase conflict — see Troubleshooting below

link (global mode)

Read .skill-lock.json, create relative symlinks from each agent's global skills directory to ~/.agents/skills/.

sm link                              # interactive prompt
sm link --agents cursor opencode     # non-interactive, skip prompt

Interactive behavior:

The agent selector has two sections:

  1. Locked section — 10 universal agents (amp, cline, codex, cursor, gemini-cli, github-copilot, kimi-cli, opencode, replit, universal) are always included because they share ~/.agents/skills/ as their path.
  2. Searchable list — 31 non-universal agents. Type to search/filter.

Pre-selection priority: saved config > .skill-lock.json > agents already existing on disk.

When --agents is provided, the interactive prompt is skipped entirely. Use this for scripting and AI agent automation:

sm link --agents cursor opencode claude-code

link --project

Link or copy skills to the current working directory.

sm link --project                                                       # interactive
sm link --project --agents cursor claude-code --skills my-skill         # non-interactive (copy is default)
sm link --project --agents cursor claude-code --skills my-skill --mode symlink  # explicit symlink

Interactive flow (3 steps):

  1. Select skills (--skills to skip) — choose which skills to include
  2. Select copy/symlink — in practice this prompt is skipped because --mode defaults to copy in the CLI. Only appears if linkCommand is called programmatically without defaults
  3. Select agents (--agents to skip) — same searchable multiselect with locked universal section

Copy vs symlink:

  • copy (default, recommended) — creates independent files in project. Overwrites existing skill dirs
  • symlink — creates absolute symlinks pointing to ~/.agents/skills/. Existing non-symlink dirs are skipped

Agents that share the same projectPath (e.g., trae and trae-cn both use .trae/skills) are deduplicated — one operation per unique path.

For AI agents: the fully non-interactive version is almost always what you want:

sm link --project --agents cursor opencode claude-code --skills my-skill --mode copy

Common Workflows

First-time setup on a new machine

npm install -g @tc9011/skills-manager
sm pull --repo owner/my-skills   # clone + auto-link

Daily sync

sm pull    # fetch latest + re-link
sm push    # backup local changes

Project-level skills

cd /path/to/project
sm link --project --skills my-skill --agents cursor opencode claude-code

Re-link after installing new skills

npx skills add some-repo       # install via vercel-labs/skills
sm link                         # re-link to all agents
sm push                         # backup the new skill

Troubleshooting

Push rejected (remote ahead)

Error: Push rejected — remote contains commits that you do not have locally.

Fix:

sm pull      # pulls and rebases
sm push      # retry

Or manually:

cd ~/.agents
git pull --rebase origin main
sm push

Rebase conflict on pull

Error: Rebase conflict detected. Your local skills have diverged from the remote.

The CLI auto-aborts the failed rebase. To resolve:

cd ~/.agents
git fetch origin
git rebase origin/main     # resolve conflicts manually
# OR if you want to discard local changes:
git reset --hard origin/main

No skills found

Error: No skills found in ~/.agents/skills.

This means ~/.agents/skills/ is empty or doesn't exist. Either:

  • Run sm pull --repo owner/name to restore from backup
  • Install skills via npx skills add <repo>

Unknown agent IDs

Error: Unknown agent ID(s): foo. Run with no --agents to see available IDs.

The --agents flag only accepts valid agent IDs from the 46-agent registry. Run sm link without --agents to see the interactive list.

Auth failure during push/pull

Symptom: Git errors like Authentication failed, Permission denied, or Repository not found.

This means git has no credentials and no token was found. See the "Fixing Auth Failures" section above.

~/.agents/ is not a git repo

On first push or pull, the CLI auto-initializes git. If this somehow fails:

cd ~/.agents
git init
git remote add origin https://github.com/owner/my-skills.git
sm push

Supported Agents (41)

  • 10 universal (always locked in interactive prompts): amp, cline, codex, cursor, gemini-cli, github-copilot, kimi-cli, opencode, replit, universal
  • 31 non-universal (appear in searchable list): claude-code, windsurf, trae, roo, augment, continue, goose, kilo, kode, and more

Constraints

  • .skill-lock.json is READ ONLY — never create, modify, or delete it
  • ~/.agents/ is the git repo root (not ~/.agents/skills/)
  • Global link = relative symlinks; project link = absolute symlinks or copies
  • Auth tokens are transient in-memory only — never persisted to .git/config
  • This tool does NOT install skills from the registry — use npx skills add for that

平台分布

Codex

36.02%
按下载量换算46

Claude

29.91%
按下载量换算38

Cursor

19.97%
按下载量换算25

Gemini CLI

8.72%
按下载量换算11

安全审计

Gen Agent Trust Hub

可疑

Socket

可疑

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills