Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计提醒

skill-library技能库

Agent Skill

skill-library 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。

总安装

927

周安装

39

GitHub Stars

216

下载量

324
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:skill-library(技能库)
来源仓库:https://github.com/mathews-tom/armory
仓库路径:skills/skill-library
安装命令:
npx skills add https://github.com/mathews-tom/armory --skill skill-library
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/mathews-tom/armory --skill skill-library

简介

skill-library 用于查找、检索和筛选相关信息,适合在资源库或知识库管理中快速定位可用材料。

  • 支持基于关键词、分类或来源筛选内容,提升信息组织效率。
  • 通过 npx skills add 命令从 GitHub 仓库安装,需确认仓库路径与访问权限。
  • 使用前建议检查维护状态,避免依赖已失效或存在安全风险功能。
  • 注意是否涉及外部 API 调用,确保符合本地网络与权限策略。

SKILL.md

Package Library

Agent-native catalog and installer for all armory package types. Provides browsing, searching, installing, updating, syncing, and removing packages directly within an agent session.

Variables

  • ARMORY_REPO: Mathews-Tom/armory
  • ARMORY_BRANCH: main
  • ARMORY_CATALOG_URL: https://raw.githubusercontent.com/{ARMORY_REPO}/{ARMORY_BRANCH}/manifest.yaml
  • DEFAULT_INSTALL_DIR: ~/.claude/
  • CATALOG_CACHE_PATH: /tmp/armory-manifest.yaml
  • CATALOG_CACHE_TTL: 600 (seconds)

Supported Package Types

TypeInstall TargetMethod
skill~/.claude/skills/Copy directory
agent~/.claude/agents/Copy directory
hook~/.claude/hooks/Copy directory
rule~/.claude/rules/Body-only file
command~/.claude/commands/Body-only file
utility~/.claude/utilities/Copy + chmod +x
preset~/.claude/presets/Copy directory

Command Reference

CommandCookbookPurpose
/library listcookbook/list.mdShow all packages with type, version, installed status, update available
/library list --type <type>cookbook/list.mdFilter listing by package type (skill, agent, hook, rule, etc.)
/library use <name>cookbook/use.mdPull a package from armory (auto-detects type from manifest)
/library search <keyword>cookbook/search.mdKeyword search across all package types, names, and descriptions
/library search --category <name>cookbook/search.mdFilter search by category (development, review, security, etc.)
/library synccookbook/sync.mdRe-pull all installed packages that have updates
/library info <name>cookbook/info.mdShow full detail for a package (type, version, tags, category)
/library updatecookbook/update.mdCheck all installed packages for version bumps (dry-run sync)
/library remove <name>cookbook/remove.mdRemove an installed package
/library profilescookbook/profiles.mdShow available install profiles with package counts

Cookbook Dispatch

User commands are routed to the corresponding cookbook file based on the subcommand. When a /library command is received, extract the subcommand (the first token after /library) and load the matching cookbook file from the cookbook/ directory relative to this skill. The cookbook file contains the full execution procedure for that operation.

For example, /library use commit-standards dispatches to cookbook/use.md with commit-standards as the package name argument. /library list --type agent dispatches to cookbook/list.md with --type agent as the filter.

If the subcommand does not match any known cookbook, report the error and list the valid subcommands from the table above.

Type Detection

When /library use <name> is called, determine the package type by searching all sections of the manifest (packages.skills, packages.agents, packages.hooks, etc.). The first section containing a matching name entry determines the type. Use the type to:

  1. Resolve the correct source path: {type_dir}/{name}/
  2. Determine the install target: ~/.claude/{install_subdir}/
  3. Choose the install method: directory copy or body-only extraction

Behavioral Notes

  • All bash operations must use absolute paths. Never cd into temp dirs.
  • Fetch uses a 3-tier fallback chain: sparse checkout, then gh api, then curl. Attempt each in order; proceed to the next only on failure.
  • Cache lives in /tmp/ with a 10-minute TTL. A missing cache file is treated as expired (triggers a re-fetch), not as an error.
  • The catalog is read from manifest.yaml on GitHub (at ARMORY_CATALOG_URL), not from a separate catalog file. This is the same manifest format used by the armory repository.
  • All package type sections share the same entry format: name, version, description, path, source, plus optional tags, category, difficulty.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.2%
按下载量换算121

Claude

29.01%
按下载量换算94

Cursor

17.86%
按下载量换算58

Gemini CLI

10.74%
按下载量换算35

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills