Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计异常

learn学习

Agent Skill

learn 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

665

周安装

28

GitHub Stars

27

下载量

233
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:learn(学习)
来源仓库:https://github.com/aviz85/claude-skills-library
仓库路径:skills/learn
安装命令:
npx skills add https://github.com/aviz85/claude-skills-library --skill learn
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/aviz85/claude-skills-library --skill learn

简介

learn 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。

  • 它通过学习任何主题并将其知识固化为永久技能,覆盖代码库、API 与行业知识。
  • 支持新建或更新现有技能,使用 Context7 增强文档检索能力。
  • 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。
  • learn 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Learn: Teach Claude Any Topic

Research and learn any topic, then retain the knowledge as a permanent skill. Works for:

  • Code libraries: React, Stripe, Supabase (uses Context7 when available)
  • APIs & Services: Twilio, OpenAI, Google APIs
  • Concepts & Methodologies: GTD, Agile, Design Patterns
  • Domain Knowledge: Tax law, medical terminology, industry practices
  • Tools: Docker, Kubernetes, FFmpeg

After learning, Claude becomes an expert on that topic in all future conversations.

Usage

/learn <topic>           # Create new skill from docs
/learn <topic> --update  # Update existing skill with latest docs
/learn <topic> --project # Save to project (.claude/skills/) instead of global

Process

1. Research the Topic

For code libraries/APIs - try Context7 first:

mcp__plugin_context7_context7__resolve-library-id
  query: "user's task/question"
  libraryName: "<topic>"

For any topic (or if Context7 doesn't have it) - use WebSearch:

WebSearch: "<topic>" guide tutorial best practices
WebSearch: "<topic>" official documentation
WebSearch: "<topic>" examples patterns

For domain knowledge - broader research:

WebSearch: "<topic>" comprehensive guide
WebSearch: "<topic>" key concepts terminology
WebSearch: "<topic>" common mistakes pitfalls

Use WebFetch to read the most relevant pages found.

2. Extract Knowledge

Query the documentation for key information:

mcp__plugin_context7_context7__query-docs
  libraryId: "<resolved-id>"
  query: "getting started setup authentication common patterns"

Extract:

  • Setup/Installation: How to get started
  • Core concepts: Key abstractions and terminology
  • Common patterns: Typical usage examples
  • API reference: Essential methods/functions
  • Gotchas: Non-obvious pitfalls mentioned in docs
  • Best practices: Recommended approaches

If docs are large, make multiple targeted queries:

  1. "installation setup quickstart"
  2. "authentication API keys configuration"
  3. "common patterns examples"
  4. "error handling troubleshooting"

3. Consult Claude Code Guide

Before creating the skill, use the claude-code-guide agent to verify current skill conventions:

Task tool with subagent_type: claude-code-guide
prompt: "What are the current conventions for writing Claude Code skills?
        I need to know: required/optional frontmatter fields,
        description best practices, and recommended structure."

This ensures the generated skill follows the latest Claude Code patterns.

4. Generate Skill Structure

Create skill at appropriate location:

  • Default: ~/.claude/skills/<topic>/skill.md
  • With --project: .claude/skills/<topic>/skill.md

Skill template:

---
name: <topic>
description: <What the library does>. Use when <specific triggers>. Covers: <main capabilities>.
---

# <Topic> Quick Reference

## Setup

[Installation commands and initial config]

## Core Concepts

[Key abstractions - 2-3 sentences each]

## Common Patterns

### [Pattern 1 Name]
[Code example with brief explanation]

### [Pattern 2 Name]
[Code example with brief explanation]

## API Quick Reference

| Method | Purpose | Example |
|--------|---------|---------|
| ... | ... | ... |

## Gotchas

- [Non-obvious issue 1]
- [Non-obvious issue 2]

## Links

- [Official Docs](url)
- [API Reference](url)

5. Verify and Announce

After creating the skill:

  1. Confirm the skill was created
  2. Show the description (what triggers it)
  3. Show 2-3 example prompts that would activate it

Quality Guidelines

Do:

  • Focus on practical, actionable information
  • Include real code examples from docs
  • Capture version-specific details if relevant
  • Add the official docs URL for reference

Don't:

  • Copy entire documentation (copyright)
  • Include marketing/promotional content
  • Add information Claude already knows generally
  • Make the skill too long (under 500 lines)

Update Mode (--update)

When updating an existing skill:

  1. Read current skill content
  2. Query docs for latest/new information
  3. Merge new content, preserving existing structure
  4. Note version changes if applicable

Example

User: /learn stripe-payments

Claude:
1. Resolves "stripe" via Context7 → /stripe/stripe-node
2. Queries: setup, authentication, common patterns, webhooks
3. Consults claude-code-guide for current skill conventions
4. Creates ~/.claude/skills/stripe-payments/skill.md with:
   - API key setup
   - Payment intent flow
   - Webhook verification
   - Error handling patterns
5. Reports: "Created stripe-payments skill. Triggers on: 'Stripe payment', 'charge card', 'payment intent'"

Requirements

  • Context7 MCP plugin (recommended) - for accessing library documentation
  • OR WebSearch/WebFetch tools - as fallback for any documentation

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

36.27%
按下载量换算85

Claude

29.01%
按下载量换算68

Cursor

18.52%
按下载量换算43

Gemini CLI

9.01%
按下载量换算21

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

权限和风险

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 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