Token导航 LogoToken导航

Agent Skill · 研究检索

learn(学习)

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。

learn 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,权限为执行命令;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 54,235。

总安装 514周安装 21GitHub Stars 49下载 166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:learn(学习)
来源仓库:https://github.com/soul-brews-studio/arra-oracle-skills
仓库路径:skills/learn
安装命令:
npx skills add https://github.com/soul-brews-studio/arra-oracle-skills --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/soul-brews-studio/arra-oracle-skills --skill learn

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。

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。适用于个性化学习路径规划与知识获取支持,整合在线课程与文档资源。可返回学习计划、推荐书籍或练习题目链接,适配不同水平用户。

安装命令为 npx skills add https://github.com/soul-brews-studio/arra-oracle-skills --skill learn,需确认是否调用第三方教育平台。建议在使用前核实内容版权,避免分发受保护的学习材料。

来源仓库内路径:skills/learn

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/soul-brews-studio/arra-oracle-skills --skill l…;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

    它需要执行命令,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

learn 怎么安装?

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

learn 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。

learn 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/soul-brews-studio/arra-oracle-skills --skill learn 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

learn 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。

learn 用的人多吗?

公开数据是累计安装 514 次,近一周安装 21 次,下载 166 次,GitHub 49 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。

learn 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

  • 需要执行命令,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

  • 不能接受 Skill 在你机器上执行命令的人。
  • 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
learn

学习 · 本页

51449执行命令未明确有提醒

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

/learn - Deep Dive Learning Pattern

Explore a codebase with 3 parallel Haiku agents → create organized documentation.

Usage

/learn [url]             # Auto: clone via ghq, symlink origin/, then explore
/learn [slug]            # Use slug from ψ/memory/slugs.yaml
/learn [repo-path]       # Path to repo
/learn [repo-name]       # Finds in ψ/learn/owner/repo
/learn --init            # Restore all origins after git clone (like submodule init)

Depth Modes

FlagAgentsFilesUse Case
--fast11 overviewQuick scan, "what is this?"
(default)33 docsNormal exploration
--deep55 docsMaster complex codebases
/learn --fast [target]   # Quick overview (1 agent, ~2 min)
/learn [target]          # Standard (3 agents, ~5 min)
/learn --deep [target]   # Deep dive (5 agents, ~10 min)

Directory Structure

ψ/learn/
├── .origins             # Manifest of learned repos (committed)
└── owner/
    └── repo/
        ├── origin       # Symlink to ghq source (gitignored)
        ├── repo.md      # Hub file - links to all sessions (committed)
        └── YYYY-MM-DD/  # Date folder
            ├── 1349_ARCHITECTURE.md      # Time-prefixed files
            ├── 1349_CODE-SNIPPETS.md
            ├── 1349_QUICK-REFERENCE.md
            ├── 1520_ARCHITECTURE.md      # Second run same day
            └── ...

Multiple learnings: Each run gets time-prefixed files (HHMM_), nested in date folder.

Offload source, keep docs:

unlink ψ/learn/owner/repo/origin   # Remove symlink
ghq rm owner/repo                  # Remove source
# Docs remain in ψ/learn/owner/repo/

/learn --init

Restore all origins after cloning (like git submodule init):

ROOT="$(pwd)"
# Read .origins manifest and restore symlinks
while read repo; do
  ghq get -u "https://github.com/$repo"
  OWNER=$(dirname "$repo")
  REPO=$(basename "$repo")
  mkdir -p "$ROOT/ψ/learn/$OWNER/$REPO"
  ln -sf "$(ghq root)/github.com/$repo" "$ROOT/ψ/learn/$OWNER/$REPO/origin"
  echo "✓ Restored: $repo"
done < "$ROOT/ψ/learn/.origins"

Step 0: Detect Input Type + Resolve Path

CRITICAL: Capture ABSOLUTE paths first (before spawning any agents):

date "+🕐 %H:%M %Z (%A %d %B %Y)" && ROOT="$(pwd)"
echo "Learning from: $ROOT"

IMPORTANT FOR SUBAGENTS: When spawning Haiku agents, you MUST give them TWO literal paths:

  1. SOURCE_DIR (where to READ code) - the origin/ symlink
  2. DOCS_DIR (where to WRITE docs) - the parent directory, NOT inside origin/

⚠️ THE BUG: If you only give agents origin/ path, they cd into it and write there → files end up in WRONG repo!

FIX: Always give BOTH paths as LITERAL absolute values (no variables!):

Example: ROOT=/home/user/ghq/.../my-oracle, learning acme-corp/cool-library, TODAY=2026-02-04, TIME=1349:

READ from:  .../ψ/learn/acme-corp/cool-library/origin/
WRITE to:   .../ψ/learn/acme-corp/cool-library/2026-02-04/1349_[FILENAME].md

Tell each agent: "Read from [SOURCE_DIR]. Write to [DOCS_DIR]/[TIME]_[FILENAME].md"

If URL (http* or owner/repo format)

Clone, create docs dir, symlink origin, update manifest:

# Replace [URL] with actual URL
URL="[URL]"
ROOT="$(pwd)"  # CRITICAL: Save current directory!
ghq get -u "$URL" && \
  GHQ_ROOT=$(ghq root) && \
  OWNER=$(echo "$URL" | sed -E 's|.*github.com/([^/]+)/.*|\1|') && \
  REPO=$(echo "$URL" | sed -E 's|.*/([^/]+)(\.git)?$|\1|') && \
  mkdir -p "$ROOT/ψ/learn/$OWNER/$REPO" && \
  ln -sf "$GHQ_ROOT/github.com/$OWNER/$REPO" "$ROOT/ψ/learn/$OWNER/$REPO/origin" && \
  echo "$OWNER/$REPO" >> "$ROOT/ψ/learn/.origins" && \
  sort -u -o "$ROOT/ψ/learn/.origins" "$ROOT/ψ/learn/.origins" && \
  echo "✓ Ready: $ROOT/ψ/learn/$OWNER/$REPO/origin → source"

Verify:

ls -la "$ROOT/ψ/learn/$OWNER/$REPO/"
Note: Grep tool doesn't follow symlinks. Use: rg -L "pattern" ψ/learn/owner/repo/origin/

Then resolve path:

# Find by name (searches origin symlinks)
find ψ/learn -name "origin" -type l | xargs -I{} dirname {} | grep -i "$INPUT" | head -1

Scope

For external repos: Clone with script first, then explore via origin/ For local projects (in specs/, ψ/lib/): Read directly

Step 1: Detect Mode & Calculate Paths

Check arguments for --fast or --deep:

  • --fast → Single overview agent
  • --deep → 5 parallel agents
  • (neither) → 3 parallel agents (default)

Calculate ACTUAL paths (replace variables with real values):

TODAY = YYYY-MM-DD (e.g., 2026-02-04)
TIME = HHMM (e.g., 1349)
REPO_DIR = [ROOT]/ψ/learn/[OWNER]/[REPO]/
DOCS_DIR = [ROOT]/ψ/learn/[OWNER]/[REPO]/[TODAY]/   ← date folder
SOURCE_DIR = [ROOT]/ψ/learn/[OWNER]/[REPO]/origin/  ← symlink
FILE_PREFIX = [TIME]_                               ← time prefix for files

Example:
- ROOT = /home/user/ghq/github.com/my-org/my-oracle
- OWNER = acme-corp
- REPO = cool-library
- TODAY = 2026-02-04, TIME = 1349
- DOCS_DIR = .../ψ/learn/acme-corp/cool-library/2026-02-04/
- Files: 1349_ARCHITECTURE.md, 1349_CODE-SNIPPETS.md, etc.

⚠️ CRITICAL: Create symlink AND date folder FIRST, then spawn agents!

  1. Run the clone + symlink script in Step 0 FIRST
  2. Capture TIME: date +%H%M (e.g., 1349)
  3. Create the date folder: mkdir -p "$DOCS_DIR"
  4. Capture DOCS_DIR, SOURCE_DIR, and TIME as literal values
  5. THEN spawn agents with paths including TIME prefix

Multiple runs same day? Each run gets unique TIME prefix → no overwrites.


Mode: --fast (1 agent)

Single Agent: Quick Overview

Prompt the agent with (use LITERAL paths, not variables!):

You are exploring a codebase.

READ source code from: [SOURCE_DIR]
WRITE your output to:   [DOCS_DIR]/[TIME]_OVERVIEW.md

⚠️ IMPORTANT: Write to DOCS_DIR (the date folder), NOT inside origin/!

Analyze:
- What is this project? (1 sentence)
- Key files to look at
- How to use it (install + basic example)
- Notable patterns or tech

Skip to Step 2 after agent completes.


Mode: Default (3 agents)

Launch 3 agents in parallel. Each prompt must include (use LITERAL paths!):

READ source code from: [SOURCE_DIR]
WRITE your output to:   [DOCS_DIR]/[TIME]_[filename].md

⚠️ IMPORTANT: Write to DOCS_DIR (the date folder), NOT inside origin/!

Agent 1: Architecture Explorer → [TIME]_ARCHITECTURE.md

  • Directory structure
  • Entry points
  • Core abstractions
  • Dependencies

Agent 2: Code Snippets Collector → [TIME]_CODE-SNIPPETS.md

  • Main entry point code
  • Core implementations
  • Interesting patterns

Agent 3: Quick Reference Builder → [TIME]_QUICK-REFERENCE.md

  • What it does
  • Installation
  • Key features
  • Usage patterns

Skip to Step 2 after all agents complete.


Mode: --deep (5 agents)

Launch 5 agents in parallel. Each prompt must include (use LITERAL paths!):

READ source code from: [SOURCE_DIR]
WRITE your output to:   [DOCS_DIR]/[TIME]_[filename].md

⚠️ IMPORTANT: Write to DOCS_DIR (the date folder), NOT inside origin/!

Agent 1: Architecture Explorer → [TIME]_ARCHITECTURE.md

  • Directory structure & organization philosophy
  • Entry points (all of them)
  • Core abstractions & their relationships
  • Dependencies (direct + transitive patterns)

Agent 2: Code Snippets Collector → [TIME]_CODE-SNIPPETS.md

  • Main entry point code
  • Core implementations with context
  • Interesting patterns & idioms
  • Error handling examples

Agent 3: Quick Reference Builder → [TIME]_QUICK-REFERENCE.md

  • What it does (comprehensive)
  • Installation (all methods)
  • Key features with examples
  • Configuration options

Agent 4: Testing & Quality Patterns → [TIME]_TESTING.md

  • Test structure and conventions
  • Test utilities and helpers
  • Mocking patterns
  • Coverage approach

Agent 5: API & Integration Surface → [TIME]_API-SURFACE.md

  • Public API documentation
  • Extension points / hooks
  • Integration patterns
  • Plugin/middleware architecture

Skip to Step 2 after all agents complete.

Step 2: Create/Update Hub File ([REPO].md)

# [REPO] Learning Index

## Source
- **Origin**: ./origin/
- **GitHub**: https://github.com/$OWNER/$REPO

## Explorations

### [TODAY] [TIME] ([mode])
- [[YYYY-MM-DD/HHMM_ARCHITECTURE|Architecture]]
- [[YYYY-MM-DD/HHMM_CODE-SNIPPETS|Code Snippets]]
- [[YYYY-MM-DD/HHMM_QUICK-REFERENCE|Quick Reference]]
- [[YYYY-MM-DD/HHMM_TESTING|Testing]]        <!-- --deep only -->
- [[YYYY-MM-DD/HHMM_API-SURFACE|API Surface]] <!-- --deep only -->

**Key insights**: [2-3 things learned]

### [TODAY] [EARLIER-TIME] ([mode])
...

Output Summary

--fast mode

## 📚 Quick Learn: [REPO]

**Mode**: fast (1 agent)
**Location**: ψ/learn/$OWNER/$REPO/[TODAY]/[TIME]_*.md

| File | Description |
|------|-------------|
| [REPO].md | Hub (links all sessions) |
| [TODAY]/[TIME]_OVERVIEW.md | Quick overview |

Default mode

## 📚 Learning Complete: [REPO]

**Mode**: default (3 agents)
**Location**: ψ/learn/$OWNER/$REPO/[TODAY]/[TIME]_*.md

| File | Description |
|------|-------------|
| [REPO].md | Hub (links all sessions) |
| [TODAY]/[TIME]_ARCHITECTURE.md | Structure |
| [TODAY]/[TIME]_CODE-SNIPPETS.md | Code examples |
| [TODAY]/[TIME]_QUICK-REFERENCE.md | Usage guide |

**Key Insights**: [2-3 things learned]

--deep mode

## 📚 Deep Learning Complete: [REPO]

**Mode**: deep (5 agents)
**Location**: ψ/learn/$OWNER/$REPO/[TODAY]/[TIME]_*.md

| File | Description |
|------|-------------|
| [REPO].md | Hub (links all sessions) |
| [TODAY]/[TIME]_ARCHITECTURE.md | Structure & design |
| [TODAY]/[TIME]_CODE-SNIPPETS.md | Code examples |
| [TODAY]/[TIME]_QUICK-REFERENCE.md | Usage guide |
| [TODAY]/[TIME]_TESTING.md | Test patterns |
| [TODAY]/[TIME]_API-SURFACE.md | Public API |

**Key Insights**: [3-5 things learned]

.gitignore Pattern

For Oracles that want to commit docs but ignore symlinks:

# Ignore origin symlinks only (source lives in ghq)
# Note: no trailing slash - origin is a symlink, not a directory
ψ/learn/**/origin

After running /learn, check your repo's .gitignore has these patterns so docs are committed but symlinks are ignored.

Trace Connection

After writing docs, log the learning to Oracle so it's discoverable via /trace:

arra_learn({
  pattern: "Learned [REPO]: [2-3 key insights]",
  concepts: ["learn", "codebase", relevant-tags],
  source: "learn: OWNER/REPO"
})

This connects /learn to the shared knowledge layer — future /trace queries find what was learned.

Notes

  • --fast: 1 agent, quick scan for "what is this?"
  • Default: 3 agents in parallel, good balance
  • --deep: 5 agents, comprehensive for complex repos
  • Haiku for exploration = cost effective
  • Main reviews = quality gate
  • origin/ structure allows easy offload
  • .origins manifest enables --init restore

平台分布

Codex

37.66%
按下载量换算63

Claude

30.31%
按下载量换算50

Cursor

16.49%
按下载量换算27

Gemini CLI

10.02%
按下载量换算17

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/soul-brews-studio/arra-oracle-skills --skill learn 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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