Token导航 LogoToken导航

Agent Skill · 研究检索

ship-learn-next(ship 学习 Next.js)

ship-learn-next 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。

ship-learn-next 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,权限为只读;许可证为 MIT,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 57,864。

总安装 423周安装 18GitHub Stars 公开资料未说明下载 148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
MIT

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:ship-learn-next(ship 学习 Next.js)
来源仓库:https://github.com/ryanhudson/tapestry-skills-for-claude-code
仓库路径:skills/ship-learn-next
安装命令:
npx skills add ryanhudson/tapestry-skills-for-claude-code --skill "ship-learn-next"
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。

AgentSkills.tonpx skills
npx skills add ryanhudson/tapestry-skills-for-claude-code --skill "ship-learn-next"

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。

ship-learn-next 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。适用于信息搜集、技术研究和内容筛选等需要精准匹配的场景。

通过 npx skills add 命令从 GitHub 仓库安装并使用。安装前需确认权限范围和维护状态,注意可能涉及联网或文件操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/ship-learn-next

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 ryanhudson/tapestry-skills-for-claude-code --skill "ship-learn-ne…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

ship-learn-next 怎么安装?

在终端执行 npx skills add ryanhudson/tapestry-skills-for-claude-code --skill "ship-learn-next"。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ship-learn-next 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。

ship-learn-next 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

ship-learn-next 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

ship-learn-next 用的人多吗?

公开数据是累计安装 423 次,近一周安装 18 次,下载 148 次。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。

ship-learn-next 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 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
ship-learn-next

ship 学习 Next.js · 本页

423—只读MIT未收录

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

Ship-Learn-Next Action Planner

Transform passive learning content into actionable Ship-Learn-Next cycles - turning advice and lessons into concrete, shippable iterations.

Core Framework

Every learning quest follows three repeating phases:

  1. SHIP - Create something real (code, content, product)
  2. LEARN - Honest reflection on what happened
  3. NEXT - Plan the next iteration based on learnings

Key principle: 100 reps beats 100 hours of study. Learning = doing better, not knowing more.

Workflow

Read Content → Extract Lessons → Define Quest → Design Rep 1 → Map Reps 2-5 → Save Plan

Step 1: Read and Analyze Content

Read the provided file (transcript, article, notes):

FILE_PATH="[user-provided path]"

Identify from the content:

  • Main advice/lessons: Key actionable takeaways
  • Skills being taught: What can be practiced
  • Examples/case studies: Real implementations to replicate

Focus on: Actionable parts, not summaries or theory.

Step 2: Define the Quest

Help the user frame a specific goal:

Questions to ask:

  1. "Based on this content, what do you want to achieve in 4-8 weeks?"
  2. "What would success look like? (Be specific)"
  3. "What's something concrete you could build/create/ship?"

Good quest: "Ship 10 cold outreach messages and get 2 responses" Bad quest: "Learn about sales" (too vague)

Step 3: Design Rep 1

Create the smallest shippable version:

Make it:

  • Concrete and specific
  • Completable in 1-7 days
  • Produces real evidence/artifact
  • Small enough to not be intimidating
  • Big enough to learn something meaningful

Questions:

  • "What's the smallest version you could ship THIS WEEK?"
  • "What do you need to learn JUST to do that?"
  • "What would 'done' look like?"

Step 4: Structure the Plan

Rep Template

## Rep 1: [Specific Goal]

**Ship Goal**: [What to create/do]
**Success Criteria**: [How to know it's done]
**What You'll Learn**: [Specific skills]
**Timeline**: [Deadline]

**Action Steps**:
1. [Concrete step]
2. [Concrete step]
3. [Concrete step]

**After Shipping - Reflection**:
- What actually happened?
- What worked? What didn't?
- What surprised you?
- Rate this rep: _/10
- What to try differently next time?

Progression for Reps 2-5

Each rep adds ONE new element:

  • Builds on previous rep's learnings
  • Increases difficulty based on success
  • References specific lessons from content
  • Remains shippable (not theoretical)

Step 5: Save the Plan

Filename format: Ship-Learn-Next Plan - [Brief Quest Title].md

Quest title should be:

  • Brief (3-6 words)
  • Descriptive of main goal
  • Based on content's core lesson

Complete Plan Structure

# Your Ship-Learn-Next Quest: [Title]

## Quest Overview
**Goal**: [4-8 week achievement]
**Source**: [Content that inspired this]
**Core Lessons**: [3-5 key actionable takeaways]

---

## Rep 1: [Specific, Shippable Goal]

**Ship Goal**: [Concrete deliverable]
**Timeline**: [This week / By date]
**Success Criteria**:
- [ ] [Specific thing 1]
- [ ] [Specific thing 2]

**What You'll Practice** (from the content):
- [Skill/concept 1]
- [Skill/concept 2]

**Action Steps**:
1. [Step]
2. [Step]
3. Ship it

**After Shipping - Reflection**:
[Questions listed above]

---

## Rep 2: [Next Iteration]

**Builds on**: Rep 1 learnings
**New element**: [One new challenge]
**Ship goal**: [Next deliverable]

---

## Reps 3-5: Future Path

**Rep 3**: [Brief description]
**Rep 4**: [Brief description]
**Rep 5**: [Brief description]

*(Details evolve based on Reps 1-2 learnings)*

---

## Remember

- This is about DOING, not studying
- Aim for 100 reps over time
- Each rep = Plan → Do → Reflect → Next
- You learn by shipping, not consuming

**Ready to ship Rep 1?**

Conversation Style

Direct but supportive:

  • "Ship it, then we'll improve it"
  • "What's the smallest version you could do this week?"

Question-driven:

  • Make them think, don't just tell
  • Push for concrete commitments

Specific, not generic:

  • "By Friday, ship one landing page" not "Learn web development"

What NOT to Do

  • Create a study plan (create a SHIP plan)
  • List all resources to consume (minimal resources for current rep only)
  • Let perfect be the enemy of shipped
  • Accept vague goals ("learn X" → "ship Y by Z date")
  • Overwhelm with the full journey (focus on Rep 1)

Key Phrases

  • "What's the smallest version you could ship this week?"
  • "What do you need to learn JUST to do that?"
  • "This isn't about perfection - it's rep 1 of 100"
  • "Ship something real, then we'll improve it"
  • "Learning = doing better, not knowing more"

Content Type Handling

YouTube Transcripts

  • Focus on advice, not stories
  • Extract concrete techniques
  • Identify case studies to replicate

Articles/Tutorials

  • Identify "now do this" parts vs theory
  • Extract specific workflows
  • Find minimal starting example

Course Notes

  • What's the smallest project?
  • Which modules needed for Rep 1?
  • What can be practiced immediately?

Success Metrics

A good plan has:

  • Specific, shippable Rep 1 (1-7 days)
  • Clear success criteria
  • Concrete artifacts to produce
  • Direct connection to source content
  • Progression path for Reps 2-5
  • Emphasis on action over consumption
  • Built-in reflection

After Creating the Plan

Display to user:

  1. Confirm file saved: "Saved to: [filename]"
  2. Brief quest overview
  3. Highlight Rep 1 (due this week)

Then ask:

  1. "When will you ship Rep 1?"
  2. "What might stop you? How will you handle it?"
  3. "Come back after shipping and we'll reflect + plan Rep 2"

Remember: Not creating a curriculum. Helping them ship something real, learn from it, and ship the next thing.

Let's help them ship.

平台分布

Claude Code

31.24%
按下载量换算46

trae

24.17%
按下载量换算36

OpenCode

17.99%
按下载量换算27

Antigravity

13.46%
按下载量换算20

Gemini CLI

8.06%
按下载量换算12

windsurf

3.78%
按下载量换算6

安全审计

暂无安全审计结果可展示。

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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