ship-learn-next by softaworks/agent-toolkit
npx skills add https://github.com/softaworks/agent-toolkit --skill ship-learn-next此技能帮助将被动学习内容转化为可执行的 Ship-Learn-Next 循环——将建议和课程转化为具体、可交付的迭代。
当用户出现以下情况时激活:
每个学习探索都遵循三个重复阶段:
关键原则:100 次练习胜过 100 小时的学习。学习 = 做得更好,而不是知道更多。
阅读用户提供的文件(文字稿、文章、笔记):
# User provides path to file
FILE_PATH="/path/to/content.txt"
使用 Read 工具分析内容。
从内容中识别:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
不要:
帮助用户框定他们的学习目标:
询问:
好的探索目标示例:“发送 10 封陌生开发信并获得 2 封回复” 差的探索目标示例:“学习销售”(太模糊)
将探索目标分解为最小的可交付版本:
询问:
使其:
为每个练习构建结构:
## Rep 1: [具体目标]
**交付目标**: [你将创建/做什么]
**成功标准**: [你如何知道它已完成]
**你将学到什么**: [具体技能/见解]
**所需资源**: [最少 - 仅为此练习所需]
**时间线**: [具体截止日期]
**行动步骤**:
1. [具体步骤 1]
2. [具体步骤 2]
3. [具体步骤 3]
...
**交付后 - 反思问题**:
- 实际发生了什么?(要具体)
- 什么有效?什么无效?
- 什么让你感到惊讶?
- 按 1-10 分,这次练习进行得如何?
- 下次你会有什么不同的做法?
基于内容,建议一个进展:
## Rep 2: [下一级别]
**基于**: 你在 Rep 1 中学到的东西
**新挑战**: 要尝试/改进的一个新事物
**预期难度**: [更简单/相同/更难 - 以及原因]
## Rep 3: [继续进展]
...
进展原则:
对于每个练习,引用原始材料:
但是:始终强调实践而非研究。仅在特定练习需要时指向资源。
直接但支持性:
问题驱动:
具体,而非笼统:
行动导向:
# 你的 Ship-Learn-Next 探索:[标题]
## 探索概述
**目标**: [他们希望在 4-8 周内实现什么]
**来源**: [启发此探索的内容]
**核心课程**: [从内容中提取的 3-5 个关键可操作要点]
---
## Rep 1: [具体、可交付的目标]
**交付目标**: [具体可交付成果]
**时间线**: [本周 / 在 [日期] 之前]
**成功标准**:
- [ ] [具体事项 1]
- [ ] [具体事项 2]
- [ ] [具体事项 3]
**你将练习什么**(来自内容):
- [来自原始材料的技能/概念 1]
- [来自原始材料的技能/概念 2]
**行动步骤**:
1. [具体步骤]
2. [具体步骤]
3. [具体步骤]
4. 交付它(发布/部署/分享/演示)
**最少资源**(仅为此练习):
- [链接或参考 - 如果确实需要]
**交付后 - 反思**:
回答这些问题:
- 实际发生了什么?
- 什么有效?什么无效?
- 什么让你感到惊讶?
- 给这次练习评分:_/10
- 下次要尝试的一件不同的事是什么?
---
## Rep 2: [下一次迭代]
**基于**: Rep 1 + [你学到的东西]
**新元素**: [一个新挑战/技能]
**交付目标**: [下一个具体可交付成果]
[类似结构...]
---
## Rep 3-5: 未来路径
**Rep 3**: [简要描述]
**Rep 4**: [简要描述]
**Rep 5**: [简要描述]
*(细节将根据你在 Reps 1-2 中学到的东西而演变)*
---
## 记住
- 这是关于**实践**,而不是学习
- 目标是随着时间的推移进行 100 次练习(而不是在第一次练习中追求完美)
- 每次练习 = 计划 → 执行 → 反思 → 下一步
- 你通过交付来学习,而不是通过消费
**准备好交付 Rep 1 了吗?**
一个好的 Ship-Learn-Next 计划应具备:
重要:始终将计划保存到文件中供用户使用。
始终使用格式:
Ship-Learn-Next Plan - [简要探索标题].md示例:
Ship-Learn-Next Plan - Build in Proven Markets.mdShip-Learn-Next Plan - Learn React.mdShip-Learn-Next Plan - Cold Email Outreach.md探索标题应:
完整计划包括:
格式:始终保存为 Markdown(.md)格式以便阅读
向用户展示:
然后询问:
记住:你不是在创建课程。你是在帮助他们交付一些真实的东西,从中学习,然后交付下一个东西。
让我们帮助他们交付。
每周安装量
572
仓库
GitHub 星标数
1.2K
首次出现
Jan 20, 2026
安全审计
安装于
codex417
gemini-cli417
cursor417
claude-code415
opencode400
cline398
This skill helps transform passive learning content into actionable Ship-Learn-Next cycles - turning advice and lessons into concrete, shippable iterations.
Activate when the user:
Every learning quest follows three repeating phases:
Key principle : 100 reps beats 100 hours of study. Learning = doing better, not knowing more.
Read the file the user provides (transcript, article, notes):
# User provides path to file
FILE_PATH="/path/to/content.txt"
Use the Read tool to analyze the content.
Identify from the content:
Do NOT :
Help the user frame their learning goal:
Ask:
Example good quest : "Ship 10 cold outreach messages and get 2 responses" Example bad quest : "Learn about sales" (too vague)
Break down the quest into the smallest shippable version :
Ask:
Make it:
Structure each rep with:
## Rep 1: [Specific Goal]
**Ship Goal**: [What you'll create/do]
**Success Criteria**: [How you'll know it's done]
**What You'll Learn**: [Specific skills/insights]
**Resources Needed**: [Minimal - just what's needed for THIS rep]
**Timeline**: [Specific deadline]
**Action Steps**:
1. [Concrete step 1]
2. [Concrete step 2]
3. [Concrete step 3]
...
**After Shipping - Reflection Questions**:
- What actually happened? (Be specific)
- What worked? What didn't?
- What surprised you?
- On a scale of 1-10, how did this rep go?
- What would you do differently next time?
Based on the content, suggest a progression:
## Rep 2: [Next level]
**Builds on**: What you learned in Rep 1
**New challenge**: One new thing to try/improve
**Expected difficulty**: [Easier/Same/Harder - and why]
## Rep 3: [Continue progression]
...
Progression principles :
For each rep, reference the source material:
But : Always emphasize DOING over studying. Point to resources only when needed for the specific rep.
Direct but supportive :
Question-driven :
Specific, not generic :
Action-oriented :
# Your Ship-Learn-Next Quest: [Title]
## Quest Overview
**Goal**: [What they want to achieve in 4-8 weeks]
**Source**: [The content that inspired this]
**Core Lessons**: [3-5 key actionable takeaways from content]
---
## Rep 1: [Specific, Shippable Goal]
**Ship Goal**: [Concrete deliverable]
**Timeline**: [This week / By [date]]
**Success Criteria**:
- [ ] [Specific thing 1]
- [ ] [Specific thing 2]
- [ ] [Specific thing 3]
**What You'll Practice** (from the content):
- [Skill/concept 1 from source material]
- [Skill/concept 2 from source material]
**Action Steps**:
1. [Concrete step]
2. [Concrete step]
3. [Concrete step]
4. Ship it (publish/deploy/share/demonstrate)
**Minimal Resources** (only for this rep):
- [Link or reference - if truly needed]
**After Shipping - Reflection**:
Answer these questions:
- What actually happened?
- What worked? What didn't?
- What surprised you?
- Rate this rep: _/10
- What's one thing to try differently next time?
---
## Rep 2: [Next Iteration]
**Builds on**: Rep 1 + [what you learned]
**New element**: [One new challenge/skill]
**Ship goal**: [Next concrete deliverable]
[Similar structure...]
---
## Rep 3-5: Future Path
**Rep 3**: [Brief description]
**Rep 4**: [Brief description]
**Rep 5**: [Brief description]
*(Details will evolve based on what you learn in Reps 1-2)*
---
## Remember
- This is about DOING, not studying
- Aim for 100 reps over time (not perfection on rep 1)
- Each rep = Plan → Do → Reflect → Next
- You learn by shipping, not by consuming
**Ready to ship Rep 1?**
A good Ship-Learn-Next plan has:
IMPORTANT : Always save the plan to a file for the user.
Always use the format:
Ship-Learn-Next Plan - [Brief Quest Title].mdExamples:
Ship-Learn-Next Plan - Build in Proven Markets.mdShip-Learn-Next Plan - Learn React.mdShip-Learn-Next Plan - Cold Email Outreach.mdQuest title should be :
Complete plan including :
Format : Always save as Markdown (.md) for readability
Display to user :
Then ask :
Remember : You're not creating a curriculum. You're helping them ship something real, learn from it, and ship the next thing.
Let's help them ship.
Weekly Installs
572
Repository
GitHub Stars
1.2K
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
codex417
gemini-cli417
cursor417
claude-code415
opencode400
cline398
Python PDF处理教程:合并拆分、提取文本表格、创建PDF文件
53,300 周安装
OpenAPI 转 TypeScript 工具 - 自动生成 API 接口与类型守卫
563 周安装
数据库模式设计器 - 内置最佳实践,自动生成生产级SQL/NoSQL数据库架构
564 周安装
Rust Unsafe代码检查器 - 安全使用Unsafe Rust的完整指南与最佳实践
564 周安装
.NET并发编程模式指南:async/await、Channels、Akka.NET选择决策树
565 周安装
韩语语法检查器 - 基于国立国语院标准的拼写、空格、语法、标点错误检测与纠正
565 周安装
技能安全扫描器 - 检测Claude技能安全漏洞,防范提示注入与恶意代码
565 周安装