test-driven-development
Write tests first, watch them fail, then implement minimal code to pass.
ljg-qa
信息提问机。给一篇文章/论文/书,把核心观点抽成 Q-A 对——Question 切要害,不教科书;Answer 简洁清晰,有形式化收口,逻辑链完整。读者顺 Q 链走过,每个 A 砸下一枚钉子,复现作者整套推理。Use when user says '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa', or shares an article/paper/book and asks for Q-A extraction. Triggers when the user wants ideas extracted not as a summary but as a sequence of incisive questions with answered. NOT FOR FAQ generation, glossary creation, or comprehension quizzes — this is intellectual scaffolding, not study aids.
Full skill instructions
读一份东西,把它的思想拆成「为什么—怎么—边界」的问答链。
读者顺着 Q 走过去,每个 A 砸下来一枚钉子。
把作者的论证骨架翻出来,每根骨头长成一个尖锐的问题。读者沿着 Q 链读,能复现作者的整套思路——而不是被告知结论。
Q 切要害 —— 问的是「为什么这个解法成立」「它跟另一种做法差在哪」「它的代价是什么」「它在哪里失效」,不是「它定义是什么」。一个 Q 必须能让答案承重,不能被一句话敷衍过去。
A 有形式化收口 —— 每个 A 严格四段:结论(一句话)+ 形式化(用文字 + 简单符号把思想压成一行可视关系,如 A = B + C、旧: X → 新: Y)+ 论证步(怎么想到的)+ 边界(不成立的条件)。形式化是"思想的几何",让读者一眼看出关系。
Q 链有方向 —— Q 之间不是并列罗列,是「Q1 答完→Q2 自然冒出来」。读者读完整串 Q,相当于走了一遍作者的推理路径。
按 Workflows/Extract.md 的步骤执行。
Q 怎么提、A 怎么收口的具体模式见 References/QuestionDesign.md。
执行 workflow 时:
curl -s -X POST http://localhost:31337/notify \
-H "Content-Type: application/json" \
-d '{"message": "Running Extract in ljg-qa"}' \
> /dev/null 2>&1 &
输出文本:
Running **Extract** in **ljg-qa**...
*bold*,禁 markdown 语法)~/Documents/notes/{YYYYMMDDTHHMMSS}--qa-{核心主题 5-10 字}__qa.orgExample 1: URL
User: /ljg-qa https://example.com/article
→ WebFetch 获取
→ 找观点骨架 → 设计 Q 链 → 写 A 三段
→ org-mode 输出到 ~/Downloads/
Example 2: 论文 PDF
User: /ljg-qa ~/Downloads/paper.pdf
→ Read PDF(注意 pages 参数)
→ Q 抽出方法的「为什么」「代价」「边界」
→ 输出 org-mode
Example 3: 直接文本
User: 把这段抽成 Q-A: [text]
→ 跳过获取,直接抽
→ 输出
通才 = 协调,专才 = 干活。是"思想的几何",不是"数学的形式"Write tests first, watch them fail, then implement minimal code to pass.
Enforce verification commands before claiming work completion, fixes, or test passes—no success assertions without fresh evidence.
Dispatch fresh subagents per task with two-stage review (spec compliance, then code quality) in the current session.
Evaluate code review feedback with technical rigor before implementing, avoiding performative agreement and blind implementation.
Test-driven documentation for creating reusable agent techniques, patterns, and reference guides.
Structured workflow for completing development branches with test verification and merge/PR options.
Browser automation with 40+ commands for navigation, interaction, form filling, and web testing.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Comprehensive reference guide for writing, debugging, and maintaining Playwright tests across all testing types and scenarios.
End-to-end Solana development with framework-kit, @solana/kit, Anchor programs, and local testing.
ab testing
Build custom Expo development clients for testing native code on physical devices via EAS Build or locally.
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.