skills
scenario-labs/skills의 67가지 에이전트 스킬(시나리오·게임·영상 포함), npx skills add로 설치
무료: 코딩 에이전트용 계획 스킬, 7요소·15사례 제공. 코스0 $99, I‑IV $299 번들, UC Berkeley
Free: a plan-first skill for your coding agent, 7 building blocks, 15 case studies. Course 0 $99, Courses I-IV $299 bundle. UC Berkeley.
스킬PythonGitHub @kayashaolu온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
아직 감지된 업데이트가 없습니다. GitHub 릴리스가 나오면 여기에 보입니다.
개인 계정의 공개 저장소 소유자는 GitHub로 로그인해 운영자를 확인하고 소개를 직접 관리할 수 있습니다. 관리자 승인은 필요하지 않습니다.
로그인한 뒤 확인 파일을 만들어 이 저장소의 기본 브랜치에 30분 안에 커밋해 주세요. 다른 브랜치나 포크의 파일은 인정하지 않습니다. 파일을 올린 뒤 아래에서 확인하면 관리자 승인 없이 관리할 수 있습니다. 자격을 유지하려면 파일을 남겨 두세요.
로그인이 필요하면 로그인 화면으로 이동합니다. 로그인 후 이곳으로 돌아와 원하는 확인 버튼을 다시 눌러 주세요.
프로젝트 폴더에서 /nomorevibe verify를 실행하면 소유권을 확인하고 소개를 직접 관리할 수 있습니다.
1분 만에 확인하기Free tools from Systems Thinking Lab: design-with-blocks (design an app with 7 building blocks), review-with-blocks (senior-level design review), and scaffold (a plan-first mentor workflow).
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
Free tools from Systems Thinking Lab, installable as
Claude Code plugins or, for other coding agents, as
Agent Skills (see Install below). Scaffold is the workflow; design-with-blocks and
review-with-blocks apply the seven building blocks (see The tools and The framework below).
Updates later are just /plugin marketplace update systemthinkinglab.
Each skill lands in your project's .agents/skills/ / as an Agent Skill; they are built and tested in Claude Code.
All three are free, open source (Apache-2.0), and installable byREADME 전문 보기 ↗Free tools from Systems Thinking Lab, installable as Claude Code plugins or, for other coding agents, as Agent Skills (see Install below). Scaffold is the workflow; design-with-blocks and review-with-blocks apply the seven building blocks (see The tools and The framework below).
Add the marketplace once:
/plugin marketplace add kayashaolu/systemthinkinglab
Then install any tool:
/plugin install design-with-blocks@systemthinkinglab
/plugin install review-with-blocks@systemthinkinglab
/plugin install scaffold@systemthinkinglab
Updates later are just /plugin marketplace update systemthinkinglab.
For agents other than Claude Code:
npx skills add kayashaolu/systemthinkinglab --skill design-with-blocks
npx skills add kayashaolu/systemthinkinglab --skill review-with-blocks
npx skills add kayashaolu/systemthinkinglab --skill scaffold
Each skill lands in your project's .agents/skills/<name>/ as an Agent Skill; they are built and tested in Claude Code.
| Plugin | What it does |
|---|---|
| design-with-blocks | Design an app using the 7 Universal Building Blocks: describe it in plain English, decompose features into blocks, get per-block technology recommendations, and output a buildable design doc. |
| review-with-blocks | Review a finished system design against the 7 building blocks and the non-functional "-ilities": decompose it, flag wrong/missing/over-engineered blocks, rate each load-bearing -ility (holds / at-risk / gap) with its tradeoff, and surface the questions a senior would ask. |
| scaffold | A plan-first developer workflow, run by an AI mentor: it predicts before it builds, keeps a compounding wiki of your codebase, and holds an honest ledger of what you've demonstrated you know, in craft or direction mode. |
All three are free, open source (Apache-2.0), and installable by anyone. Together they cover the arc design → build → review: design-with-blocks plans the architecture, scaffold runs the plan-first workflow while you build it, and review-with-blocks judges the result. All three use the seven building blocks, free to read at systemthinkinglab.ai/learn.
Every system, from Instagram to Stripe, is built from the same seven primitives: Service, Worker, Key-Value Store, File Store, Queue, Relational Database, Vector Database; plus three external entities: User, External Service, Time. That vocabulary is the intellectual work of Kay Ashaolu, founder of Systems Thinking Lab. If you want pattern literacy, the ability to design any future system without a tool, you can learn the 7 building blocks for free at systemthinkinglab.ai/learn.