Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Made by mertduzgun.com
Skills
vinvcn avatar

Prototype

vinvcn/mattpocock-skills-zh-cn

Throwaway code to answer a design question before you commit. Routes between two approaches: a minimal terminal app when you need to sanity-check state logic or a data model, or multiple radically different UI variations on one route with URL toggles when you're exploring visual design. Everything lives in memory, runs with one command, and gets deleted once you have your answer. The split matters because picking the wrong branch wastes the whole prototype. Good for "does this state machine actually work" or "let me see three different ways this could look" moments. Document what you learned, then throw it away.

installs
5.8K
GitHub stars
5.3K
last updated
Aug 21, 2026
View on GitHubSave

Install

$ npx -y skills add vinvcn/mattpocock-skills-zh-cn --skill prototype --agent claude-code

Installs into .claude/skills of the current project.

Files

原型

Prototype 是用来回答一个问题的 throwaway code。问题决定形状。

选择分支

先识别正在回答哪个问题:来自用户 prompt、周围代码,或在用户在线时直接询问:

  • "Does this logic / state model feel right?" → LOGIC.md。构建一个单一、可分享的 HTML 文件(free-play buttons 加 tabbed guided walkthroughs),推动 state machine 跑过纸面上难以推理的 cases,而且非开发人员也能驱动它。
  • "What should this look like?" → UI.md。在单一路由上生成几种差异很大的 UI variations,并通过 URL search param 和浮动底栏切换。

这两个分支会产出非常不同的 artifacts;选错会浪费整个 prototype。如果问题确实模糊且用户不可达,默认选择更匹配周围代码的分支(backend module → logic;page 或 component → UI),并在 prototype 顶部说明假设。

两个分支通用的规则

  1. 从第一天就是 throwaway,并明确标记。 Prototype code 要靠近它实际会被使用的位置(放在被 prototype 的 module 或 page 旁边),这样上下文清楚;但命名要让随手读代码的人看出它是 prototype,不是 production。对 throwaway UI routes,遵守项目现有 routing convention;不要发明新的顶层结构。
  2. 运行毫无负担。 UI prototype 从项目 task runner 中的一条命令启动:pnpm <name>、python <path>、bun <path> 等。Logic demo 则是用户双击即可打开的单个 HTML 文件。无论哪种,启动都不需要动脑。
  3. 默认不持久化。 State 保存在内存中。Persistence 是 prototype 要_检查_的东西,不该成为依赖。如果问题明确涉及 database,就用 scratch DB 或带有清晰 “PROTOTYPE, wipe me” 名称的本地文件。
  4. 跳过 polish。 不写 tests,不做超过“能跑起来”所需的 error handling,不做 abstractions。重点是快速学到东西。
  5. 暴露 state。 每次 action(logic)或每次 variant switch(UI)后,打印或渲染完整相关 state,让用户看到发生了什么变化。
  6. 完成后 capture。 把验证过的 decision 折进真实 code,然后把 prototype 本身作为 primary source 保存:commit 到 main 之外的 throwaway branch,并在 implementation issue 上留下指向该 branch 的 context pointer。同时在 issue 或 commit 中 capture answer,也就是 verdict 与它解决的问题。Main branch 只保留验证过的 decision。
SKILL.md on GitHub

Sponsors

CodeRabbitSponsoredAI writes the code. CodeRabbit catches the slop.SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneknobsSee your site on any phone, any day, in any languagebelt - the only tool your agent needsSponsoredbelt cli automatically finds the best tools and skills for your agent. image, video, music, tts...Open StepsSponsoredFree an open-source skills that make AI coding agents easier to understand, verify, and control.AppSignalSponsoredMonitor with ease. Code with confidence.

Details

Repository
github.com/vinvcn/mattpocock-skills-zh-cn
First seen
Jun 3, 2026

More from vinvcn/mattpocock-skills-zh-cn

All 39
  • Triage5.6K
  • Git Guardrails Claude Code5.5K
  • Scaffold Exercises5.5K
  • Setup Pre Commit5.5K
  • Migrate To Shoehorn5.4K
  • Teach5.2K
  • Grilling4.4K
  • Domain Modeling4.2K
  • Code Review4.2K
  • Ask Matt4.2K
  • Diagnosing Bugs4.2K
  • Implement4.1K
  • Codebase Design4.1K
  • Research4K
  • Writing Shape3.6K
  • Writing Fragments3.6K
  • Writing Beats3.6K
  • Resolving Merge Conflicts3.5K
  • To Prd2.2K
  • Design An Interface2.1K
  • To Issues2.1K
  • Qa2.1K
  • Edit Article2.1K
  • Obsidian Vault2.1K

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels594.9Kinstalls
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.4Minstalls
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s37.9Kinstalls
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes309.2Kinstalls
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kinstalls
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.1Minstalls