メニュー
TypeScript project initialization best practices
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.96 | Python v0.1.56. Covers: query(), hooks, subagents, MCP, permissions, sandbox, structured outputs, and sessions. Use when: building AI agents, configuring MCP servers, setting up permissions/hooks, using structured outputs, troubleshooting SDK errors, or working with subagents.
Xiaolai's Claude tools collection. Use when user types /xiaolai. Routes to: (1) claude-agent-sdk — Agent SDK reference for building autonomous AI agents, or (2) nlpm — Natural-Language Programming Manager for scanning, scoring, and fixing NL artifacts.
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".
记录和跟踪个人重大决策。当用户说"记决策"、"记个决策"、"决策跟踪"、"回填"、"decision",或描述一个刚做的/正在考虑的重大决策(创业/事业/财务/人生)并希望系统化记录与复盘时使用。自动四层拆解(原始信息/决策事实/假设推断/结果验证),生成 2 个文件,维护索引与行为模式库,并在记新决策时用历史教训主动拦截。
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)
| name | ts-project-initialize |
| description | TypeScript project initialization best practices |
Initialize TypeScript projects with proper tooling, type checking, and framework setup.
Reference documentation: package.md, workspace.md, typescript.md, oxc.md, hono.md, tanstack-spa.md, shadcn-ui.md, dev-tools.md, ci.md
<configuration_decisions>
Project visibility:
Package structure:
Application type:
<setup_principles>
Required setup sequence (due to configuration dependencies):
package.md): Foundation for all subsequent configsworkspace.md): Only if monorepo - must precede package setupoxc.md): Requires package structure to be establishedpackages/*/ directoriestypescript.md): Required for all projectshono.mdtanstack-spa.mdshadcn-ui.mddev-tools.md): Requires application structureci.md): Final step after all configs establishedLocation constraints:
packages/*/
</setup_principles><reference_index>
Core setup (all projects):
package.md: Package configuration (package.json, pnpm)typescript.md: TypeScript strict configurationoxc.md: Linting and formatting with oxcdev-tools.md: Development utilitiesci.md: CI/CD pipelinesStructure-specific:
workspace.md: Monorepo/pnpm workspace setupFramework-specific:
hono.md: Backend API with Honotanstack-spa.md: Frontend SPA with TanStack Routershadcn-ui.md: UI component library setup</reference_index>
<best_practices>
TypeScript:
Package management:
Tooling consistency:
</best_practices>