Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计异常

nodejs-expertNode.js expert 搜索

Agent Skill

nodejs-expert 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,056

周安装

84

GitHub Stars

25

下载量

665
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:nodejs-expert(Node.js expert 搜索)
来源仓库:https://github.com/oimiragieo/agent-studio
仓库路径:skills/nodejs-expert
安装命令:
npx skills add https://github.com/oimiragieo/agent-studio --skill nodejs-expert
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/oimiragieo/agent-studio --skill nodejs-expert

简介

nodejs-expert 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。

  • 适用于需要根据关键词或任务场景从仓库中提取线索的场景,如 Node.js 开发相关研究。
  • 通过 npx skills add 命令从 GitHub 安装,结合原始 README 核验具体用法。
  • 安装前需确认权限范围和维护状态,注意是否触发联网、命令执行或文件读写操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Nodejs Expert

nestjs core module guidelines

When reviewing or writing code, apply these guidelines:

  • Global filters for exception handling.
  • Global middlewares for request management.
  • Guards for permission management.
  • Interceptors for request management.

nestjs general guidelines

When reviewing or writing code, apply these guidelines:

  • Use modular architecture
  • Encapsulate the API in modules.

- One module per main domain/route. - One controller for its route. - And other controllers for secondary routes. - A models folder with data types. - DTOs validated with class-validator for inputs. - Declare simple types for outputs. - A services module with business logic and persistence. - One service per entity.

  • A core module for nest artifacts

- Global filters for exception handling. - Global middlewares for request management. - Guards for permission management. - Interceptors for request management.

  • A shared module for services shared between modules.

- Utilities - Shared business logic

  • Use the standard Jest framework for testing.
  • Write tests for each controller and service.
  • Write end to end tests for each api module.
  • Add a admin/test method to each controller as a smoke test.

nestjs module structure guidelines

When reviewing or writing code, apply these guidelines:

  • One module per main domain/route.
  • One controller for its route.
  • And other controllers for secondary routes.
  • A models folder with data types.
  • DTOs validated with class-validator for inputs.
  • Declare simple types for outputs.
  • A services module with business logic and persistence.
  • One service per entity.

nestjs shared module guidelines

When reviewing or writing code, apply these guidelines:

  • Utilities
  • Shared business logic

nestjs testing guidelines

When reviewing or writing code, apply these guidelines:

  • Use the standard Jest framework for testing.
  • Write tests for each controller and service.
  • Write end to end tests for eac

Consolidated Skills

This expert skill consolidates 1 individual skills:

  • nodejs-expert

Related Skills

  • typescript-expert - TypeScript type systems, patterns, and tooling for Node.js development

Iron Laws

  1. ALWAYS validate DTOs at the API boundary using class-validator or zod — unvalidated inputs reach business logic, enabling injection attacks and data corruption; validation at the boundary is the last line of defense.
  2. NEVER use callbacks in new Node.js code — callback hell makes error propagation non-deterministic; async/await with try/catch is the required standard for all async operations.
  3. ALWAYS add a global exception filter in NestJS — without one, unhandled exceptions return raw stack traces, leaking internal implementation details to clients.
  4. NEVER block the Node.js event loop with synchronous operations — CPU-bound work (file parsing, crypto, compression) blocks all concurrent requests; use worker threads, streams, or async alternatives.
  5. ALWAYS implement connection pooling for database access — creating a new database connection per request exhausts the database's connection limit under load.

Anti-Patterns

Anti-PatternWhy It FailsCorrect Approach
Missing DTO validation at API boundaryUnvalidated inputs enable injection and data corruptionUse class-validator on DTOs; reject invalid inputs at the controller boundary
Using callbacks in new codeError propagation non-deterministic; unhandled rejections crash the processUse async/await with try/catch for all async operations
No global exception filter in NestJSUnhandled exceptions expose raw stack traces to clientsAdd a global ExceptionFilter that logs internally and returns sanitized error responses
Synchronous operations on the event loopBlocks all concurrent requests; latency spikes under any loadUse async alternatives (fsPromises, streams); offload CPU-bound work to worker threads
New database connection per requestExhausts connection limit under load; adds connection overhead latencyPool connections at startup with pg.Pool, Knex, or ORM connection pooling

Memory Protocol (MANDATORY)

Before starting:

cat .claude/context/memory/learnings.md

After completing: Record any new patterns or exceptions discovered.

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.92%
按下载量换算239

Claude

27.52%
按下载量换算183

Cursor

21.06%
按下载量换算140

Gemini CLI

9.38%
按下载量换算62

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills