search-first

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/search-first — Research Before You Code

/search-first — 编码前调研

Systematizes the "search for existing solutions before implementing" workflow.

将「实现前先搜索现有解决方案」的工作流系统化。

Trigger

触发场景

Use this skill when:

Starting a new feature that likely has existing solutions
Adding a dependency or integration
The user asks "add X functionality" and you're about to write code
Before creating a new utility, helper, or abstraction

在以下场景使用此skill：

启动一个可能已有现成解决方案的新功能
添加依赖或集成
用户要求「添加X功能」，而你即将编写代码时
创建新的工具类、辅助函数或抽象层之前

Workflow

工作流

┌─────────────────────────────────────────────┐
│  1. NEED ANALYSIS                           │
│     Define what functionality is needed      │
│     Identify language/framework constraints  │
├─────────────────────────────────────────────┤
│  2. PARALLEL SEARCH (researcher agent)      │
│     ┌──────────┐ ┌──────────┐ ┌──────────┐  │
│     │  npm /   │ │  MCP /   │ │  GitHub / │  │
│     │  PyPI    │ │  Skills  │ │  Web      │  │
│     └──────────┘ └──────────┘ └──────────┘  │
├─────────────────────────────────────────────┤
│  3. EVALUATE                                │
│     Score candidates (functionality, maint, │
│     community, docs, license, deps)         │
├─────────────────────────────────────────────┤
│  4. DECIDE                                  │
│     ┌─────────┐  ┌──────────┐  ┌─────────┐  │
│     │  Adopt  │  │  Extend  │  │  Build   │  │
│     │ as-is   │  │  /Wrap   │  │  Custom  │  │
│     └─────────┘  └──────────┘  └─────────┘  │
├─────────────────────────────────────────────┤
│  5. IMPLEMENT                               │
│     Install package / Configure MCP /       │
│     Write minimal custom code               │
└─────────────────────────────────────────────┘

┌─────────────────────────────────────────────┐
│  1. 需求分析                               │
│     明确所需功能                            │
│     识别语言/框架约束                        │
├─────────────────────────────────────────────┤
│  2. 并行搜索（研究员Agent）                  │
│     ┌──────────┐ ┌──────────┐ ┌──────────┐  │
│     │  npm /   │ │  MCP /   │ │  GitHub / │  │
│     │  PyPI    │ │  Skills  │ │  Web      │  │
│     └──────────┘ └──────────┘ └──────────┘  │
├─────────────────────────────────────────────┤
│  3. 评估                                   │
│     对候选方案评分（功能、维护情况、         │
│     社区活跃度、文档、许可证、依赖）         │
├─────────────────────────────────────────────┤
│  4. 决策                                   │
│     ┌─────────┐  ┌──────────┐  ┌─────────┐  │
│     │  直接采用  │  │  扩展/封装  │  │  自定义开发  │  │
│     │         │  │          │  │         │  │
│     └─────────┘  └──────────┘  └─────────┘  │
├─────────────────────────────────────────────┤
│  5. 实现                                   │
│     安装包 / 配置MCP /                      │
│     编写最少的自定义代码                    │
└─────────────────────────────────────────────┘

Decision Matrix

决策矩阵

Signal	Action
Exact match, well-maintained, MIT/Apache	Adopt — install and use directly
Partial match, good foundation	Extend — install + write thin wrapper
Multiple weak matches	Compose — combine 2-3 small packages
Nothing suitable found	Build — write custom, but informed by research

信号	行动
完全匹配、维护良好、采用MIT/Apache协议	直接采用 — 直接安装使用
部分匹配、基础良好	扩展 — 安装并编写轻量封装层
多个弱匹配方案	组合 — 整合2-3个小型包
未找到合适方案	自定义开发 — 基于调研结果编写自定义代码

How to Use

使用方法

Quick Mode (inline)

快速模式（内联）

Before writing a utility or adding functionality, mentally run through:

Is this a common problem? → Search npm/PyPI
Is there an MCP for this? → Check
```
~/.claude/settings.json
```
and search
Is there a skill for this? → Check
```
~/.claude/skills/
```
Is there a GitHub template? → Search GitHub

在编写工具类或添加功能前，在脑中快速过一遍：

这是常见问题吗？→ 搜索npm/PyPI
有没有对应的MCP？→ 查看
```
~/.claude/settings.json
```
并搜索
有没有对应的skill？→ 查看
```
~/.claude/skills/
```
有没有GitHub模板？→ 搜索GitHub

Full Mode (agent)

完整模式（Agent）

For non-trivial functionality, launch the researcher agent:

Task(subagent_type="general-purpose", prompt="
  Research existing tools for: [DESCRIPTION]
  Language/framework: [LANG]
  Constraints: [ANY]

  Search: npm/PyPI, MCP servers, Claude Code skills, GitHub
  Return: Structured comparison with recommendation
")

对于非 trivial 的功能，启动研究员Agent：

Task(subagent_type="general-purpose", prompt="
  Research existing tools for: [DESCRIPTION]
  Language/framework: [LANG]
  Constraints: [ANY]

  Search: npm/PyPI, MCP servers, Claude Code skills, GitHub
  Return: Structured comparison with recommendation
")

Search Shortcuts by Category

按类别划分的搜索快捷方式

Development Tooling

开发工具链

Linting →
```
eslint
```
,
```
ruff
```
,
```
textlint
```
,
```
markdownlint
```
Formatting →
```
prettier
```
,
```
black
```
,
```
gofmt
```
Testing →
```
jest
```
,
```
pytest
```
,
```
go test
```
Pre-commit →
```
husky
```
,
```
lint-staged
```
,
```
pre-commit
```

代码检查 →
```
eslint
```
,
```
ruff
```
,
```
textlint
```
,
```
markdownlint
```
代码格式化 →
```
prettier
```
,
```
black
```
,
```
gofmt
```
测试 →
```
jest
```
,
```
pytest
```
,
```
go test
```
提交前检查 →
```
husky
```
,
```
lint-staged
```
,
```
pre-commit
```

AI/LLM Integration

AI/LLM集成

Claude SDK → Context7 for latest docs
Prompt management → Check MCP servers
Document processing →
```
unstructured
```
,
```
pdfplumber
```
,
```
mammoth
```

Claude SDK → Context7 获取最新文档
提示词管理 → 检查MCP服务器
文档处理 →
```
unstructured
```
,
```
pdfplumber
```
,
```
mammoth
```

Data & APIs

数据与API

HTTP clients →
```
httpx
```
(Python),
```
ky
```
/
```
got
```
(Node)
Validation →
```
zod
```
(TS),
```
pydantic
```
(Python)
Database → Check for MCP servers first

HTTP客户端 →
```
httpx
```
(Python),
```
ky
```
/
```
got
```
(Node)
校验 →
```
zod
```
(TS),
```
pydantic
```
(Python)
数据库 → 先检查MCP服务器

Content & Publishing

内容与发布

Markdown processing →
```
remark
```
,
```
unified
```
,
```
markdown-it
```
Image optimization →
```
sharp
```
,
```
imagemin
```

Markdown处理 →
```
remark
```
,
```
unified
```
,
```
markdown-it
```
图片优化 →
```
sharp
```
,
```
imagemin
```

Integration Points

集成点

With planner agent

与规划师Agent集成

The planner should invoke researcher before Phase 1 (Architecture Review):

Researcher identifies available tools
Planner incorporates them into the implementation plan
Avoids "reinventing the wheel" in the plan

规划师应在阶段1（架构评审）前调用研究员：

研究员识别可用工具
规划师将其纳入实现计划
避免在计划中「重复造轮子」

With architect agent

与架构师Agent集成

The architect should consult researcher for:

Technology stack decisions
Integration pattern discovery
Existing reference architectures

架构师应向研究员咨询：

技术栈决策
集成模式探索
现有参考架构

With iterative-retrieval skill

与迭代检索skill集成

Combine for progressive discovery:

Cycle 1: Broad search (npm, PyPI, MCP)
Cycle 2: Evaluate top candidates in detail
Cycle 3: Test compatibility with project constraints

结合使用以进行渐进式发现：

第一轮：广泛搜索（npm、PyPI、MCP）
第二轮：详细评估顶级候选方案
第三轮：测试与项目约束的兼容性

Examples

示例

Example 1: "Add dead link checking"

示例1：「添加死链检查功能」

Need: Check markdown files for broken links
Search: npm "markdown dead link checker"
Found: textlint-rule-no-dead-link (score: 9/10)
Action: ADOPT — npm install textlint-rule-no-dead-link
Result: Zero custom code, battle-tested solution

需求：检查Markdown文件中的死链
搜索：npm "markdown dead link checker"
找到：textlint-rule-no-dead-link（评分：9/10）
行动：直接采用 — npm install textlint-rule-no-dead-link
结果：零自定义代码，经过实战检验的解决方案

Example 2: "Add HTTP client wrapper"

示例2：「添加HTTP客户端封装」

Need: Resilient HTTP client with retries and timeout handling
Search: npm "http client retry", PyPI "httpx retry"
Found: got (Node) with retry plugin, httpx (Python) with built-in retry
Action: ADOPT — use got/httpx directly with retry config
Result: Zero custom code, production-proven libraries

需求：具备重试和超时处理的高可用HTTP客户端
搜索：npm "http client retry", PyPI "httpx retry"
找到：got（Node）带重试插件，httpx（Python）内置重试功能
行动：直接采用 — 直接使用got/httpx并配置重试
结果：零自定义代码，生产环境验证的库

Example 3: "Add config file linter"

示例3：「添加配置文件检查器」

Need: Validate project config files against a schema
Search: npm "config linter schema", "json schema validator cli"
Found: ajv-cli (score: 8/10)
Action: ADOPT + EXTEND — install ajv-cli, write project-specific schema
Result: 1 package + 1 schema file, no custom validation logic

需求：根据Schema验证项目配置文件
搜索：npm "config linter schema", "json schema validator cli"
找到：ajv-cli（评分：8/10）
行动：直接采用+扩展 — 安装ajv-cli，编写项目专属Schema
结果：1个包 + 1个Schema文件，无需自定义校验逻辑

Anti-Patterns

反模式

Jumping to code: Writing a utility without checking if one exists
Ignoring MCP: Not checking if an MCP server already provides the capability
Over-customizing: Wrapping a library so heavily it loses its benefits
Dependency bloat: Installing a massive package for one small feature

直接写代码：不检查是否已有工具类就直接编写
忽略MCP：不检查MCP服务器是否已提供该能力
过度自定义：对库进行过度封装，使其失去原有优势
依赖膨胀：为了一个小功能安装大型包