Agent skill

Search First

by affaan-m in affaan-m/ECC

研究优先于编码的工作流程。在编写自定义代码之前,搜索现有的工具、库和模式。调用研究员代理. An agent skill from affaan-m/ECC.

MITAuto-check passedDevelopment

Install Search First

skills CLI
$ npx skills add affaan-m/ECC --skill search-first -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install affaan-m/ECC search-first --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/zh-CN/skills/search-first .claude/skills/search-first && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
search-first
GitHub stars
277k
Used in
3 other repos
Token cost
~873 tokens
SKILL.md length
164 words
Files
1
Skills in repo
683
Repo updated
First seen
Licence
MIT

At a glance

研究优先于编码的工作流程。在编写自定义代码之前,搜索现有的工具、库和模式。调用研究员代理. An agent skill from affaan-m/ECC.

  • Works in 5 steps: 这已经在仓库中存在吗? → 首先通过相关模块/测试检查 rg → 这是一个常见问题吗? → 搜索 npm/PyPI → 有对应的 MCP 吗? → 检查 ~/.claude/settings.json… → …
  • Tasks that involve Linting and formatting
  • SKILL.md covers 触发时机, 工作流程, 决策矩阵 and 使用方法, plus 4 more sections
  • Calls go

What it does

Search First is an agent skill from affaan-m/ECC. 研究优先于编码的工作流程。在编写自定义代码之前,搜索现有的工具、库和模式。调用研究员代理。

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Linting and formatting. It works with Model Context Protocol. The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.

When your agent uses it

  • Tasks that involve Linting and formatting

Example prompts

  • “/search-first”

Requirements

  • Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 这已经在仓库中存在吗? → 首先通过相关模块/测试检查 rg
  2. 这是一个常见问题吗? → 搜索 npm/PyPI
  3. 有对应的 MCP 吗? → 检查 ~/.claude/settings.json 并进行搜索
  4. 有对应的技能吗? → 检查 ~/.claude/skills/
  5. 有 GitHub 上的实现/模板吗? → 在编写全新代码之前,先运行 GitHub 代码搜索以查找维护中的开源项目

What it can do on your machine

Read from SKILL.md and the folder at commit 2d515e4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Search First loads about 873 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 164 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~873

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from affaan-m/ECC at commit 2d515e4, republished under its MIT licence (© affaan-m). 164 words, ~873 tokens.

Download SKILL.mdSave it as .claude/skills/search-first/SKILL.md (or your agent's skills folder).
name
search-first
description
研究优先于编码的工作流程。在编写自定义代码之前,搜索现有的工具、库和模式。调用研究员代理。
origin
ECC

/search-first — 编码前先研究

系统化“在实现之前先寻找现有解决方案”的工作流程。

触发时机

在以下情况使用此技能:

  • 开始一项很可能已有解决方案的新功能
  • 添加依赖项或集成
  • 用户要求“添加 X 功能”而你准备开始编写代码
  • 在创建新的实用程序、助手或抽象之前

工作流程

┌─────────────────────────────────────────────┐
│  1. 需求分析                               │
│     确定所需功能                          │
│     识别语言/框架限制                     │
├─────────────────────────────────────────────┤
│  2. 并行搜索(研究员代理)                │
│     ┌──────────┐ ┌──────────┐ ┌──────────┐  │
│     │  npm /   │ │  MCP /   │ │  GitHub / │  │
│     │  PyPI    │ │  技能    │ │  网络     │  │
│     └──────────┘ └──────────┘ └──────────┘  │
├─────────────────────────────────────────────┤
│  3. 评估                                   │
│     对候选方案进行评分(功能、维护、      │
│     社区、文档、许可证、依赖)            │
├─────────────────────────────────────────────┤
│  4. 决策                                   │
│     ┌─────────┐  ┌──────────┐  ┌─────────┐  │
│     │  采用   │  │  扩展    │  │  构建   │  │
│     │ 原样    │  │  /包装   │  │  定制   │  │
│     └─────────┘  └──────────┘  └─────────┘  │
├─────────────────────────────────────────────┤
│  5. 实施                                   │
│     安装包 / 配置 MCP /                    │
│     编写最小化自定义代码                   │
└─────────────────────────────────────────────┘

决策矩阵

信号行动
完全匹配,维护良好,MIT/Apache 许可证采纳 — 直接安装并使用
部分匹配,基础良好扩展 — 安装 + 编写薄封装层
多个弱匹配组合 — 组合 2-3 个小包
未找到合适的构建 — 编写自定义代码,但需基于研究

使用方法

快速模式(内联)

在编写实用程序或添加功能之前,在脑中过一遍:

  1. 这已经在仓库中存在吗? → 首先通过相关模块/测试检查 rg
  2. 这是一个常见问题吗? → 搜索 npm/PyPI
  3. 有对应的 MCP 吗? → 检查 ~/.claude/settings.json 并进行搜索
  4. 有对应的技能吗? → 检查 ~/.claude/skills/
  5. 有 GitHub 上的实现/模板吗? → 在编写全新代码之前,先运行 GitHub 代码搜索以查找维护中的开源项目
完整模式(代理)

对于非平凡的功能,启动研究员代理:

任务(子代理类型="通用型",提示="
  研究现有工具用于:[描述]
  语言/框架:[语言]
  约束:[任何]

  搜索:npm/PyPI、MCP 服务器、Claude Code 技能、GitHub
  返回:结构化对比与推荐
")

按类别搜索快捷方式

开发工具
  • Linting → eslint, ruff, textlint, markdownlint
  • Formatting → prettier, black, gofmt
  • Testing → jest, pytest, go test
  • Pre-commit → husky, lint-staged, pre-commit
AI/LLM 集成
  • Claude SDK → 使用 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
数据与 API
  • HTTP 客户端 → httpx (Python), ky/got (Node)
  • 验证 → zod (TS), pydantic (Python)
  • 数据库 → 首先检查是否有 MCP 服务器
内容与发布
  • Markdown 处理 → remark, unified, markdown-it
  • 图片优化 → sharp, imagemin

集成点

与规划器代理

规划器应在阶段 1(架构评审)之前调用研究员:

  • 研究员识别可用的工具
  • 规划器将它们纳入实施计划
  • 避免在计划中“重新发明轮子”
与架构师代理

架构师应向研究员咨询:

  • 技术栈决策
  • 集成模式发现
  • 现有参考架构
与迭代检索技能

结合进行渐进式发现:

  • 循环 1:广泛搜索 (npm, PyPI, MCP)
  • 循环 2:详细评估顶级候选方案
  • 循环 3:测试与项目约束的兼容性

示例

示例 1:“添加死链检查”
需求:检查 Markdown 文件中的失效链接
搜索:npm "markdown dead link checker"
发现:textlint-rule-no-dead-link(评分:9/10)
行动:采纳 — npm install textlint-rule-no-dead-link
结果:无需自定义代码,经过实战检验的解决方案
示例 2:“添加 HTTP 客户端包装器”
需求:具备重试和超时处理能力的弹性 HTTP 客户端
搜索:npm "http client retry"、PyPI "httpx retry"
发现:got(Node)带重试插件、httpx(Python)带内置重试功能
行动:采用——直接使用 got/httpx 并配置重试
结果:零定制代码,生产验证的库
示例 3:“添加配置文件 linter”
需求:根据模式验证项目配置文件
搜索:npm "config linter schema"、"json schema validator cli"
发现:ajv-cli(评分:8/10)
操作:采用 + 扩展 —— 安装 ajv-cli,编写项目特定的模式
结果:1 个包 + 1 个模式文件,无需自定义验证逻辑

反模式

  • 直接跳转到编码:不检查是否存在就编写实用程序
  • 忽略 MCP:不检查 MCP 服务器是否已提供该能力
  • 过度定制:对库进行如此厚重的包装以至于失去了其优势
  • 依赖项膨胀:为了一个小功能安装一个庞大的包

© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/zh-CN/skills/search-first of affaan-m/ECC.

Open the folder on GitHubat commit 2d515e4

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in affaan-m/ECC, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Search First next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Search First compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Search First this skillaffaan-m/ECC277k3 repos~873Automated safety check: PassMIT
Ue Code AuthoringJasonMa0012/MooaToon750—~1.9kAutomated safety check: NotesCustom licence
Rsigmatimescale/rsigma166—~1.2kAutomated safety check: PassMIT
Code Reviewnteract/semiotic2.7k—~1.5kAutomated safety check: PassApache-2.0
Building Glamorous TuisDicklesworthstone/meta_skill205—~3.4kAutomated safety check: PassCustom licence
Cuga Contributor Workflowscuga-project/cuga-agent896—~277Automated safety check: PassCustom licence

Similar skills

  • Ue Code Authoring

    JasonMa0012/MooaToon

    A skill your agent uses when writing or modifying UE C++ (classes, actors, components, subsystems, interfaces, function libraries) with Rider MCP available.

    750 GitHub stars~1.9k tokensUpdated 23 days ago
    DevelopmentAuto-check: notes
  • Rsigma

    timescale/rsigma

    Use the rsigma CLI and MCP server: engine eval, engine daemon, rule lint, rule draft, rule tune, rule backtest, backend convert, mcp serve.

    166 GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Code Review

    nteract/semiotic

    Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence.

    2.7k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Building Glamorous Tuis

    Dicklesworthstone/meta_skill

    Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum).

    205 GitHub stars~3.4k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Cuga Contributor Workflows

    cuga-project/cuga-agent

    Run CUGA contributor workflows: Conventional Commits, create pull requests against origin with gh and PR templates, and ruff check/format via uv.

    896 GitHub stars~277 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Zhtw Verify

    sysprog21/zhtw-mcp

    How a zhtw-mcp change is validated - make check as the gate, the generated tables and the ruleset normalization that have to be current before it passes, the formatter chain in scripts/indent.sh…

    488 GitHub stars~2.8k tokensUpdated today
    DevelopmentAuto-check passed

More from affaan-m/ECC

All 682 skills in this repo
  • Skill Stocktake

    affaan-m/ECC

    Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.

    277k GitHub starsUsed in 5 repos~3.1k tokens
    Auto-check passed
  • Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.

    277k GitHub starsUsed in 3 repos~3.5k tokens
    Auto-check: notes
  • Docs Governance

    affaan-m/ECC

    Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references.

    277k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    277k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed
  • Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    277k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Set an ECC-specific frontend design direction for production UI work.

    277k GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Categories

Questions about Search First

What does Search First do?

研究优先于编码的工作流程。在编写自定义代码之前,搜索现有的工具、库和模式。调用研究员代理. An agent skill from affaan-m/ECC. Search First is an agent skill from affaan-m/ECC.

When should I use Search First?

Search First fits situations like: tasks that involve Linting and formatting.

How do I install Search First in Claude Code?

Run `npx skills add affaan-m/ECC --skill search-first -a claude-code`. Or copy the skill folder (docs/zh-CN/skills/search-first in affaan-m/ECC) into .claude/skills/search-first in your project. Claude Code loads it when a task matches its description.

How do I install Search First in Codex?

Run `npx skills add affaan-m/ECC --skill search-first -a codex`. Or copy the skill folder (docs/zh-CN/skills/search-first in affaan-m/ECC) into .agents/skills/search-first in your project. Codex loads it when a task matches its description.

Can I use Search First in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill search-first -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/search-first, .gemini/skills/search-first, .github/skills/search-first and .opencode/skills/search-first in your project.

What does Search First need to run?

Going by SKILL.md and its folder, Search First needs the command-line tools its instructions call (go). Our summary lists: Node.js.

Does Search First access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Search First safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Search First use?

Search First is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Search First use?

About 873 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Search First?

Skills that share tags, products or a category with Search First: Ue Code Authoring (JasonMa0012/MooaToon, 750 stars), Rsigma (timescale/rsigma, 166 stars), Code Review (nteract/semiotic, 2.7k stars) and Building Glamorous Tuis (Dicklesworthstone/meta_skill, 205 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Search First?

affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 276,673 GitHub stars. The repository holds 683 skills in this directory. The repository was last updated on October 11, 2026.

Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.