Token导航 LogoToken导航

Agent Skill · 研究检索

c4-code(c4 代码)

c4-code 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。

c4-code 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 20,555。

总安装 5,180周安装 218GitHub Stars 35,737下载 1,814核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:c4-code(c4 代码)
来源仓库:https://github.com/sickn33/antigravity-awesome-skills
仓库路径:skills/c4-code
安装命令:
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill c4-code
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/sickn33/antigravity-awesome-skills --skill c4-code

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

c4-code 用于查找、检索和筛选相关信息,支持关键词驱动的任务场景。适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。通过 npx skills add 命令从 GitHub 仓库安装,便于集成到现有工作流。安装前应检查权限范围和仓库维护状态,防止意外网络请求或文件操作。

c4-code 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/c4-code

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill c4-…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

c4-code 怎么安装?

在终端执行 npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill c4-code。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

c4-code 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

c4-code 需要什么权限?

权限级别是需要联网。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。

c4-code 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

c4-code 用的人多吗?

公开数据是累计安装 5,180 次,近一周安装 218 次,下载 1,814 次,GitHub 35,737 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

c4-code 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 来源仓库有 35,737 星,维护活跃度相对可查。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
c4-code

c4 代码 · 本页

5,18035,737需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

C4 Code Level: [Directory Name]

Use this skill when

  • Working on c4 code level: [directory name] tasks or workflows
  • Needing guidance, best practices, or checklists for c4 code level: [directory name]

Do not use this skill when

  • The task is unrelated to c4 code level: [directory name]
  • You need a different domain or tool outside this scope

Instructions

  • Clarify goals, constraints, and required inputs.
  • Apply relevant best practices and validate outcomes.
  • Provide actionable steps and verification.
  • If detailed examples are required, open resources/implementation-playbook.md.

Overview

  • Name: [Descriptive name for this code directory]
  • Description: [Short description of what this code does]
  • Location: [Link to actual directory path]
  • Language: [Primary programming language(s)]
  • Purpose: [What this code accomplishes]

Code Elements

Functions/Methods

  • functionName(param1: Type, param2: Type): ReturnType

- Description: [What this function does] - Location: [file path:line number] - Dependencies: [what this function depends on]

Classes/Modules

  • ClassName

- Description: [What this class does] - Location: [file path] - Methods: [list of methods] - Dependencies: [what this class depends on]

Dependencies

Internal Dependencies

  • [List of internal code dependencies]

External Dependencies

  • [List of external libraries, frameworks, services]

Relationships

Optional Mermaid diagrams for complex code structures. Choose the diagram type based on the programming paradigm. Code diagrams show the internal structure of a single component.

Object-Oriented Code (Classes, Interfaces)

Use classDiagram for OOP code with classes, interfaces, and inheritance:

---
title: Code Diagram for [Component Name]
---
classDiagram
    namespace ComponentName {
        class Class1 {
            +attribute1 Type
            +method1() ReturnType
        }
        class Class2 {
            -privateAttr Type
            +publicMethod() void
        }
        class Interface1 {
            <<interface>>
            +requiredMethod() ReturnType
        }
    }

    Class1 ..|> Interface1 : implements
    Class1 --> Class2 : uses
### Functional/Procedural Code (Modules, Functions)

For functional or procedural code, you have two options:

**Option A: Module Structure Diagram** - Use `classDiagram` to show modules and their exported functions:

title: Module Structure for [Component Name]


classDiagram namespace DataProcessing { class validators { <<module>> +validateInput(data) Result~Data, Error~ +validateSchema(schema, data) bool +sanitize(input) string } class transformers { <<module>> +parseJSON(raw) Record +normalize(data) NormalizedData +aggregate(items) Summary } class io { <<module>> +readFile(path) string +writeFile(path, content) void } }

transformers --> validators : uses transformers --> io : reads from


**Option B: Data Flow Diagram** - Use `flowchart` to show function pipelines and data transformations:

title: Data Pipeline for [Component Name]


flowchart LR subgraph Input A[readFile] end subgraph Transform B[parseJSON] C[validateInput] D[normalize] E[aggregate] end subgraph Output F[writeFile] end

A -->|raw string| B B -->|parsed data| C C -->|valid data| D D -->|normalized| E E -->|summary| F


**Option C: Function Dependency Graph** - Use `flowchart` to show which functions call which:

title: Function Dependencies for [Component Name]


flowchart TB subgraph Public API processData[processData] exportReport[exportReport] end subgraph Internal Functions validate[validate] transform[transform] format[format] cache[memoize] end subgraph Pure Utilities compose[compose] pipe[pipe] curry[curry] end

processData --> validate processData --> transform processData --> cache transform --> compose transform --> pipe exportReport --> format exportReport --> processData


### Choosing the Right Diagram

| Code Style                       | Primary Diagram                  | When to Use                                             |
| -------------------------------- | -------------------------------- | ------------------------------------------------------- |
| OOP (classes, interfaces)        | `classDiagram`                   | Show inheritance, composition, interface implementation |
| FP (pure functions, pipelines)   | `flowchart`                      | Show data transformations and function composition      |
| FP (modules with exports)        | `classDiagram` with `<<module>>` | Show module structure and dependencies                  |
| Procedural (structs + functions) | `classDiagram`                   | Show data structures and associated functions           |
| Mixed                            | Combination                      | Use multiple diagrams if needed                         |

**Note**: According to the [C4 model](https://c4model.com/diagrams), code diagrams are typically only created when needed for complex components. Most teams find system context and container diagrams sufficient. Choose the diagram type that best communicates the code structure regardless of paradigm.

## Notes

[Any additional context or important information]

Example Interactions

Object-Oriented Codebases

  • "Analyze the src/api directory and create C4 Code-level documentation"
  • "Document the service layer code with complete class hierarchies and dependencies"
  • "Create C4 Code documentation showing interface implementations in the repository layer"

Functional/Procedural Codebases

  • "Document all functions in the authentication module with their signatures and data flow"
  • "Create a data pipeline diagram for the ETL transformers in src/pipeline"
  • "Analyze the utils directory and document all pure functions and their composition patterns"
  • "Document the Rust modules in src/handlers showing function dependencies"
  • "Create C4 Code documentation for the Elixir GenServer modules"

Mixed Paradigm

  • "Document the Go handlers package showing structs and their associated functions"
  • "Analyze the TypeScript codebase that mixes classes with functional utilities"

Key Distinctions

  • vs C4-Component agent: Focuses on individual code elements; Component agent synthesizes multiple code files into components
  • vs C4-Container agent: Documents code structure; Container agent maps components to deployment units
  • vs C4-Context agent: Provides code-level detail; Context agent creates high-level system diagrams

Output Examples

When analyzing code, provide:

  • Complete function/method signatures with all parameters and return types
  • Clear descriptions of what each code element does
  • Links to actual source code locations
  • Complete dependency lists (internal and external)
  • Structured documentation following C4 Code-level template
  • Mermaid diagrams for complex code relationships when needed
  • Consistent naming and formatting across all code documentation

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

平台分布

Codex

38.34%
按下载量换算695

Claude

26.94%
按下载量换算489

Cursor

18.32%
按下载量换算332

Gemini CLI

9.9%
按下载量换算180

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills