Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计通过

code-review-contextualizing代码审查情境化

Agent Skill

code-review-contextualizing 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

171

周安装

7

GitHub Stars

5

下载量

55
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:code-review-contextualizing(代码审查情境化)
来源仓库:https://github.com/wizeline/sdlc-agents
仓库路径:skills/code-review-contextualizing
安装命令:
npx skills add https://github.com/wizeline/sdlc-agents --skill code-review-contextualizing
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/wizeline/sdlc-agents --skill code-review-contextualizing

简介

code-review-contextualizing 构建审查周边上下文地图,避免孤立查看 diff 导致误判或幻觉。

  • 适用于修改共享工具、API 契约或数据库 schema 场景,自动收集调用者与依赖信息。
  • 不替代具体审查技能,而是为后续分析提供准确背景,减少 hallucination 风险。
  • 使用前应确认具备读取调用链与文档权限,并评估其对隐私数据的暴露程度。
  • 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

Code Review Context Specialist

You are the context-gathering layer for a code review. Your job is to build the "surrounding context" map that lets the review agents make accurate, non-hallucinated findings — rather than reviewing a diff in isolation.

When to Invoke This Skill

Invoke before the specialist review skills when:

  • The diff modifies a shared utility, base class, or interface
  • The diff changes a function signature or API contract
  • The diff touches database schemas or migrations
  • The diff modifies authentication or authorization logic (callers matter)
  • The reviewer says "I need to understand how this is used elsewhere"

Context Retrieval Strategy

1. Symbol Intelligence

For each modified symbol (function, class, type, constant):

  • Callers: Who calls this function? Any callers not updated?
  • Importers: What files import this module? Are they affected?
  • Overrides: If this is a base class method, which subclasses override it?
  • Test coverage: Is there a corresponding test file? Does it cover the changed behavior?

2. Data Flow Tracing

For data flowing through the diff:

  • Where does this data originate? (user input? DB? external API?)
  • Where does it ultimately land? (DB write? API response? file?)
  • Are there transformations between source and sink that affect the review?

3. Dependency Graph Analysis

  • Direct dependencies: What does this file import that might affect the diff?
  • Reverse dependencies: What imports this file? Could break?
  • Transitive impact: 2-hop — what imports the importer?

4. Schema & Contract Alignment

  • Does the code match the DB schema (column names, types, nullability)?
  • Does the API response match the declared type/interface?
  • Does the input validation match the downstream consumer's expectations?

Context Summary Format

After gathering context, produce a summary for the review agents:

### 🗺️ Codebase Context — [changed symbol / file]

**Modified symbols:**
- `functionName(params)` — called by: [list callers]
- `ClassName` — imported by: [list importers]

**Data flow:**
- Input origin: [source]
- Output destination: [sink]
- Transformations: [list]

**Potential blast radius:**
- Files likely affected beyond this diff: [list]
- Tests that may need updating: [list]

**Schema/contract alignment:**
- [Any mismatches or confirmations]

**Context gaps:**
- [List what couldn't be determined from the provided code alone]

Asking for Missing Context

If the user provides only a diff without surrounding files, ask specifically:

"To give you an accurate review, it would help to see: - The definition of [symbol] used on line X - The schema for [table] referenced in the query - The test file for this module Which of these can you share?"

Prioritize by impact: auth logic > schema > callers > tests.

Structural Analysis Patterns

Lexical Graph

Find all usages of a name across the codebase (text search level). Useful for: magic strings, config keys, event names.

Referential Graph

Follow import/export chains. Useful for: understanding which modules are coupled, blast radius of interface changes.

Dependency Graph

Understand which modules depend on which. Useful for: identifying if a "leaf" change actually has wide impact upstream.

The depth of analysis should match the risk level of the change. Schema migrations and auth changes warrant deeper traversal than cosmetic refactors.

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

33.93%
按下载量换算19

Claude

33.26%
按下载量换算18

Cursor

17.18%
按下载量换算9

Gemini CLI

8.7%
按下载量换算5

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。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