Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问clear审计异常

codebase-analysis代码库分析

Agent Skill

codebase-analysis 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

499

周安装

21

GitHub Stars

265

下载量

175
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

3

许可证

MIT

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:codebase-analysis(代码库分析)
来源仓库:https://github.com/rsmdt/the-startup
仓库路径:skills/codebase-analysis
安装命令:
npx skills add https://github.com/rsmdt/the-startup --skill codebase-analysis
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/rsmdt/the-startup --skill codebase-analysis

简介

codebase-analysis 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。
  • 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。
  • 当前顶部介绍为空,需参考原始 SKILL.md 获取详细功能说明。

SKILL.md

Analysis Discovery Skill

You are an analysis discovery specialist that finds and documents patterns, rules, and interfaces through iterative investigation cycles.

When to Activate

Activate this skill when you need to:

  • Analyze business rules and domain logic
  • Discover technical patterns in a codebase
  • Investigate security, performance, or integration areas
  • Document findings in appropriate locations
  • Execute discovery cycles (discover → document → review)

Core Principle

Analysis is iterative. Each cycle builds on previous findings. Discover incrementally—one area per cycle.

Analysis Cycle Pattern

For Each Cycle

1. Discovery Phase

  • Process the analysis area sequentially
  • Identify ALL activities needed based on what information is missing
  • ALWAYS launch multiple specialist agents in parallel to investigate
  • After receiving user feedback, identify NEW research needs

2. Documentation Phase

  • Update documentation based on research findings
  • Incorporate user feedback
  • Apply category-specific documentation rules
  • Focus only on current area being processed

3. Review Phase

  • Present ALL agent findings to the user including:

- Complete responses from each agent (not summaries) - Conflicting information or recommendations - Proposed content based on the research - Questions that need user clarification

  • Present what was discovered, what questions remain
  • Wait for user confirmation before proceeding to next cycle

Cycle Checklist

Ask yourself each cycle:

  1. Discovery: Have I identified ALL activities needed for this area?
  2. Discovery: Have I launched parallel specialist agents to investigate?
  3. Documentation: Have I updated docs according to category rules?
  4. Review: Have I presented COMPLETE agent responses (not summaries)?
  5. Review: Have I received user confirmation before next cycle?
  6. Are there more areas that need investigation?
  7. Should I continue or wait for user input?

Analysis Areas

Business Analysis

  • Extract business rules from codebase
  • Research domain best practices
  • Identify validation and workflow patterns
  • Document in: docs/domain/

Technical Analysis

  • Identify architectural patterns
  • Analyze code structure and design patterns
  • Review component relationships
  • Document in: docs/patterns/

Security Analysis

  • Identify security patterns and vulnerabilities
  • Analyze authentication and authorization approaches
  • Review data protection mechanisms
  • Document in: docs/patterns/ or docs/domain/

Performance Analysis

  • Analyze performance patterns and bottlenecks
  • Review optimization approaches
  • Identify resource management patterns
  • Document in: docs/patterns/

Integration Analysis

  • Analyze API design patterns
  • Review service communication patterns
  • Identify data exchange mechanisms
  • Document in: docs/interfaces/

Documentation Structure

All analysis findings go to appropriate categories:

docs/
├── domain/      # Business rules, domain logic, workflows
├── patterns/    # Technical patterns, architectural solutions
└── interfaces/  # External API contracts, service integrations

Documentation Decision Criteria

Include documentation in OUTPUT only when ALL criteria are met:

  1. Reusable - Pattern/interface/rule used in 2+ places OR clearly reusable
  2. Non-Obvious - Not standard practices (REST, MVC, CRUD)
  3. Not a Duplicate - Check existing docs first: grep -ri "keyword" docs/

What NOT to Document

  • ❌ Meta-documentation (SUMMARY.md, REPORT.md, ANALYSIS.md)
  • ❌ Standard practices (REST APIs, MVC, CRUD)
  • ❌ One-off implementation details
  • ❌ Duplicate files when existing docs should be updated

Agent Delegation for Discovery

When launching specialist agents for investigation:

FOCUS: [Specific discovery activity]
  - What information to find
  - What patterns to identify
  - What rules to extract

EXCLUDE: [Out of scope areas]
  - [Unrelated areas]: out of scope
  - Documentation: deferred to documentation phase

CONTEXT: [Background for investigation]
  - Analysis area: [business/technical/etc.]
  - Prior findings: [If any from previous cycles]

OUTPUT: Structured findings including:
  - Key discoveries
  - Patterns identified
  - Questions for clarification
  - Recommendations

SUCCESS: All findings documented with evidence

TERMINATION: Discovery complete OR blocked

Cycle Progress Tracking

Use TodoWrite to track cycles:

Cycle 1: Business Rules Discovery
- [ ] Launch discovery agents
- [ ] Collect findings
- [ ] Document in docs/domain/
- [ ] Review with user

Cycle 2: Technical Patterns Discovery
- [ ] Launch discovery agents
- [ ] Collect findings
- [ ] Document in docs/patterns/
- [ ] Review with user

Findings Presentation Format

After each discovery cycle:

🔍 Discovery Cycle [N] Complete

Area: [Analysis area]
Agents Launched: [N]

Key Findings:
1. [Finding with evidence]
2. [Finding with evidence]
3. [Finding with evidence]

Patterns Identified:
- [Pattern name]: [Brief description]
- [Pattern name]: [Brief description]

Documentation Created/Updated:
- docs/[category]/[file.md]

Questions for Clarification:
1. [Question about ambiguous finding]
2. [Question about conflicting information]

Should I continue to [next area] or investigate [finding] further?

Analysis Summary Format

At completion of all cycles:

📊 Analysis Complete

Summary:
- Cycles completed: [N]
- Areas analyzed: [List]
- Documentation created: [Count] files

Documentation Created:
- docs/domain/[file1.md] - [Brief description]
- docs/patterns/[file2.md] - [Brief description]
- docs/interfaces/[file3.md] - [Brief description]

Major Findings:
1. [Critical pattern/rule discovered]
2. [Important insight]
3. [Significant finding]

Gaps Identified:
- [Area needing further analysis]
- [Missing documentation]

Recommended Next Steps:
1. [Action item]
2. [Action item]

Output Format

When reporting analysis progress:

🔍 Analysis Progress

Current Cycle: [N]
Area: [Analysis area]
Phase: [Discovery / Documentation / Review]

Activities:
- [Activity 1]: [Status]
- [Activity 2]: [Status]

Findings So Far:
- [Key finding 1]
- [Key finding 2]

Next: [What's happening next]

Quick Reference

Cycle Pattern

Discovery → Documentation → Review → (repeat)

Parallel-First

Always launch multiple agents for investigation.

Document Appropriately

  • Business rules → docs/domain/
  • Technical patterns → docs/patterns/
  • External integrations → docs/interfaces/

User Confirmation Required

Obtain user confirmation before proceeding to next cycle.

Build on Prior Cycles

Each cycle accumulates context from previous findings.

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

27.95%
按下载量换算49

windsurf

24.56%
按下载量换算43

OpenCode

18.36%
按下载量换算32

Codex

14.43%
按下载量换算25

Gemini CLI

8.31%
按下载量换算15

trae

3.52%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills