Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计未展示

code-analyze代码分析

Agent Skill

code-analyze 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

318

周安装

13

GitHub Stars

公开资料未说明

下载量

102
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

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:code-analyze(代码分析)
来源仓库:https://github.com/giantcroissant-lunar/lunar-snake-hub
仓库路径:skills/code-analyze
安装命令:
npx skills add giantcroissant-lunar/lunar-snake-hub --skill "code-analyze"
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。

AgentSkills.tonpx skills
npx skills add giantcroissant-lunar/lunar-snake-hub --skill "code-analyze"

简介

code-analyze 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。
  • 发现并安装 AI 代理的技能。
  • 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

name
code-analyze
version
0.1.0
kind
cli
description
Run static analysis, security scans, and dependency checks on .NET code. Use when task involves code quality, security audits, or vulnerability detection.
inputs
analysis_type
[static, security, dependencies, all]
project_path
string
severity_filter
[error, warning, suggestion, all]
contracts
success
Analysis completes with findings report; exit code 0
failure
Non-zero exit code or tool execution errors

Code Analysis Skill (Entry Map)

Goal: Guide agent to the exact analysis procedure needed.

Quick Start (Pick One)

  • Run static code analysisreferences/static-analysis.md
  • Scan for security issuesreferences/security-scan.md
  • Check dependency vulnerabilitiesreferences/dependency-check.md

When to Use

  • Enforce code quality standards and best practices
  • Detect potential bugs and code smells
  • Identify security vulnerabilities in code
  • Check for vulnerable dependencies
  • Run automated code reviews

NOT for: building (dotnet-build), testing (dotnet-test), or formatting (code-format)

Inputs & Outputs

Inputs: analysis_type (static/security/dependencies/all), project_path (default: ./dotnet/PigeonPea.sln), severity_filter (error/warning/suggestion)

Outputs: analysis_report (findings with file/line), exit_code (0=clean, 1=issues), metrics (violations by severity)

Guardrails: Analyze only, never modify code, report all findings with context, fail on critical issues

Navigation

1. Static Code Analysisreferences/static-analysis.md

  • Roslyn analyzers, StyleCop, code quality rules, best practices

2. Security Scanningreferences/security-scan.md

  • Secret detection (gitleaks, detect-secrets), security analyzers, vulnerability patterns

3. Dependency Vulnerability Checkreferences/dependency-check.md

  • NuGet package vulnerabilities, outdated dependencies, CVE detection

Common Patterns

Quick Analysis (All Checks)

cd ./dotnet
dotnet build PigeonPea.sln /p:TreatWarningsAsErrors=true
dotnet list package --vulnerable

Static Analysis Only

cd ./dotnet
dotnet build PigeonPea.sln /p:RunAnalyzers=true /warnaserror

Security Scan (Pre-commit)

pre-commit run gitleaks --all-files
pre-commit run detect-secrets --all-files

Dependency Check

cd ./dotnet
dotnet list package --vulnerable --include-transitive
dotnet list package --outdated

Full Analysis Suite

# Run from repository root
.agent/skills/code-analyze/scripts/analyze.sh --all

Analysis with Specific Severity

cd ./dotnet
# Errors only
dotnet build PigeonPea.sln /p:TreatWarningsAsErrors=false

# Warnings as errors
dotnet build PigeonPea.sln /p:TreatWarningsAsErrors=true

Troubleshooting

No analyzers found: Verify Roslyn analyzers enabled. See references/static-analysis.md.

Too many warnings: Filter by severity or add suppressions. See references/static-analysis.md.

False positives: Use .editorconfig or suppressions. See references/static-analysis.md.

Secrets not detected: Check .gitleaksignore and .secrets.baseline. See references/security-scan.md.

Dependency scan fails: Network issues or package restore needed. See references/dependency-check.md.

Success Indicators

Static Analysis:

Build succeeded.
    0 Warning(s)
    0 Error(s)

Security Scan:

gitleaks................Passed
detect-secrets...........Passed

Dependency Check:

No vulnerable packages found.

Integration

Before commit: Run security scans (gitleaks, detect-secrets) After build: Run static analysis (Roslyn, StyleCop) Regular checks: Run dependency vulnerability checks

CI/CD Integration: Include all analysis in build pipeline, fail on critical issues

Related

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

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

windsurf

29.41%
按下载量换算30

OpenCode

23.35%
按下载量换算24

weavefox

18.09%
按下载量换算18

Codex

11.01%
按下载量换算11

github-copilot

7.54%
按下载量换算8

Claude Code

3.36%
按下载量换算3

安全审计

暂无安全审计结果可展示。

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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