Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问许可证需确认审计异常

claude-code-analyzerClaude 代码分析器

Agent Skill

claude-code-analyzer 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

396

周安装

17

GitHub Stars

9

下载量

139
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:claude-code-analyzer(Claude 代码分析器)
来源仓库:https://github.com/kriscard/kriscard-claude-plugins
仓库路径:skills/claude-code-analyzer
安装命令:
npx skills add https://github.com/kriscard/kriscard-claude-plugins --skill claude-code-analyzer
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/kriscard/kriscard-claude-plugins --skill claude-code-analyzer

简介

claude-code-analyzer 用于查找、检索和筛选相关信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。
  • 使用时需要结合来源仓库、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或文件读写。
  • 涉及命令执行时,应在提示词中明确确认步骤和失败处理方式。

SKILL.md

Claude Code Analyzer

Optimize your Claude Code workflow by analyzing usage patterns, detecting project structure, and discovering community resources.

Capabilities

FeatureScriptPurpose
Usage Analysisanalyze.shExtract tool/model usage from history
Project Detectionanalyze-claude-md.shDetect stack, suggest CLAUDE.md improvements
Feature Referencefetch-features.shList Claude Code capabilities
GitHub Discoverygithub-discovery.shFind community skills/agents/commands

Workflow

1. Analyze Current Project

Run project structure detection:

bash scripts/analyze-claude-md.sh

If the script is missing or fails, fall back to manual analysis:

  • Read the project's CLAUDE.md (or note its absence)
  • Check package.json for framework detection
  • Scan directory structure for conventions
  • Provide CLAUDE.md recommendations based on findings

Identifies:

  • Missing CLAUDE.md or incomplete sections
  • Undocumented commands or patterns
  • Framework-specific suggestions

2. Review Usage Patterns

Analyze Claude Code history for current project:

bash scripts/analyze.sh --current-project

If the script is unavailable, suggest the user check:

  • Settings > auto-allowed tools (are frequently-used tools approved?)
  • Model usage (cost awareness)
  • Common workflow patterns

Identifies:

  • Most-used tools (optimize auto-allow)
  • Model distribution (cost awareness)
  • Active projects

3. Discover Community Resources

Search GitHub for relevant resources:

bash scripts/github-discovery.sh all [query]
bash scripts/github-discovery.sh skills react
bash scripts/github-discovery.sh agents typescript

If the script is unavailable, search GitHub directly:

gh search repos "claude-code plugin" --sort stars --limit 10
gh search repos "claude-code skill" --sort stars --limit 10

4. Generate Recommendations

Based on analysis, provide actionable suggestions:

  • CLAUDE.md improvements (load references/best-practices.md if available)
  • Settings optimizations
  • New skills or agents to create
  • Community resources to adopt

Recommendation Patterns

No CLAUDE.md Detected

  1. Run stack detection (script or manual)
  2. Generate CLAUDE.md template from detected info
  3. Include commands from package.json scripts
  4. Add architecture notes based on directory structure

Underutilized Features

If analysis shows limited tool variety:

  • Suggest auto-allowing frequently-used tools
  • Recommend Explore agents for searches
  • Propose skills for repeated workflows

High Tool Usage Without Auto-Allow

If frequently used tools aren't auto-allowed:

  • Suggest adding to autoAllowedTools in settings
  • Reference trust levels in best-practices.md

Dependencies

  • jq - JSON processing (required for analyze.sh)
  • gh - GitHub CLI (optional, enhances github-discovery.sh)

Install: brew install jq gh

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

32.94%
按下载量换算46

Claude

28.23%
按下载量换算39

Cursor

19.34%
按下载量换算27

Gemini CLI

10.33%
按下载量换算14

安全审计

Gen Agent Trust Hub

未通过

Socket

可疑

Snyk

可疑

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