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

analyze分析

Agent Skill

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

192

周安装

8

GitHub Stars

38

下载量

64
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:analyze(分析)
来源仓库:https://github.com/aviflombaum/claude-code-in-avinyc
仓库路径:skills/analyze
安装命令:
npx skills add https://github.com/aviflombaum/claude-code-in-avinyc --skill 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。

skills.shnpx skills
npx skills add https://github.com/aviflombaum/claude-code-in-avinyc --skill analyze

简介

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。

  • 它将开发交互转化为持久学习系统,识别委托机会与自动化候选点。
  • 通过分析框架评估重复任务、领域操作与并行工作流,提升效率与可扩展性。
  • 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。
  • analyze 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Compound Engineering Analyzer

Transform development interactions into permanent learning systems that create exponential value over time. Identify how today's work can become tomorrow's accelerator.

Core Analysis Framework

1. DELEGATION OPPORTUNITIES

Identify subtasks where specialized agents could provide superior efficiency:

  • Repetitive analysis or review tasks that follow consistent patterns
  • Domain-specific operations requiring deep expertise
  • Parallel workstreams that could be handled independently
  • Tasks with clear inputs/outputs suitable for agent delegation

2. AUTOMATION CANDIDATES

Spot recurring manual processes ripe for systematic automation:

  • Multi-step workflows that appear repeatedly
  • Manual checks that could become automated validations
  • Data transformations or migrations following patterns
  • Testing or verification sequences that could be scripted

3. SYSTEMATIZATION TARGETS

Find knowledge that must be captured for compound benefits:

  • Architectural decisions and their rationale
  • Problem-solving patterns that emerged during work
  • Configuration standards or conventions discovered
  • Error patterns and their prevention strategies

4. LEARNING EXTRACTION

Highlight insights preventing future issues or accelerating similar work:

  • Root cause analyses that reveal systemic issues
  • Performance optimizations discovered through experimentation
  • Integration gotchas and their workarounds
  • Best practices validated through implementation

5. PARALLEL PROCESSING

Suggest independent workstreams for simultaneous execution:

  • Decoupled components that could be developed in parallel
  • Independent testing or validation streams
  • Documentation tasks that could run alongside development
  • Research activities that don't block primary work

Output Format

COMPOUND ENGINEERING OPPORTUNITIES:

SUGGESTION: [Specific, actionable recommendation with clear scope] COMPOUND BENEFIT: [Long-term compounding value, quantified where possible] IMPLEMENTATION: [Approach, complexity (Simple/Moderate/Complex), timing] CONFIDENCE: [High/Medium/Low] - [Reasoning based on observed patterns]

Evaluation Criteria

  • Frequency: How often will this benefit be realized?
  • Impact: What's the magnitude of improvement each time?
  • Effort: Implementation cost versus ongoing benefit?
  • Risk: What could prevent successful implementation?
  • Dependencies: What prerequisites or resources are needed?

Core Principles

  • Every bug becomes a prevention system through automated checks
  • Every manual process becomes an automation candidate
  • Every architectural decision becomes documented knowledge
  • Every repetitive task becomes a delegation opportunity
  • Every solution becomes a template for similar problems

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

34.76%
按下载量换算22

Claude

29.32%
按下载量换算19

Cursor

20.67%
按下载量换算13

Gemini CLI

10.13%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

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