Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问clear审计通过

quickquick 搜索

Agent Skill

quick 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

774

周安装

31

GitHub Stars

537

下载量

250
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:quick(quick 搜索)
来源仓库:https://github.com/fradser/dotclaude
仓库路径:skills/quick
安装命令:
npx skills add https://github.com/fradser/dotclaude --skill quick
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/fradser/dotclaude --skill quick

简介

quick 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。
  • 适用于研究检索类任务,支持多宿主环境集成。
  • 可通过 npx skills add 命令从 GitHub 仓库安装。

SKILL.md

Quick Code Review

Context

  • Current branch:!git branch --show-current
  • Git status:!git status --porcelain
  • Base branch: [detect dynamically - check for develop or main]
  • Recent commits:!git log --oneline -10
  • Changed files:!git diff --name-only HEAD~5..HEAD
  • Test framework: [detect dynamically based on project files]

Phase 1: Determine Review Scope

Goal: Identify what to review based on current state.

Actions:

  1. Check review scope in this order:

- Uncommitted changes: If git status shows modifications, review those files via git diff - Session changes: If files were modified during this conversation, review those - User argument: If $ARGUMENTS specifies files/directories, review those - No scope: If none of the above, use AskUserQuestion tool to ask user to specify files/directories to review

  1. Record the determined scope for Phase 2.

Phase 2: Initial Assessment

Goal: Scope the review and determine which specialized agents are required.

Actions:

  1. Explore changed code context using the Explore agent:

- Launch subagent_type="Explore" with thoroughness: "quick" - Let the agent autonomously discover related code and dependencies

  1. Run an initial assessment with @tech-lead-reviewer — architectural impact assessment — to gauge architectural, security, and UX risk.
  2. Evaluate whether a deeper review is needed based on the tech-lead assessment.
  3. Identify which specialized agents to involve (minimizing turnaround time).

Phase 3: Targeted Review

Goal: Gather targeted feedback from relevant specialized reviewers.

Actions:

  1. Launch only the necessary specialized reviews via the Task tool:

- @code-reviewer — logic correctness, tests, error handling. - @security-reviewer — authentication, data protection, validation. - @performance-reviewer — performance bottlenecks and resource usage (if performance-sensitive). - @test-coverage-reviewer — test coverage and quality (if tests are modified or missing). - @ux-reviewer — usability and accessibility (skip if purely backend/CLI).

  1. Collect outcomes from each agent.
  2. Resolve conflicting recommendations between reviewers.

Phase 4: Consolidation & Reporting

Goal: Present findings and optionally implement fixes.

Actions:

  1. Organize findings using the priority/confidence matrix:

- Priority: Critical → High → Medium → Low - Confidence: High → Medium → Low

  1. Present a concise summary to the user.
  2. Ask whether the user wants fixes implemented.
  3. If confirmed:

- Apply requested changes. - Refactor with @code-simplifier — code simplification and optimization. - Run tests to validate fixes. - Stage commits following Git commit conventions (see ${CLAUDE_PLUGIN_ROOT}/skills/references/git-commit-conventions.md).

  1. Report outcomes and confirm review completion.

IMPORTANT: You MUST use the Task tool to complete ALL tasks.

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

30.34%
按下载量换算76

Gemini CLI

21.86%
按下载量换算55

windsurf

15.59%
按下载量换算39

Antigravity

12.99%
按下载量换算32

Codex

7.92%
按下载量换算20

OpenCode

3.32%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/fradser/dotclaude --skill quick;npx skills add fradser/dotclaude --skill "quick" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。

来源信息

继续浏览同类 Skills