跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 review-claudemd

Review Claudemd

审查最近的对话,以寻找对 CLAUDE.md 文件的改进.

238 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

审查最近的对话,以寻找对 CLAUDE.md 文件的改进.

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Review CLAUDE.md from conversation history、Step 1: Find conversation history、Find the project folder (replace / with -)、Step 2: Extract recent conversations、Step 3: Spin up subagents、Step 4: Aggregate findings。 其中含规范建议的小节:分步指令。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Review recent conversations to find improvements for CLAUDE.md files.

Review CLAUDE.md from conversation historyStep 1: Find conversation historyFind the project folder (replace / with -)Step 2: Extract recent conversationsStep 3: Spin up subagentsStep 4: Aggregate findings

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
review-claudemd
description
Review recent conversations to find improvements for CLAUDE.md files.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「review-claudemd」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-ddaf25dca1e6c0ff-%E5%AE%A1%E6%9F%A5%E5%85%8B%E6%B4%9B%E5%BE%B7%E5%A7%86%E5%BE%B7.html
请存为 .cursor/skills/review-claudemd/SKILL.md 或 .claude/skills/review-claudemd/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/ykdojo/claude-code-tips' --list

npx skills add 'https://github.com/ykdojo/claude-code-tips' --skill 'review-claudemd'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: review-claudemd description: Review recent conversations to find improvements for CLAUDE.md files.

Review CLAUDE.md from conversation history

Analyze recent conversations to improve both global (~/.claude/CLAUDE.md) and local (project) CLAUDE.md files.

Step 1: Find conversation history

The project's conversation history is in ~/.claude/projects/. The folder name is the project path with slashes replaced by dashes.

# Find the project folder (replace / with -)
PROJECT_PATH=$(pwd | sed 's|/|-|g' | sed 's|^-||')
CONVO_DIR=~/.claude/projects/-${PROJECT_PATH}
ls -lt "$CONVO_DIR"/*.jsonl | head -20

Step 2: Extract recent conversations

Extract the 15-20 most recent conversations (excluding the current one) to a temp directory:

SCRATCH=/tmp/claudemd-review-$(date +%s)
mkdir -p "$SCRATCH"

for f in $(ls -t "$CONVO_DIR"/*.jsonl | head -20); do
  basename=$(basename "$f" .jsonl)
  # Skip current conversation if known
  cat "$f" | jq -r '
    if .type == "user" then
      "USER: " + (.message.content // "")
    elif .type == "assistant" then
      "ASSISTANT: " + ((.message.content // []) | map(select(.type == "text") | .text) | join("\n"))
    else
      empty
    end
  ' 2>/dev/null | grep -v "^ASSISTANT: $" > "$SCRATCH/${basename}.txt"
done

ls -lhS "$SCRATCH"

Step 3: Spin up subagents

Launch parallel subagents to analyze conversations. Each agent should read:

  • Global CLAUDE.md: ~/.claude/CLAUDE.md
  • Local CLAUDE.md: ./CLAUDE.md (if exists)
  • Batch of conversation files

Give each agent this prompt template:

Read:
1. Global CLAUDE.md: ~/.claude/CLAUDE.md
2. Local CLAUDE.md: [project]/CLAUDE.md
3. Conversations: [list of files]

Analyze the conversations against BOTH CLAUDE.md files. Find:
1. Instructions that exist but were violated (need reinforcement or rewording)
2. Patterns that should be added to LOCAL CLAUDE.md (project-specific)
3. Patterns that should be added to GLOBAL CLAUDE.md (applies everywhere)
4. Anything in either file that seems outdated or unnecessary

Be specific. Output bullet points only.

Batch conversations by size:

  • Large (>100KB): 1-2 per agent
  • Medium (10-100KB): 3-5 per agent
  • Small (<10KB): 5-10 per agent

Step 4: Aggregate findings

Combine results from all agents into a summary with these sections:

  1. Instructions violated - existing rules that weren't followed (need stronger wording)
  2. Suggested additions - LOCAL - project-specific patterns
  3. Suggested additions - GLOBAL - patterns that apply everywhere
  4. Potentially outdated - items that may no longer be relevant

Present as tables or bullet points. Ask user if they want edits drafted.

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…