做什么
审查最近的对话,以寻找对 CLAUDE.md 文件的改进.
技能库 智客分类:Agent 工作流 review-claudemd
审查最近的对话,以寻找对 CLAUDE.md 文件的改进.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
审查最近的对话,以寻找对 CLAUDE.md 文件的改进.
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。
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: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。
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
namereview-claudemddescription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 ↗
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。
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。
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。
Analyze recent conversations to improve both global (~/.claude/CLAUDE.md) and local (project) CLAUDE.md files.
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 "$CONVO_DIR"/*.jsonl | head -20
Extract the 15-20 most recent conversations (excluding the current one) to a temp directory:
SCRATCH=/tmp/claudemd-review-$(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"
Launch parallel subagents to analyze conversations. Each agent should read:
~/.claude/CLAUDE.md./CLAUDE.md (if exists)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:
Combine results from all agents into a summary with these sections:
Present as tables or bullet points. Ask user if they want edits drafted.
Agent 工作流
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
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
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
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…