做什么
根据Anthropic的官方最佳做法,包括500行规则和渐进披露模式,以自动激活系统创建和管理克洛德法典技能的全面指南.
技能库 智客分类:Agent 工作流 skill-developer
根据Anthropic的官方最佳做法,包括500行规则和渐进披露模式,以自动激活系统创建和管理克洛德法典技能的全面指南.
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。
根据Anthropic的官方最佳做法,包括500行规则和渐进披露模式,以自动激活系统创建和管理克洛德法典技能的全面指南.
这个技能
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:Skill Developer Guide、Purpose、When to Use This Skill、System Overview、Two-Hook Architecture、Configuration File。 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。
Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the 500-line rule and progressive disclosure pattern.
Skill Developer GuidePurposeWhen to Use This SkillSystem OverviewTwo-Hook ArchitectureConfiguration FileSkill Types1. Guardrail Skills2. Domain SkillsQuick Start: Creating a New SkillStep 1: Create Skill FileMy New Skill
来源分类:skills.sh agent-skill
nameskill-developerdescription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「skill-developer」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-890ac20ce6f6e4de-%E6%8A%80%E8%83%BD%E5%BC%80%E5%8F%91%E8%80%85.html 请存为 .cursor/skills/skill-developer/SKILL.md 或 .claude/skills/skill-developer/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/sickn33/agentic-awesome-skills' --list
npx skills add 'https://github.com/sickn33/agentic-awesome-skills' --skill 'skill-developer'
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。
Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the 500-line rule and progressive disclosure pattern.
Automatically activates when you mention:
1. UserPromptSubmit Hook (Proactive Suggestions)
.claude/hooks/skill-activation-prompt.ts2. Stop Hook - Error Handling Reminder (Gentle Reminders)
.claude/hooks/error-handling-reminder.tsPhilosophy Change (2025-10-27): We moved away from blocking PreToolUse for Sentry/error handling. Instead, use gentle post-response reminders that don't block workflow but maintain code quality awareness.
Location: .claude/skills/skill-rules.json
Defines:
Purpose: Enforce critical best practices that prevent errors
Characteristics:
"guardrail""block""critical" or "high"Examples:
database-verification - Verify table/column names before Prisma queriesfrontend-dev-guidelines - Enforce React/TypeScript patternsWhen to Use:
Purpose: Provide comprehensive guidance for specific areas
Characteristics:
"domain""suggest""high" or "medium"Examples:
backend-dev-guidelines - Node.js/Express/TypeScript patternsfrontend-dev-guidelines - React/TypeScript best practiceserror-tracking - Sentry integration guidanceWhen to Use:
Location: .claude/skills/{skill-name}/SKILL.md
Template:
---
name: my-new-skill
description: Brief description including keywords that trigger this skill. Mention topics, file types, and use cases. Be explicit about trigger terms.
---
# My New Skill
## Purpose
What this skill helps with
## When to Use
Specific scenarios and conditions
## Key Information
The actual guidance, documentation, patterns, examples
Best Practices:
See SKILL_RULES_REFERENCE.md for complete schema.
Basic Template:
{
"my-new-skill": {
"type": "domain",
"enforcement": "suggest",
"priority": "medium",
"promptTriggers": {
"keywords": ["keyword1", "keyword2"],
"intentPatterns": ["(create|add).*?something"]
}
}
}
Test UserPromptSubmit:
echo '{"session_id":"test","prompt":"your test prompt"}' | \
npx tsx .claude/hooks/skill-activation-prompt.ts
Test PreToolUse:
cat <<'EOF' | npx tsx .claude/hooks/skill-verification-guard.ts
{"session_id":"test","tool_name":"Edit","tool_input":{"file_path":"test.ts"}}
EOF
Based on testing:
✅ Keep SKILL.md under 500 lines ✅ Use progressive disclosure with reference files ✅ Add table of contents to reference files > 100 lines ✅ Write detailed description with trigger keywords ✅ Test with 3+ real scenarios before documenting ✅ Iterate based on actual usage
Example: Database column name verification
Example: Frontend development guidelines
Rarely used - most skills are either BLOCK or SUGGEST.
Purpose: Don't nag repeatedly in same session
How it works:
State File: .claude/hooks/state/skills-used-{session_id}.json
Purpose: Permanent skip for verified files
Marker: // @skip-validation
Usage:
// @skip-validation
import { PrismaService } from './prisma';
// This file has been manually verified
NOTE: Use sparingly - defeats the purpose if overused
Purpose: Emergency disable, temporary override
Global disable:
export SKIP_SKILL_GUARDRAILS=true # Disables ALL PreToolUse blocks
Skill-specific:
export SKIP_DB_VERIFICATION=true
export SKIP_ERROR_REMINDER=true
When creating a new skill, verify:
.claude/skills/{name}/SKILL.mdskill-rules.jsonjq . skill-rules.jsonFor detailed information on specific topics, see:
Complete guide to all trigger types:
Complete skill-rules.json schema:
Deep dive into hook internals:
Comprehensive debugging guide:
Ready-to-use pattern collection:
Future enhancements and ideas:
.claude/skills/{name}/SKILL.md with frontmatter.claude/skills/skill-rules.jsonnpx tsx commandsSee TRIGGER_TYPES.md for complete details.
// @skip-validation (permanent skip)SKIP_SKILL_GUARDRAILS (emergency disable)✅ 500-line rule: Keep SKILL.md under 500 lines ✅ Progressive disclosure: Use reference files for details ✅ Table of contents: Add to reference files > 100 lines ✅ One level deep: Don't nest references deeply ✅ Rich descriptions: Include all trigger keywords (max 1024 chars) ✅ Test first: Build 3+ evaluations before extensive documentation ✅ Gerund naming: Prefer verb + -ing (e.g., "processing-pdfs")
Test hooks manually:
# UserPromptSubmit
echo '{"prompt":"test"}' | npx tsx .claude/hooks/skill-activation-prompt.ts
# PreToolUse
cat <<'EOF' | npx tsx .claude/hooks/skill-verification-guard.ts
{"tool_name":"Edit","tool_input":{"file_path":"test.ts"}}
EOF
See TROUBLESHOOTING.md for complete debugging guide.
Configuration:
.claude/skills/skill-rules.json - Master configuration.claude/hooks/state/ - Session tracking.claude/settings.json - Hook registrationHooks:
.claude/hooks/skill-activation-prompt.ts - UserPromptSubmit.claude/hooks/error-handling-reminder.ts - Stop event (gentle reminders)All Skills:
.claude/skills/*/SKILL.md - Skill content filesSkill Status: COMPLETE - Restructured following Anthropic best practices ✅ Line Count: < 500 (following 500-line rule) ✅ Progressive Disclosure: Reference files for detailed information ✅
Next: Create more skills, refine patterns based on usage
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…