代理标识开发_agent-identifier
以下为本文档的中文说明该技能为Claude Code插件中的代理开发提供全面指导涵盖代理结构设计、触发条件配置、系统提示词编写等关键方面。主要功能是帮助开发者创建自主化的子代理使其能够独立处理复杂的多步骤任务。使用场景包括当用户需要创建代理、“添加代理”、编写子代理时提供模板和最佳实践指导如何设置代理的触发条件、工具权限和运行模型以及如何设计有效的系统提示词来描述代理行为。核心原则包括代理Agent用于自主工作命令Command用于用户发起的操作——两者有明确的职责区分Markdown文件格式配合YAML前置元数据定义代理结构通过描述字段中的示例来定义触发条件系统提示词决定代理的行为模式和边界。该技能还涵盖模型选择、颜色定制和工具配置等内容帮助开发者构建功能强大、行为可控的自主代理。Agent Development for Claude Code PluginsOverviewAgents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.Key concepts:Agents are FOR autonomous work, commands are FOR user-initiated actionsMarkdown file format with YAML frontmatterTriggering via description field with examplesSystem prompt defines agent behaviorModel and color customizationAgent File StructureComplete Format--- name: agent-identifier description: Use this agent when [triggering conditions]. Examples: example Context: [Situation description] user: [User request] assistant: [How assistant should respond and use this agent] commentary [Why this agent should be triggered] /commentary /example example [Additional example...] /example model: inherit color: blue tools: [Read, Write, Grep] --- You are [agent role description]... **Your Core Responsibilities:** 1. [Responsibility 1] 2. [Responsibility 2] **Analysis Process:** [Step-by-step workflow] **Output Format:** [What to return]Frontmatter Fieldsname (required)Agent identifier used for namespacing and invocation.Format:lowercase, numbers, hyphens onlyLength:3-50 charactersPattern:Must start and end with alphanumericGood examples:code-reviewertest-generatorapi-docs-writersecurity-analyzerBad examples:helper(too generic)-agent-(starts/ends with hyphen)my_agent(underscores not allowed)ag(too short, 3 chars)description (required)Defines when Claude should trigger this agent.This is the most critical field.Must include:Triggering conditions (“Use this agent when…”)Multipleexampleblocks showing usageContext, user request, and assistant response in each examplecommentaryexplaining why agent triggersFormat:Use this agent when [conditions]. Examples: example Context: [Scenario description] user: [What user says] assistant: [How Claude should respond] commentary [Why this agent is appropriate] /commentary /example [More examples...]Best practices:Include 2-4 concrete examplesShow proactive and reactive triggeringCover different phrasings of same intentExplain reasoning in commentaryBe specific about when NOT to use the agentmodel (required)Which model the agent should use.Options:inherit- Use same model as parent (recommended)sonnet- Claude Sonnet (balanced)opus- Claude Opus (most capable, expensive)haiku- Claude Haiku (fast, cheap)Recommendation:Useinheritunless agent needs specific model capabilities.color (required)Visual identifier for agent in UI.Options:blue,cyan,green,yellow,magenta,redGuidelines:Choose distinct colors for different agents in same pluginUse consistent colors for similar agent typesBlue/cyan: Analysis, reviewGreen: Success-oriented tasksYellow: Caution, validationRed: Critical, securityMagenta: Creative, generationtools (optional)Restrict agent to specific tools.Format:Array of tool namestools:[Read,Write,Grep,Bash]Default:If omitted, agent has access to all toolsBest practice:Limit tools to minimum needed (principle of least privilege)Common tool sets:Read-only analysis:[Read, Grep, Glob]Code generation:[Read, Write, Grep]Testing:[Read, Bash, Grep]Full access: Omit field or use[*]System Prompt DesignThe markdown body becomes the agent’s system prompt. Write in second person, addressing the agent directly.StructureStandard template:You are [role] specializing in [domain]. **Your Core Responsibilities:** 1. [Primary responsibility] 2. [Secondary responsibility] 3. [Additional responsibilities...] **Analysis Process:** 1. [S tep one] 2. [Step two] 3. [Step three] [...] **Quality Standards:** - [Standard 1] - [Standard 2] **Output Format:** Provide results in this format: - [What to include] - [How to structure] **Edge Cases:** Handle these situations: - [Edge case 1]: [How to handle] - [Edge case 2]: [How to handle]Best Practices✅DO:Write in second person (“You are…”, “You will…”)Be specific about responsibilitiesProvide step-by-step processDefine output formatInclude quality standardsAddress edge casesKeep under 10,000 characters❌DON’T:Write in first person (“I am…”, “I will…”)Be vague or genericOmit process stepsLeave output format undefinedSkip quality guidanceIgnore error casesCreating AgentsMethod 1: AI-Assisted GenerationUse this prompt pattern (extracted from Claude Code):Create an agent configuration based on this request: [YOUR DESCRIPTION] Requirements: 1. Extract core intent and responsibilities 2. Design expert persona for the domain 3. Create comprehensive system prompt with: - Clear behavioral boundaries - Specific methodologies - Edge case handling - Output format 4. Create identifier (lowercase, hyphens, 3-50 chars) 5. Write description with triggering conditions 6. Include 2-3 example blocks showing when to use Return JSON with: { identifier: agent-name, whenToUse: Use this agent when... Examples: example.../example, systemPrompt: You are... }Then convert to agent file format with frontmatter.Seeexamples/agent-creation-prompt.mdfor complete template.Method 2: Manual CreationChoose agent identifier (3-50 chars, lowercase, hyphens)Write description with examplesSelect model (usuallyinherit)Choose color for visual identificationDefine tools (if restricting access)Write system prompt with structure aboveSave asagents/agent-name.mdValidation RulesIdentifier Validation✅ Valid: code-reviewer, test-gen, api-analyzer-v2 ❌ Invalid: ag (too short), -start (starts with hyphen), my_agent (underscore)Rules:3-50 charactersLowercase letters, numbers, hyphens onlyMust start and end with alphanumericNo underscores, spaces, or special charactersDescription ValidationLength:10-5,000 charactersMust include:Triggering conditions and examplesBest:200-1,000 characters with 2-4 examplesSystem Prompt ValidationLength:20-10,000 charactersBest:500-3,000 charactersStructure:Clear responsibilities, process, output formatAgent OrganizationPlugin Agents Directoryplugin-name/ └── agents/ ├── analyzer.md ├── reviewer.md └── generator.mdAll.mdfiles inagents/are auto-discovered.NamespacingAgents are namespaced automatically:Single plugin:agent-nameWith subdirectories:plugin:subdir:agent-nameTesting AgentsTest TriggeringCreate test scenarios to verify agent triggers correctly:Write agent with specific triggering examplesUse similar phrasing to examples in testCheck Claude loads the agentVerify agent provides expected functionalityTest System PromptEnsure system prompt is complete:Give agent typical taskCheck it follows process stepsVerify output format is correctTest edge cases mentioned in promptConfirm quality standards are metQuick ReferenceMinimal Agent--- name: simple-agent description: Use this agent when... Examples: example.../example model: inherit color: blue --- You are an agent that [does X]. Process: 1. [Step 1] 2. [Step 2] Output: [What to provide]Frontmatter Fields SummaryFieldRequiredFormatExamplenameYeslowercase-hyphenscode-reviewerdescriptionYesText examplesUse when… …modelYesinherit/sonnet/opus/haikuinheritcolorYesColor namebluetoolsNoArray of toolnames[“Read”, “Grep”]Best PracticesDO:✅ Include 2-4 concrete examples in description✅ Write specific triggering conditions✅ Useinheritfor model unless specific need✅ Choose appropriate tools (least privilege)✅ Write clear, structured system prompts✅ Test agent triggering thoroughlyDON’T:❌ Use generic descriptions without examples❌ Omit triggering conditions❌ Give all agents same color❌ Grant unnecessary tool access❌ Write vague system prompts❌ Skip testingAdditional ResourcesReference FilesFor detailed guidance, consult:references/system-prompt-design.md- Complete system prompt patternsreferences/triggering-examples.md- Example formats and best practicesreferences/agent-creation-system-prompt.md- The exact prompt from Claude CodeExample FilesWorking examples inexamples/:agent-creation-prompt.md- AI-assisted agent generation templatecomplete-agent-examples.md- Full agent examples for different use casesUtility ScriptsDevelopment tools inscripts/:validate-agent.sh- Validate agent file structuretest-agent-trigger.sh- Test if agent triggers correctlyImplementation WorkflowTo create an agent for a plugin:Define agent purpose and triggering conditionsChoose creation method (AI-assisted or manual)Createagents/agent-name.mdfileWrite frontmatter with all required fieldsWrite system prompt following best practicesInclude 2-4 triggering examples in descriptionValidate withscripts/validate-agent.shTest triggering with real scenariosDocument agent in plugin READMEFocus on clear triggering conditions and comprehensive system prompts for autonomous operation.3c:[“,,,L3f”,null,{“content”:“$40”,“frontMatter”:{“name”:“Agent Development”,“description”:“This skill should be used when the user asks to \“create an agent\”, \“add an agent\”, \“write a subagent\”, \“agent frontmatter\”, \“when to use description\”, \“agent examples\”, \“agent tools\”, \“agent colors\”, \“autonomous agent\”, or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.”,“version”:“0.1.0”}}]3d:[“KaTeX parse error: Expected }, got EOF at end of input: …,children:[[”,“div”,null,{“className”:“flex items-center justify-between border-b border-border bg-muted/30 px-4 py-2.5”,“children”:[[“KaTeX parse error: Expected }, got EOF at end of input: …,children:[”,“span”,null,{“className”:“truncate text-xs font-medium text-muted-foreground”,“children”:“同仓库更多 Skills”}]}],[“KaTeX parse error: Expected EOF, got } at position 88: …ldren:同仓库}]]}̲],[”,“div”,null,{“className”:“p-4 sm:p-5”,“children”:[[“,h2,null,id:related−skills−heading,className:text−2xlfont−semiboldtracking−normaltext−foreground,children:同仓库更多Skills],[,h2,null,{id:related-skills-heading,className:text-2xl font-semibold tracking-normal text-foreground,children:同仓库更多 Skills}],[,h2,null,id:related−skills−heading,className:text−2xlfont−semiboldtracking−normaltext−foreground,children:同仓库更多Skills],[”,“div”,null,{“className”:“mt-4 grid gap-3 sm:grid-cols-2”,“children”:[“L41,L41,L41,L42”,“L43,L43,L43,L44”,“L45,L45,L45,L46”]}]]}]]}]47:I[206516,[“/_next/static/chunks/051aanbhrv4br.js”,“/_next/static/chunks/0mizr60h7ayzt.js”,“/_next/static/chunks/0v9lm1dmbdoo-.js”,“/_next/static/chunks/0rxr1j1j3j-.r.js”,“/_next/static/chunks/02ftybezfvqjd.js”,“/_next/static/chunks/0.v9ksvnnj8ia.js”,“/_next/static/chunks/0bn6id96nx3k.js,“/_next/static/chunks/13ybnhn37c.tc.js”,“/_next/static/chunks/0_fnrdtruz8uf.js”,“/_next/static/chunks/0r6l15utt1mwb.js”,“/_next/static/chunks/0dm9a5into854.js”,/_next/static/chunks/07k6hqoibtcn.js”,“/next/static/chunks/0b4cao.4y…j.js”,“/_next/static/chunks/02i-n28z7kjd0.js”],“default”]

相关新闻

AUX传感器控制器事件管理与TDC寄存器配置详解

AUX传感器控制器事件管理与TDC寄存器配置详解

1. AUX传感器控制器:嵌入式系统的“神经中枢” 在物联网和可穿戴设备这类对功耗和实时性都极为敏感的应用场景里,主MCU(微控制器单元)常常需要处理大量琐碎但频繁的传感器任务,比如周期性读取温度、检测按键按下、或者…

2026/11/21 15:30:03 阅读更多 →
Windows网络调试终极指南:5分钟掌握socat-windows端口转发神器

Windows网络调试终极指南:5分钟掌握socat-windows端口转发神器

Windows网络调试终极指南:5分钟掌握socat-windows端口转发神器 【免费下载链接】socat-windows unofficial windows build of socat http://www.dest-unreach.org/socat/ 项目地址: https://gitcode.com/gh_mirrors/so/socat-windows 在Windows平台上进行网络…

2026/11/19 15:24:47 阅读更多 →
GPU加速AI:从CUDA架构到深度学习性能优化

GPU加速AI:从CUDA架构到深度学习性能优化

1. GPU算力与人工智能的共生关系 2006年NVIDIA推出CUDA架构时,可能没想到这个为图形处理设计的并行计算架构会成为AI革命的基石。如今在深度学习训练中,一块高端GPU的运算速度可达CPU的50-100倍,这种数量级的性能差异彻底改变了人工智能的发展…

2026/11/14 14:56:00 阅读更多 →

最新新闻

Electron桌面应用开发实战:从环境搭建到打包发布全流程

Electron桌面应用开发实战:从环境搭建到打包发布全流程

做前端这些年,我大部分时间都在跟浏览器标签页打交道,直到第一次把桌面应用跑起来,才发现原来自己一直被限制在地址栏和刷新按钮围起来的框框里。Electron这个词,最开始是在某段时间频繁出现在同事的讨论里,一个用HTML…

2026/11/21 23:27:35 阅读更多 →
滑盖智能锁T109深度解析:结构原理、安装调试与故障排查

滑盖智能锁T109深度解析:结构原理、安装调试与故障排查

简介:亚太天能T109滑盖智能锁产品说明书是一份PDF格式的官方技术文档,主要面向智能锁安装人员、终端用户及售后维护者,帮助快速掌握产品安装、配置与常见故障处理。全包仅1个PDF文件,大小4.37MB,内容结构清晰&#xff…

2026/11/21 23:27:35 阅读更多 →
PMSM弱磁控制原理与Simulink建模:高速AGV驱动系统设计指南

PMSM弱磁控制原理与Simulink建模:高速AGV驱动系统设计指南

上个月我在调试一台高速AGV的驱动系统,整车要求空载跑到8m/s,电机转速已经拉到额定点,驱动器的输出电压也顶到了母线电压极限附近。再往上踩速度指令,转速纹丝不动,三相电流反而开始震荡。那会儿我的第一反应就是&…

2026/11/21 23:27:35 阅读更多 →
C++核心知识点:从内存管理到STL的实战指南

C++核心知识点:从内存管理到STL的实战指南

C 这门语言我前前后后折腾了十几年,用它写过嵌入式驱动、做过游戏服务端,也搭过基础组件库。每次看到新人一头扎进"C 核心知识点"这个搜索词,我其实挺感慨的——这门语言的难点从来不是语法多,而是知识点之间的耦合太深…

2026/11/21 23:27:35 阅读更多 →
T109滑盖智能锁怎么装?安装调试与故障排查全攻略

T109滑盖智能锁怎么装?安装调试与故障排查全攻略

简介:亚太天能T109滑盖智能锁产品说明书以PDF格式发布,适合智能锁用户、安装人员与售后维修人员阅读。内容围绕T109系列指纹密码刷卡锁展开,先介绍前面板、后面板、锁体、机械钥匙、电池盒盖等部件名称与功能,再给出完整安装步骤&…

2026/11/21 23:27:36 阅读更多 →
LLM知识降熵:从信息垄断到理解权下放

LLM知识降熵:从信息垄断到理解权下放

你有没有过这种经历:翻开源码注释、论文摘要或者一份专业报告,每个字都认识,连在一起却像天书。想找人聊聊,身边要么没人懂,要么懂的懒得跟你解释。后来我试着把同一段内容丢给一个大语言模型,几秒钟之后&a…

2026/11/21 23:27:37 阅读更多 →

日新闻

周新闻

月新闻