菜单
设计并构建各类 AI 智能体/助手。适用于用户： (1) 询问“创建 agent / 助手 / 智能体系统” (2) 想理解 agent 架构、agentic 模式或自治式 AI (3) 需要能力设计、子代理、规划或 skills 机制建议 (4) 询问 Claude Code、Cursor 等智能体内部实现 (5) 想为业务/研究/创作/运营等场景构建 agent 关键词：agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | agent-builder |
| description | 设计并构建各类 AI 智能体/助手。适用于用户： (1) 询问“创建 agent / 助手 / 智能体系统” (2) 想理解 agent 架构、agentic 模式或自治式 AI (3) 需要能力设计、子代理、规划或 skills 机制建议 (4) 询问 Claude Code、Cursor 等智能体内部实现 (5) 想为业务/研究/创作/运营等场景构建 agent 关键词：agent, assistant, autonomous, workflow, tool use, multi-step, orchestration |
Build AI agents for any domain - customer service, research, operations, creative work, or specialized business processes.
The model already knows how to be an agent. Your job is to get out of the way.
An agent is not complex engineering. It's a simple loop that invites the model to act:
LOOP:
Model sees: context + available capabilities
Model decides: act or respond
If act: execute capability, add result, continue
If respond: return to user
That's it. The magic isn't in the code - it's in the model. Your code just provides the opportunity.
Atomic actions the agent can perform: search, read, create, send, query, modify.
Design principle: Start with 3-5 capabilities. Add more only when the agent consistently fails because a capability is missing.
Domain expertise injected on-demand: policies, workflows, best practices, schemas.
Design principle: Make knowledge available, not mandatory. Load it when relevant, not upfront.
The conversation history - the thread connecting actions into coherent behavior.
Design principle: Context is precious. Isolate noisy subtasks. Truncate verbose outputs. Protect clarity.
Before building, understand:
CRITICAL: Trust the model. Don't over-engineer. Don't pre-specify workflows. Give it capabilities and let it reason.
Start simple. Add complexity only when real usage reveals the need:
| Level | What to add | When to add it |
|---|---|---|
| Basic | 3-5 capabilities | Always start here |
| Planning | Progress tracking | Multi-step tasks lose coherence |
| Subagents | Isolated child agents | Exploration pollutes context |
| Skills | On-demand knowledge | Domain expertise needed |
Most agents never need to go beyond Level 2.
Business: CRM queries, email, calendar, approvals Research: Database search, document analysis, citations Operations: Monitoring, tickets, notifications, escalation Creative: Asset generation, editing, collaboration, review
The pattern is universal. Only the capabilities change.
| Pattern | Problem | Solution |
|---|---|---|
| Over-engineering | Complexity before need | Start simple |
| Too many capabilities | Model confusion | 3-5 to start |
| Rigid workflows | Can't adapt | Let model decide |
| Front-loaded knowledge | Context bloat | Load on-demand |
| Micromanagement | Undercuts intelligence | Trust the model |
Philosophy & Theory:
references/agent-philosophy.md - Deep dive into why agents workImplementation:
references/minimal-agent.py - Complete working agent (~80 lines)references/tool-templates.py - Capability definitionsreferences/subagent-pattern.py - Context isolationScaffolding:
scripts/init_agent.py - Generate new agent projectsFrom: "How do I make the system do X?" To: "How do I enable the model to do X?"
From: "What's the workflow for this task?" To: "What capabilities would help accomplish this?"
The best agent code is almost boring. Simple loops. Clear capabilities. Clean context. The magic isn't in the code.
Give the model capabilities and knowledge. Trust it to figure out the rest.
商业级视觉资产与网页(详情页/落地页)的审美与UX视觉审查：输出P0/P1/P2问题清单、可落地的样式tokens与改稿建议；可结合截图、URL与源码进行定位与修改。
启用 agents-team 协作，双代理完成小说逐章元数据抽取与完整性审校（parser + checker），并写入可续跑的记忆索引。
Enable general multi-agent team mode via spawn_agent/wait tools. Supports orchestrator, worker, reviewer, research, writer, and editor roles.
进行全面代码审查，覆盖安全、正确性、性能与可维护性；适用于用户要求 review、排查潜在 bug 或审计代码库。
Agents-CLI 认知记忆系统。用于管理长期记忆（core/episodic/semantic/procedural/vault）、可检索回忆、归档遗忘、以及多代理写入治理。
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.