AI 技能AI 插件人工智能【免费下载链接】agentic-awesome-skillsAAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,600 agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.项目地址https://gitcode.com/GitHub_Trending/an/agentic-awesome-skills点击查看免费下载本文围绕 agentic-awesome-skills 仓库中autonomous-agent-patterns技能根技能定义见 SKILL.md完整程序与参考材料见 详细指南展开系统讲解设计自主编码 Agent 所需的六大核心模式Agent 循环、多模型架构、工具设计、权限与安全、浏览器自动化、上下文管理与 MCP 集成。读完本文你将能够照着可复制的代码骨架搭建一个具备工具调用、审批机制、沙箱隔离、断点恢复能力的自主编码 Agent并将其接入仓库技能体系进行组合使用。在 agentic-awesome-skills 仓库中autonomous-agent-patterns被收录于 catalog.json归类为ai-ml类别、critical风险等级标签为autonomous、agent触发词覆盖 building coding agents 等常见表述——这意味着当用户提出构建自主编码 Agent 的需求时该技能会被 Agent 自动激活。该技能以 Cline 与 OpenAI Codex 为设计灵感来源与仓库内兄弟技能 autonomous-agents侧重 ReAct、Plan-Execute、Reflection 等推理模式与可靠性原则互为补充前者提供如何实现的工程骨架后者提供如何设计的原则约束。1. 核心 Agent 架构1.1 Agent 循环Agent Loop所有自主 Agent 的本质都是一个循环思考Think→ 决策Decide→ 执行Act→ 观察Observe循环往复直到任务完成或达到迭代上限。┌─────────────────────────────────────────────────────────────┐ │ AGENT LOOP │ │ │ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ │ │ Think │───▶│ Decide │───▶│ Act │ │ │ │ (Reason) │ │ (Plan) │ │ (Execute)│ │ │ └──────────┘ └──────────┘ └──────────┘ │ │ ▲ │ │ │ │ ┌──────────┐ │ │ │ └─────────│ Observe │◀─────────┘ │ │ │ (Result) │ │ │ └──────────┘ │ └─────────────────────────────────────────────────────────────┘详细指南给出了一份可直接运行的最小实现。其关键设计点在于循环终止条件LLM 返回tool_calls时持续执行工具不再返回工具调用时即视为任务完成若达到max_iterations仍未收敛则返回 Max iterations reached 防止失控。详细指南中的默认值为 50 次迭代。历史即状态整个history列表同时承担对话上下文与工具结果回传两个职责role: tool的消息通过tool_call_id与对应的工具调用建立关联这是 OpenAI 风格工具调用协议的标准写法。工具注册表self.tools {t.name: t for t in tools}以工具名为键建立索引_execute_tool内部通过json.loads(tool_call.arguments)解析参数并动态调用。class AgentLoop: def __init__(self, llm, tools, max_iterations50): self.llm llm self.tools {t.name: t for t in tools} self.max_iterations max_iterations self.history [] def run(self, task: str) - str: self.history.append({role: user, content: task}) for i in range(self.max_iterations): # Think: Get LLM response with tool options response self.llm.chat( messagesself.history, toolsself._format_tools(), tool_choiceauto ) # Decide: Check if agent wants to use a tool if response.tool_calls: for tool_call in response.tool_calls: # Act: Execute the tool result self._execute_tool(tool_call) # Observe: Add result to history self.history.append({ role: tool, tool_call_id: tool_call.id, content: str(result) }) else: # No more tool calls task complete return response.content return Max iterations reached def _execute_tool(self, tool_call) - Any: tool self.tools[tool_call.name] args json.loads(tool_call.arguments) return tool.execute(**args)从仓库兄弟技能 autonomous-agents 详细指南 可以印证该循环背后的设计动机ReAct 模式Thought → Action → Observation 交替是现代 Agent 的基础而显式推理轨迹让调试成为可能是必须坚持的原则——因此实现中不应把推理过程吞掉而应像上述代码一样把每一步思考与工具结果都写入history保证可审计、可回放。1.2 多模型架构Multi-Model Architecture自主编码 Agent 不必所有环节共用同一个模型。详细指南建议按任务类型差异化选型快速模型负责计划、强大模型负责复杂推理、专门模型负责代码生成。class MultiModelAgent: Use different models for different purposes: - Fast model for planning - Powerful model for complex reasoning - Specialized model for code generation def __init__(self): self.models { fast: gpt-3.5-turbo, # Quick decisions smart: gpt-4-turbo, # Complex reasoning code: claude-3-sonnet, # Code generation } def select_model(self, task_type: str) - str: if task_type planning: return self.models[fast] elif task_type analysis: return self.models[smart] elif task_type code: return self.models[code] return self.models[smart]说明两点上述模型名仅为示例占位实际接入时以你环境中可用的模型为准模式的本质是按任务类型建立模型路由表将task_type到模型标识的映射做成配置便于替换与成本控制。该模式与仓库内Multi-Model类技能的思路一致不是追求单一模型全知全能而是把便宜快速的模型用在高频低风险环节把昂贵强模型用在低频高风险环节。2. 工具设计模式Tool Design Patterns2.1 工具 Schema 与基类每个工具都应暴露标准的 JSON Schema 描述名称、说明、参数、必填项供 LLM 理解并生成调用。详细指南给出了Tool基类与ReadFileTool的完整实现class Tool: Base class for agent tools property def schema(self) - dict: JSON Schema for the tool return { name: self.name, description: self.description, parameters: { type: object, properties: self._get_parameters(), required: self._get_required() } } def execute(self, **kwargs) - ToolResult: Execute the tool and return result raise NotImplementedError class ReadFileTool(Tool): name read_file description Read the contents of a file from the filesystem def _get_parameters(self): return { path: { type: string, description: Absolute path to the file }, start_line: { type: integer, description: Line to start reading from (1-indexed) }, end_line: { type: integer, description: Line to stop reading at (inclusive) } } def _get_required(self): return [path] def execute(self, path: str, start_line: int None, end_line: int None) - ToolResult: try: with open(path, r) as f: lines f.readlines() if start_line and end_line: lines lines[start_line-1:end_line] return ToolResult( successTrue, output.join(lines) ) except FileNotFoundError: return ToolResult( successFalse, errorfFile not found: {path} )设计要点统一的ToolResult返回值无论成功失败都返回结构化结果success/output/errorLLM 才能可靠地根据观察决定下一步。参数描述必须面向模型description字段是给模型读的写得越明确如 Line to start reading from (1-indexed)模型生成的参数越准确。异常也要结构化捕获FileNotFoundError并返回successFalse而不是抛异常中断循环——Agent 循环要求每一步都必须有可观察的返回。2.2 编码 Agent 的必备工具清单详细指南用一张映射表给出了一个编码 Agent 的完整工具面CODING_AGENT_TOOLS { # File operations read_file: Read file contents, write_file: Create or overwrite a file, edit_file: Make targeted edits to a file, list_directory: List files and folders, search_files: Search for files by pattern, # Code understanding search_code: Search for code patterns (grep), get_definition: Find function/class definition, get_references: Find all references to a symbol, # Terminal run_command: Execute a shell command, read_output: Read command output, send_input: Send input to running command, # Browser (optional) open_browser: Open URL in browser, click_element: Click on page element, type_text: Type text into input, screenshot: Capture screenshot, # Context ask_user: Ask the user a question, search_web: Search the web for information }这张清单的划分逻辑值得借鉴文件操作 → 代码理解 → 终端执行 → 浏览器可选→ 上下文。其中ask_user与search_web属于上下文类工具——前者实现人机交互后者实现外部信息获取两者都是提升 Agent 鲁棒性的关键补充。2.3 编辑工具设计精确替换 冲突检测直接整文件覆写极易破坏用户代码因此详细指南专门给出了EditFileTool采用search/replace 精确替换并通过expected_occurrences做冲突校验——只有待替换文本出现次数与预期一致时才执行写入否则拒绝修改并返回错误。class EditFileTool(Tool): Precise file editing with conflict detection. Uses search/replace pattern for reliable edits. name edit_file description Edit a file by replacing specific content def execute( self, path: str, search: str, replace: str, expected_occurrences: int 1 ) - ToolResult: Args: path: File to edit search: Exact text to find (must match exactly, including whitespace) replace: Text to replace with expected_occurrences: How many times search should appear (validation) with open(path, r) as f: content f.read() # Validate actual_occurrences content.count(search) if actual_occurrences ! expected_occurrences: return ToolResult( successFalse, errorfExpected {expected_occurrences} occurrences, found {actual_occurrences} ) if actual_occurrences 0: return ToolResult( successFalse, errorSearch text not found in file ) # Apply edit new_content content.replace(search, replace) with open(path, w) as f: f.write(new_content) return ToolResult( successTrue, outputfReplaced {actual_occurrences} occurrence(s) )这一模式是 Cline 等主流编码 Agent 的核心可靠性手段先验证再写入。content.count(search)的精确匹配含空白字符保证了不会误改相似文本期望出现次数默认 1当代码中存在多处相同片段时强制显式声明从机制上避免批量误替换。3. 权限与安全模式Permission Safety Patterns3.1 四级权限模型自主 Agent 必须对工具调用实施分级授权。详细指南定义了AUTO / ASK_ONCE / ASK_EACH / NEVER四级权限并将工具按风险归类class PermissionLevel(Enum): # Fully automatic - no user approval needed AUTO auto # Ask once per session ASK_ONCE ask_once # Ask every time ASK_EACH ask_each # Never allow NEVER never PERMISSION_CONFIG { # Low risk - can auto-approve read_file: PermissionLevel.AUTO, list_directory: PermissionLevel.AUTO, search_code: PermissionLevel.AUTO, # Medium risk - ask once write_file: PermissionLevel.ASK_ONCE, edit_file: PermissionLevel.ASK_ONCE, # High risk - ask each time run_command: PermissionLevel.ASK_EACH, delete_file: PermissionLevel.ASK_EACH, # Dangerous - never auto-approve sudo_command: PermissionLevel.NEVER, format_disk: PermissionLevel.NEVER }分级原则一目了然只读操作自动放行AUTO写操作会话内询问一次ASK_ONCE命令执行与删除每次询问ASK_EACH毁灭性操作永不允许NEVER。该设计同时解决了效率与安全的矛盾——既不打断高频安全的读取也不放过高风险操作。3.2 审批管理器与动态风险评级仅仅按工具静态分级还不够ApprovalManager进一步引入了基于参数的动态风险评级同一个run_command工具执行ls与执行rm -rf的风险完全不同需要在审批时逐次评估。class ApprovalManager: def __init__(self, ui, config): self.ui ui self.config config self.session_approvals {} def request_approval(self, tool_name: str, args: dict) - bool: level self.config.get(tool_name, PermissionLevel.ASK_EACH) if level PermissionLevel.AUTO: return True if level PermissionLevel.NEVER: self.ui.show_error(fTool {tool_name} is not allowed) return False if level PermissionLevel.ASK_ONCE: if tool_name in self.session_approvals: return self.session_approvals[tool_name] # Show approval dialog approved self.ui.show_approval_dialog( tooltool_name, argsargs, risk_levelself._assess_risk(tool_name, args) ) if level PermissionLevel.ASK_ONCE: self.session_approvals[tool_name] approved return approved def _assess_risk(self, tool_name: str, args: dict) - str: Analyze specific call for risk level if tool_name run_command: cmd args.get(command, ) if any(danger in cmd for danger in [rm -rf, sudo, chmod]): return HIGH return MEDIUM要点会话级记忆session_approvals字典让ASK_ONCE的授权在单次会话内生效避免重复打扰。风险关键词黑名单_assess_risk通过检测rm -rf、sudo、chmod等危险片段将命令升级为HIGH风险触发更严格的审批展示。3.3 沙箱化执行Sandboxing即使有审批未经验证的第三方代码也不该直接运行在宿主环境。SandboxedExecution提供了一层轻量隔离命令白名单 路径白名单 环境隔离。class SandboxedExecution: Execute code/commands in isolated environment def __init__(self, workspace_dir: str): self.workspace workspace_dir self.allowed_commands [npm, python, node, git, ls, cat] self.blocked_paths [/etc, /usr, /bin, os.path.expanduser(~)] def validate_path(self, path: str) - bool: Ensure path is within workspace real_path os.path.realpath(path) workspace_real os.path.realpath(self.workspace) return real_path.startswith(workspace_real) def validate_command(self, command: str) - bool: Check if command is allowed cmd_parts shlex.split(command) if not cmd_parts: return False base_cmd cmd_parts[0] return base_cmd in self.allowed_commands def execute_sandboxed(self, command: str) - ToolResult: if not self.validate_command(command): return ToolResult( successFalse, errorfCommand not allowed: {command} ) # Execute in isolated environment result subprocess.run( command, shellTrue, cwdself.workspace, capture_outputTrue, timeout30, env{ **os.environ, HOME: self.workspace, # Isolate home directory } ) return ToolResult( successresult.returncode 0, outputresult.stdout.decode(), errorresult.stderr.decode() if result.returncode ! 0 else None )安全细节真实路径校验os.path.realpath解析符号链接后判断是否位于工作区之内可绕过..路径穿越。命令白名单 shlex.split先分词取可执行文件主名再校验避免python -c ...恶意...一类通过参数混入的危险allowed_commands可按项目实际需要裁剪。超时与 HOME 隔离timeout30防止失控进程挂死把HOME指向工作区使未信任命令无法访问用户真实主目录。4. 浏览器自动化Browser Automation4.1 浏览器工具模式现代编码 Agent 常需要验证前端效果或抓取页面状态。详细指南基于 Playwright/Puppeteer 给出了浏览器工具实现每次关键操作打开、点击后自动截图并回传让 Agent 具备视觉观察能力。class BrowserTool: Browser automation for agents using Playwright/Puppeteer. Enables visual debugging and web testing. def __init__(self, headless: bool True): self.browser None self.page None self.headless headless async def open_url(self, url: str) - ToolResult: Navigate to URL and return page info if not self.browser: self.browser await playwright.chromium.launch(headlessself.headless) self.page await self.browser.new_page() await self.page.goto(url) # Capture state screenshot await self.page.screenshot(typepng) title await self.page.title() return ToolResult( successTrue, outputfLoaded: {title}, metadata{ screenshot: base64.b64encode(screenshot).decode(), url: self.page.url } ) async def click(self, selector: str) - ToolResult: Click on an element try: await self.page.click(selector, timeout5000) await self.page.wait_for_load_state(networkidle) screenshot await self.page.screenshot() return ToolResult( successTrue, outputfClicked: {selector}, metadata{screenshot: base64.b64encode(screenshot).decode()} ) except TimeoutError: return ToolResult( successFalse, errorfElement not found: {selector} ) async def type_text(self, selector: str, text: str) - ToolResult: Type text into an input await self.page.fill(selector, text) return ToolResult(successTrue, outputfTyped into {selector}) async def get_page_content(self) - ToolResult: Get accessible text content of the page content await self.page.evaluate( () { // Get visible text const walker document.createTreeWalker( document.body, NodeFilter.SHOW_TEXT, null, false ); let text ; while (walker.nextNode()) { const node walker.currentNode; if (node.textContent.trim()) { text node.textContent.trim() \\n; } } return text; } ) return ToolResult(successTrue, outputcontent)实践要点截图回传metadata中携带 base64 编码的截图为后面视觉 Agent模式铺路。等待网络空闲点击后wait_for_load_state(networkidle)确保 SPA 渲染完成再截图避免截到中间态。超时即失败元素 5 秒内不可见就返回结构化错误而不是长时间挂起。4.2 视觉 Agent 模式当页面元素没有稳定的 CSS 选择器时可以退化为视觉驱动把截图交给多模态 LLM让它描述页面、甚至直接返回目标元素的近似坐标再用鼠标坐标点击。class VisualAgent: Agent that uses screenshots to understand web pages. Can identify elements visually without selectors. def __init__(self, llm, browser): self.llm llm self.browser browser async def describe_page(self) - str: Use vision model to describe current page screenshot await self.browser.screenshot() response self.llm.chat([ { role: user, content: [ {type: text, text: Describe this webpage. List all interactive elements you see.}, {type: image, data: screenshot} ] } ]) return response.content async def find_and_click(self, description: str) - ToolResult: Find element by visual description and click it screenshot await self.browser.screenshot() # Ask vision model to find element response self.llm.chat([ { role: user, content: [ { type: text, text: f Find the element matching: {description} Return the approximate coordinates as JSON: {{x: number, y: number}} }, {type: image, data: screenshot} ] } ]) coords json.loads(response.content) await self.browser.page.mouse.click(coords[x], coords[y]) return ToolResult(successTrue, outputfClicked at ({coords[x]}, {coords[y]}))该模式的代价与收益同样明显选择器方案更稳定视觉方案更通用。工程上建议先选择器、后视觉的降级策略——DOM 方案失败时再回退到截图 坐标。5. 上下文管理Context Management5.1 上下文注入模式-mention 风格编码 Agent 需要高效地把文件、文件夹、URL、IDE 诊断注入提示词。详细指南借鉴 Cline 的提及模式实现了ContextManagerclass ContextManager: Manage context provided to the agent. Inspired by Clines -mention patterns. def __init__(self, workspace: str): self.workspace workspace self.context [] def add_file(self, path: str) - None: file - Add file contents to context with open(path, r) as f: content f.read() self.context.append({ type: file, path: path, content: content }) def add_folder(self, path: str, max_files: int 20) - None: folder - Add all files in folder for root, dirs, files in os.walk(path): for file in files[:max_files]: file_path os.path.join(root, file) self.add_file(file_path) def add_url(self, url: str) - None: url - Fetch and add URL content response requests.get(url) content html_to_markdown(response.text) self.context.append({ type: url, url: url, content: content }) def add_problems(self, diagnostics: list) - None: problems - Add IDE diagnostics self.context.append({ type: diagnostics, problems: diagnostics }) def format_for_prompt(self) - str: Format all context for LLM prompt parts [] for item in self.context: if item[type] file: parts.append(f## File: {item[path]}\n\n{item[content]}\n) elif item[type] url: parts.append(f## URL: {item[url]}\n{item[content]}) elif item[type] diagnostics: parts.append(f## Problems:\n{json.dumps(item[problems], indent2)}) return \n\n.join(parts)模式价值统一格式文件用代码块包裹、URL 转 Markdown、诊断转 JSON最终拼成结构化的提示词LLM 更容易定位信息。限额保护add_folder默认最多加载 20 个文件防止文件夹过大致使上下文爆炸。这与兄弟技能 autonomous-agents 中ContextManager的令牌预算 压缩思路形成互补一个解决怎么装进上下文一个解决装不下时怎么办保留系统提示词与最近 N 条消息中间部分做摘要。5.2 检查点 / 断点续跑长任务随时可能中断超时、断网、进程被杀。CheckpointManager将完整 Agent 状态历史、上下文、工作区状态序列化到磁盘实现断点续跑class CheckpointManager: Save and restore agent state for long-running tasks. def __init__(self, storage_dir: str): self.storage_dir storage_dir os.makedirs(storage_dir, exist_okTrue) def save_checkpoint(self, session_id: str, state: dict) - str: Save current agent state checkpoint { timestamp: datetime.now().isoformat(), session_id: session_id, history: state[history], context: state[context], workspace_state: self._capture_workspace(state[workspace]), metadata: state.get(metadata, {}) } path os.path.join(self.storage_dir, f{session_id}.json) with open(path, w) as f: json.dump(checkpoint, f, indent2) return path def restore_checkpoint(self, checkpoint_path: str) - dict: Restore agent state from checkpoint with open(checkpoint_path, r) as f: checkpoint json.load(f) return { history: checkpoint[history], context: checkpoint[context], workspace: self._restore_workspace(checkpoint[workspace_state]), metadata: checkpoint[metadata] } def _capture_workspace(self, workspace: str) - dict: Capture relevant workspace state # Git status, file hashes, etc. return { git_ref: subprocess.getoutput(fcd {workspace} git rev-parse HEAD), git_dirty: subprocess.getoutput(fcd {workspace} git status --porcelain) }要点状态三件套history对话与工具结果、context注入的上下文、workspace_stateGit 提交号 工作区脏状态三者共同定义了Agent 到哪一步了。幂等续跑恢复后按session_id命名的 JSON 文件即可重建现场_capture_workspace让恢复时可以比对 Git 状态判断文件是否被外部改动从而决定是否继续。6. MCPModel Context Protocol集成6.1 MCP 服务器模式动态发现与按需创建工具MCP 让 Agent 摆脱内置工具写死的限制能够动态发现外部服务器提供的工具甚至根据一句自然语言描述让 LLM 现场生成一个新的 MCP 服务器并热加载——这是 Cline Add a tool that... 模式的直接体现。from mcp import Server, Tool class MCPAgent: Agent that can dynamically discover and use MCP tools. Add a tool that... pattern from Cline. def __init__(self, llm): self.llm llm self.mcp_servers {} self.available_tools {} def connect_server(self, name: str, config: dict) - None: Connect to an MCP server server Server(config) self.mcp_servers[name] server # Discover tools tools server.list_tools() for tool in tools: self.available_tools[tool.name] { server: name, schema: tool.schema } async def create_tool(self, description: str) - str: Create a new MCP server based on user description. Add a tool that fetches Jira tickets # Generate MCP server code code self.llm.generate(f Create a Python MCP server with a tool that does: {description} Use the FastMCP framework. Include proper error handling. Return only the Python code. ) # Save and install server_name self._extract_name(description) path f./mcp_servers/{server_name}/server.py with open(path, w) as f: f.write(code) # Hot-reload self.connect_server(server_name, {path: path}) return fCreated tool: {server_name}实现链路由三个环节组成连接connect_server→ 发现list_tools 同步 schema→ 按需生成create_tool 用 LLM 产出 FastMCP 服务器代码并热加载。每一步都有明确的调用关系可以对照仓库中其他 MCP 相关技能如 mcp-builder、mcp-server-security进一步了解服务器编写与安全加固细节。需要强调的是按需生成代码LLM 写 MCP 服务器必须叠加第 3 节的权限与沙箱机制——新生成的服务器代码应经过审查或放入隔离环境后再加载防止注入。7. 最佳实践检查清单详细指南在末尾给出了一份可直接作为交付验收标准的检查清单覆盖设计、安全、体验三个维度Agent 设计Clear task decomposition清晰的任务分解Appropriate tool granularity合适的工具粒度Error handling at each step每一步都有错误处理Progress visibility to user进度对用户可见安全Permission system implemented权限系统已实现Dangerous operations blocked危险操作已被拦截Sandbox for untrusted code未信任代码有沙箱Audit logging enabled审计日志已开启体验Approval UI is clear审批界面清晰Progress updates provided提供进度更新Undo/rollback available支持撤销/回滚Explanation of actions解释每次动作这份清单与兄弟技能 autonomous-agents 详细指南 中的可靠性原则相互呼应可靠性优先于自主性每一步都会放大错误概率把 AI 输出当作提案而非事实关键决策必须有人类参与所有动作必须可审计失败要可回滚而非静默损坏。构建自主 Agent 的第一原则永远是先建护栏再扩能力。8. 在仓库技能体系中的定位与使用方式在 agentic-awesome-skills 仓库中autonomous-agent-patterns是社区来源source: community、critical风险等级的技能定位于构建自主编码 Agent这一任务域。使用建议触发时机当任务涉及构建自主 AI Agent、设计工具/函数调用 API、实现权限与审批系统、为 Agent 做浏览器自动化、设计 human-in-the-loop 工作流时激活该技能见 SKILL.md 的 When to Use This Skill 段落。使用姿势仓库遵循根技能定义激活条件、详细指南承载完整程序的结构。端到端执行前应先通读 详细指南聚焦式工作可只加载相关小节。该技能已在 catalog.json 注册Agent 可基于autonomous、agent、building coding agents等触发词自动发现。组合搭配本文的工程骨架AgentLoop、工具、权限、沙箱、检查点、MCP与兄弟技能autonomous-agents的推理模式ReAct、Plan-Execute、Reflection配合使用效果最佳涉及多 Agent 协作时可参考 multi-agent-patterns涉及工具构建可参考 agent-tool-builder。总结本文完整继承了autonomous-agent-patterns技能的六大部分内容并补充了实现动机与安全细节从 Agent 循环与多模型路由的架构设计到工具 Schema、编辑冲突检测的工程实现从四级权限、动态风险评级与沙箱隔离的安全机制到浏览器自动化、上下文注入、断点恢复与 MCP 动态工具发现。核心结论可以浓缩为三条循环 历史是自主 Agent 的根基一切能力建立在可观察、可回放的状态之上权限与沙箱不是可选项而是必选项NEVER级拦截与危险命令检测是底线先可靠性后自主性把 AI 输出当作提案用检查清单逐项验收才能构建可长期运行的自主编码 Agent。赞分享AI 技能AI 插件人工智能【免费下载链接】agentic-awesome-skillsAAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,600 agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.项目地址https://gitcode.com/GitHub_Trending/an/agentic-awesome-skills点击查看免费下载相关推荐自主智能体设计模式全解析构建自主编码 Agent 的架构、工具、权限与安全实践基于 agentic-awesome-skills 的 autonomous-agent-patterns自主智能体设计模式全解析构建自主编码 Agent 的架构、工具、权限与安全实践基于 agentic awesome skills 的 autonomousAI 技能AI 插件人工智能基于 AAS 的 App Builder 技能从自然语言到全栈应用的 Agent 编排实战指南基于 AAS 的 App Builder 技能从自然语言到全栈应用的 Agent 编排实战指南 本文围绕 AASagentic awesome skillsAI 技能AI 插件人工智能AAS 实战基于 bats-testing-patterns 技能构建生产级 Shell 脚本测试体系AAS 实战基于 bats testing patterns 技能构建生产级 Shell 脚本测试体系 BatsBash Automated TestingAI 技能AI 插件人工智能上一篇Voyager 用户消息 LaTeX 渲染指南在 Gemini 聊天中自动渲染数学公式下一篇TanStack Table 列级行聚合 API 深度解析Column_RowAggregation 接口实现与使用指南创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考