跳到主内容
智客 ZICQ

技能库 智客分类:文档办公 ask-docs

Ask Docs

查询CrewAI的官方文档以获取答案. 当用户有一个CrewAI问题没有完全覆盖在被启动,设计代理,设计任务技能中时使用——例如具体的API细节,配置选项,高级特性,故障排除出错,企业特性,工具引用,或者任何最新的docs是真理最佳来源的地方.

6891 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

查询 CrewAI 的官方文档以获取答案

何时用

这个技能

代理如何加载

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:Ask CrewAI Docs、When to Use This Skill、How to Query the Docs、Step 1: Fetch the docs index、Step 2: Fetch the relevant page、Step 3: Synthesize and cite。 其中含规范建议的小节:分步指令、输入输出示例。

文件分析

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。

官方 description(原文)

Query the official CrewAI documentation for answers. Use when the user has a CrewAI question that isn't fully covered by the getting-started, design-agent, design-task skills — e.g., specific API details, configuration options, advanced features, troubleshooting errors, enterprise features, tool references, or anything where the latest docs are the best source of truth.

Ask CrewAI DocsWhen to Use This SkillHow to Query the DocsStep 1: Fetch the docs indexStep 2: Fetch the relevant pageStep 3: Synthesize and citeWorkflow SummaryFor an Even Better ExperienceExamples of Good Use CasesRelated Skills

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
ask-docs
description
Query the official CrewAI documentation for answers. Use when the user has a CrewAI question that isn't fully covered by the getting-started, design-agent, design-task skills — e.g., specific API details, configuration options, advanced features, troubleshooting errors, enterprise features, tool references, or anything where the latest docs are the best source of truth.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

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 ↗

安装这个技能

Skills CLI ↗

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。

交给 Agent 安装

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「ask-docs」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-1f35e0a457a9a4de-%E8%AF%A2%E9%97%AE%E6%96%87%E6%A1%A3.html
请存为 .cursor/skills/ask-docs/SKILL.md 或 .claude/skills/ask-docs/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

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/crewaiinc/skills' --list

npx skills add 'https://github.com/crewaiinc/skills' --skill 'ask-docs'

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。

阅读排版
--- name: ask-docs description: "Query the official CrewAI documentation for answers. Use when the user has a CrewAI question that isn't fully covered by the getting-started, design-agent, design-task skills — e.g., specific API details, configuration options, advanced features, troubleshooting errors, enterprise features, tool references, or anything where the latest docs are the best source of truth." --- # Ask CrewAI Docs Answer CrewAI questions by looking up the official documentation at `docs.crewai.com`. --- ## When to Use This Skill Use this skill when: - The user asks about a CrewAI feature, parameter, or behavior not covered in detail by the other skills - You need to verify current API syntax, method signatures, or configuration options - The user hits an error and needs troubleshooting guidance from official docs - The question is about a newer or less common CrewAI feature (e.g., telemetry, testing, CLI commands, deployment, enterprise features) - The question is about experimental conversational Flows and you need the current `handle_turn()`, `ConversationConfig`, `RouterConfig`, tracing, or streaming behavior - You're unsure whether your knowledge is current — the docs reflect the latest published state **Do NOT use this skill** when the question is clearly answered by one of the other skills (getting-started, design-agent, design-task). Those skills contain curated, opinionated guidance. This skill is for filling gaps and verifying details. --- ## How to Query the Docs ### Step 1: Fetch the docs index The CrewAI docs site publishes an `llms.txt` file — a structured index of every documentation page with descriptions. Fetch it first to find the right page: ``` WebFetch: https://docs.crewai.com/llms.txt ``` This returns a categorized list of all doc pages in the format: ``` - [Page Title](https://docs.crewai.com/path/to/page): "Description of what the page covers" ``` Categories include: - **API Reference** — REST endpoints (kickoff, status, resume, inputs) - **Concepts** — agents, crews, tasks, tools, flows, memory, knowledge, LLMs, processes, training, testing - **Enterprise** — RBAC, SSO, automations, traces, deployment, triggers, integrations - **Tools Library** — 40+ tools organized by category (AI/ML, automation, cloud, database, files, search, web scraping) - **MCP Integration** — MCP server setup, transports, DSL, security - **Examples & Cookbooks** — practical implementations - **Learning Paths** — tutorials and advanced topics - **Observability** — monitoring integrations For conversational Flow questions, go directly to: ``` WebFetch: https://docs.crewai.com/en/guides/flows/conversational-flows ``` Treat this page as the source of truth for the experimental `crewai.experimental.conversational` surface. Verify it before answering detailed API questions because the feature may change before it graduates. ### Step 2: Fetch the relevant page Once you identify the right page from the index, fetch its content: ``` WebFetch: https://docs.crewai.com/ ``` ### Step 3: Synthesize and cite Combine what you find from the docs with context from the other skills to give a clear, actionable response. Always include the docs URL so the user can read further. --- ## Workflow Summary 1. **Understand the user's question** — what specific CrewAI concept, API, or behavior are they asking about? 2. **Fetch `llms.txt`** — scan the index to find the most relevant page(s) 3. **Fetch the page(s)** — retrieve the actual documentation content 4. **Synthesize the answer** — combine docs content with context from other skills 5. **Cite the source** — include the docs URL in your response --- ## For an Even Better Experience Users who frequently query CrewAI docs can configure the CrewAI docs MCP server in their coding agent for richer, structured search: ``` https://docs.crewai.com/mcp ``` This is optional — the `llms.txt` workflow above works without any setup. --- ## Examples of Good Use Cases | User Question | Why This Skill | |---|---| | "What parameters does `Crew()` accept?" | Specific API reference — docs are authoritative | | "How do I set up telemetry in CrewAI?" | Niche feature not covered in other skills | | "What's the difference between `Process.sequential` and `Process.hierarchical`?" | Detailed comparison best sourced from docs | | "I'm getting `ValidationError` when using `output_pydantic`" | Troubleshooting — docs may have known issues or caveats | | "How do I deploy a CrewAI flow to production?" | Deployment guidance lives in docs, not in design skills | | "What CLI commands does `crewai` support?" | CLI reference is a docs concern | | "How do I configure memory for a crew?" | Detailed config options beyond what design-agent covers | | "What tools are available for web scraping?" | Tools library reference | | "How do I set up SSO for CrewAI enterprise?" | Enterprise features live in docs | | "How do I build a chat app with Flow.handle_turn()?" | Experimental conversational Flow API; verify the latest guide | --- ## Related Skills - **getting-started** — project scaffolding, choosing abstractions, Flow architecture - **design-agent** — agent Role-Goal-Backstory, parameter tuning, tools, memory & knowledge - **design-task** — task descriptions, expected_output, guardrails, structured output, dependencies

相关技能

文档办公

Ontology

为结构化的代理内存和可堆肥技能所打入的知识图. 在创建/征服实体(Person, project, Task, Evention, Document)时使用,链接相关对象,强制约束,规划多步动作作为图变,或技能需要共享状态时使用. 触发到"记住","我知道什么","链接X到Y",…

文档办公

Nano Pdf

使用纳米-pdf CLI编辑带有自然语言指令的PDF.

文档办公

Word / DOCX

创建,检查,并编辑有可靠样式的Microsoft Word文档和DOCX文件,编号,跟踪更改,表格,章节,并进行相容性检查. 当 (1) 任务涉及 Word 或 ".docx " 时使用; (2) 文件包括跟踪的更改,评论,字段,表格,模板,或页面布局限制; (3) 文档必须在不…

文档办公

Api Gateway

通过 Maton 网关调用第三方 API, 它为用户已经连接的应用程序注入证书 。 当用户命名一个连接的应用程序和其中的具体行动时使用此技能——读取一个邮箱,查询一个CMM,归档一个问题,更新一个电子表格,通过一个连接的搜索或刮取提供者运行一个查询. 每一次通话都到用户连接的应用…