# crewai - Doramagic AI Context Pack > 定位：安装前体验与判断资产。它帮助宿主 AI 有一个好的开始，但不代表已经安装、执行或验证目标项目。 ## 充分原则 - **充分原则，不是压缩原则**：AI Context Pack 应该充分到让宿主 AI 在开工前理解项目价值、能力边界、使用入口、风险和证据来源；它可以分层组织，但不以最短摘要为目标。 - **压缩策略**：只压缩噪声和重复内容，不压缩会影响判断和开工质量的上下文。 ## 给宿主 AI 的使用方式 你正在读取 Doramagic 为 crewai 编译的 AI Context Pack。请把它当作开工前上下文：帮助用户理解适合谁、能做什么、如何开始、哪些必须安装后验证、风险在哪里。不要声称你已经安装、运行或执行了目标项目。 ## Claim 消费规则 - **事实来源**：Repo Evidence + Claim/Evidence Graph；Human Wiki 只提供显著性、术语和叙事结构。 - **事实最低状态**：`supported` - `supported`：可以作为项目事实使用，但回答中必须引用 claim_id 和证据路径。 - `weak`：只能作为低置信度线索，必须要求用户继续核实。 - `inferred`：只能用于风险提示或待确认问题，不能包装成项目事实。 - `unverified`：不得作为事实使用，应明确说证据不足。 - `contradicted`：必须展示冲突来源，不得替用户强行选择一个版本。 ## 它最适合谁 - **正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**：README 或插件配置提到多个宿主 AI。 证据：`README.md` Claim：`clm_0003` supported 0.86 - **希望把专业流程带进宿主 AI 的用户**：仓库包含 Skill 文档。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md`, `lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md`, `lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` Claim：`clm_0004` supported 0.86 ## 它能做什么 - **AI Skill / Agent 指令资产库**（可做安装前预览）：项目包含可被宿主 AI 读取的 Skill 或 Agent 指令文件，可用于把专业流程带入 Claude、Codex、Cursor 等宿主。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md`, `lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md`, `lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` Claim：`clm_0001` supported 0.86 - **命令行启动或安装流程**（需要安装后验证）：项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 证据：`README.md` Claim：`clm_0002` supported 0.86 ## 怎么开始 - `/plugin marketplace add crewAIInc/skills` 证据：`README.md` Claim：`clm_0005` supported 0.86 - `/plugin install crewai-skills@crewai-plugins` 证据：`README.md` Claim：`clm_0006` supported 0.86 - `npx skills add crewaiinc/skills` 证据：`README.md` Claim：`clm_0007` supported 0.86 ## 继续前判断卡 - **当前建议**：仅建议沙盒试装 - **为什么**：项目存在安装命令、宿主配置或本地写入线索，不建议直接进入主力环境，应先在隔离环境试装。 ### 30 秒判断 - **现在怎么做**：仅建议沙盒试装 - **最小安全下一步**：先跑 Prompt Preview；若仍要安装，只在隔离环境试装 - **先别相信**：真实输出质量不能在安装前相信。 - **继续会触碰**：命令执行、宿主 AI 配置、本地环境或项目文件 ### 现在可以相信 - **适合人群线索：正在使用 Claude/Codex/Cursor/Gemini 等宿主 AI 的开发者**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0003` supported 0.86 - **适合人群线索：希望把专业流程带进宿主 AI 的用户**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md`, `lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md`, `lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` Claim：`clm_0004` supported 0.86 - **能力存在：AI Skill / Agent 指令资产库**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md`, `lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md`, `lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` Claim：`clm_0001` supported 0.86 - **能力存在：命令行启动或安装流程**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`README.md` Claim：`clm_0002` supported 0.86 - **存在 Quick Start / 安装命令线索**（supported）：可以相信项目文档出现过启动或安装入口；不要因此直接在主力环境运行。 证据：`README.md` Claim：`clm_0005` supported 0.86 ### 现在还不能相信 - **真实输出质量不能在安装前相信。**（unverified）：Prompt Preview 只能展示引导方式，不能证明真实项目中的结果质量。 - **宿主 AI 版本兼容性不能在安装前相信。**（unverified）：Claude、Cursor、Codex、Gemini 等宿主加载规则和版本差异必须在真实环境验证。 - **不会污染现有宿主 AI 行为，不能直接相信。**（inferred）：Skill、plugin、AGENTS/CLAUDE/GEMINI 指令可能改变宿主 AI 的默认行为。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md`, `lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md`, `lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` - **可安全回滚不能默认相信。**（unverified）：除非项目明确提供卸载和恢复说明，否则必须先在隔离环境验证。 - **真实安装后是否与用户当前宿主 AI 版本兼容？**（unverified）：兼容性只能通过实际宿主环境验证。 - **项目输出质量是否满足用户具体任务？**（unverified）：安装前预览只能展示流程和边界，不能替代真实评测。 - **安装命令是否需要网络、权限或全局写入？**（unverified）：这影响企业环境和个人环境的安装风险。 证据：`README.md` ### 继续会触碰什么 - **命令执行**：包管理器、网络下载、本地插件目录、项目配置或用户主目录。 原因：运行第一条命令就可能产生环境改动；必须先判断是否值得跑。 证据：`README.md` - **宿主 AI 配置**：Claude/Codex/Cursor/Gemini/OpenCode 等宿主的 plugin、Skill 或规则加载配置。 原因：宿主配置会改变 AI 后续工作方式，可能和用户已有规则冲突。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md`, `lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md`, `lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` - **本地环境或项目文件**：安装结果、插件缓存、项目配置或本地依赖目录。 原因：安装前无法证明写入范围和回滚方式，需要隔离验证。 证据：`README.md` - **宿主 AI 上下文**：AI Context Pack、Prompt Preview、Skill 路由、风险规则和项目事实。 原因：导入上下文会影响宿主 AI 后续判断，必须避免把未验证项包装成事实。 ### 最小安全下一步 - **先跑 Prompt Preview**：用安装前交互式试用判断工作方式是否匹配，不需要授权或改环境。（适用：任何项目都适用，尤其是输出质量未知时。） - **只在隔离目录或测试账号试装**：避免安装命令污染主力宿主 AI、真实项目或用户主目录。（适用：存在命令执行、插件配置或本地写入线索时。） - **先备份宿主 AI 配置**：Skill、plugin、规则文件可能改变 Claude/Cursor/Codex 的默认行为。（适用：存在插件 manifest、Skill 或宿主规则入口时。） - **安装后只验证一个最小任务**：先验证加载、兼容、输出质量和回滚，再决定是否深用。（适用：准备从试用进入真实工作流时。） ### 退出方式 - **保留安装前状态**：记录原始宿主配置和项目状态，后续才能判断是否可恢复。 - **准备移除宿主 plugin / Skill / 规则入口**：如果试装后行为异常，可以把宿主 AI 恢复到试装前状态。 - **记录安装命令和写入路径**：没有明确卸载说明时，至少要知道哪些目录或配置需要手动清理。 - **如果没有回滚路径，不进入主力环境**：不可回滚是继续前阻断项，不应靠信任或运气继续。 ## 哪些只能预览 - 解释项目适合谁和能做什么 - 基于项目文档演示典型对话流程 - 帮助用户判断是否值得安装或继续研究 ## 哪些必须安装后验证 - 真实安装 Skill、插件或 CLI - 执行脚本、修改本地文件或访问外部服务 - 验证真实输出质量、性能和兼容性 ## 边界与风险判断卡 - **把安装前预览误认为真实运行**：用户可能高估项目已经完成的配置、权限和兼容性验证。 处理方式：明确区分 prompt_preview_can_do 与 runtime_required。 Claim：`clm_0008` inferred 0.45 - **命令执行会修改本地环境**：安装命令可能写入用户主目录、宿主插件目录或项目配置。 处理方式：先在隔离环境或测试账号中运行。 证据：`README.md` Claim：`clm_0009` supported 0.86 - **待确认**：真实安装后是否与用户当前宿主 AI 版本兼容？。原因：兼容性只能通过实际宿主环境验证。 - **待确认**：项目输出质量是否满足用户具体任务？。原因：安装前预览只能展示流程和边界，不能替代真实评测。 - **待确认**：安装命令是否需要网络、权限或全局写入？。原因：这影响企业环境和个人环境的安装风险。 ## 开工前工作上下文 ### 加载顺序 - 先读取 how_to_use.host_ai_instruction，建立安装前判断资产的边界。 - 读取 claim_graph_summary，确认事实来自 Claim/Evidence Graph，而不是 Human Wiki 叙事。 - 再读取 intended_users、capabilities 和 quick_start_candidates，判断用户是否匹配。 - 需要执行具体任务时，优先查 role_skill_index，再查 evidence_index。 - 遇到真实安装、文件修改、网络访问、性能或兼容性问题时，转入 risk_card 和 boundaries.runtime_required。 ### 任务路由 - **AI Skill / Agent 指令资产库**：先基于 role_skill_index / evidence_index 帮用户挑选可用角色、Skill 或工作流。 边界：可做安装前 Prompt 体验。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md`, `lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md`, `lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` Claim：`clm_0001` supported 0.86 - **命令行启动或安装流程**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`README.md` Claim：`clm_0002` supported 0.86 ### 上下文规模 - 文件总数：2947 - 重要文件覆盖：40/2947 - 证据索引条目：83 - 角色 / Skill 条目：3 ### 证据不足时的处理 - **missing_evidence**：说明证据不足，要求用户提供目标文件、README 段落或安装后验证记录；不要补全事实。 - **out_of_scope_request**：说明该任务超出当前 AI Context Pack 证据范围，并建议用户先查看 Human Manual 或真实安装后验证。 - **runtime_request**：给出安装前检查清单和命令来源，但不要替用户执行命令或声称已执行。 - **source_conflict**：同时展示冲突来源，标记为待核实，不要强行选择一个版本。 ## Prompt Recipes ### 适配判断 - 目标：判断这个项目是否适合用户当前任务。 - 预期输出：适配结论、关键理由、证据引用、安装前可预览内容、必须安装后验证内容、下一步建议。 ```text 请基于 crewai 的 AI Context Pack，先问我 3 个必要问题，然后判断它是否适合我的任务。回答必须包含：适合谁、能做什么、不能做什么、是否值得安装、证据来自哪里。所有项目事实必须引用 evidence_refs、source_paths 或 claim_id。 ``` ### 安装前体验 - 目标：让用户在安装前感受核心工作流，同时避免把预览包装成真实能力或营销承诺。 - 预期输出：一段带边界标签的体验剧本、安装后验证清单和谨慎建议；不含真实运行承诺或强营销表述。 ```text 请把 crewai 当作安装前体验资产，而不是已安装工具或真实运行环境。 请严格输出四段： 1. 先问我 3 个必要问题。 2. 给出一段“体验剧本”：用 [安装前可预览]、[必须安装后验证]、[证据不足] 三种标签展示它可能如何引导工作流。 3. 给出安装后验证清单：列出哪些能力只有真实安装、真实宿主加载、真实项目运行后才能确认。 4. 给出谨慎建议：只能说“值得继续研究/试装”“先补充信息后再判断”或“不建议继续”，不得替项目背书。 硬性边界： - 不要声称已经安装、运行、执行测试、修改文件或产生真实结果。 - 不要写“自动适配”“确保通过”“完美适配”“强烈建议安装”等承诺性表达。 - 如果描述安装后的工作方式，必须使用“如果安装成功且宿主正确加载 Skill，它可能会……”这种条件句。 - 体验剧本只能写成“示例台词/假设流程”：使用“可能会询问/可能会建议/可能会展示”，不要写“已写入、已生成、已通过、正在运行、正在生成”。 - Prompt Preview 不负责给安装命令；如用户准备试装，只能提示先阅读 Quick Start 和 Risk Card，并在隔离环境验证。 - 所有项目事实必须来自 supported claim、evidence_refs 或 source_paths；inferred/unverified 只能作风险或待确认项。 ``` ### 角色 / Skill 选择 - 目标：从项目里的角色或 Skill 中挑选最匹配的资产。 - 预期输出：候选角色或 Skill 列表，每项包含适用场景、证据路径、风险边界和是否需要安装后验证。 ```text 请读取 role_skill_index，根据我的目标任务推荐 3-5 个最相关的角色或 Skill。每个推荐都要说明适用场景、可能输出、风险边界和 evidence_refs。 ``` ### 风险预检 - 目标：安装或引入前识别环境、权限、规则冲突和质量风险。 - 预期输出：环境、权限、依赖、许可、宿主冲突、质量风险和未知项的检查清单。 ```text 请基于 risk_card、boundaries 和 quick_start_candidates，给我一份安装前风险预检清单。不要替我执行命令，只说明我应该检查什么、为什么检查、失败会有什么影响。 ``` ### 宿主 AI 开工指令 - 目标：把项目上下文转成一次对话开始前的宿主 AI 指令。 - 预期输出：一段边界明确、证据引用明确、适合复制给宿主 AI 的开工前指令。 ```text 请基于 crewai 的 AI Context Pack，生成一段我可以粘贴给宿主 AI 的开工前指令。这段指令必须遵守 not_runtime=true，不能声称项目已经安装、运行或产生真实结果。 ``` ## 角色 / Skill 索引 - 共索引 3 个角色 / Skill / 项目文档条目。 - **Invalid--Name**（skill）：This skill has an invalid name. 激活提示：当用户任务与“Invalid--Name”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`lib/crewai/tests/skills/fixtures/invalid-name/SKILL.md` - **minimal-skill**（skill）：A minimal skill with only required fields. 激活提示：当用户任务与“minimal-skill”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`lib/crewai/tests/skills/fixtures/minimal-skill/SKILL.md` - **valid-skill**（skill）：A complete test skill with all optional directories. 激活提示：当用户任务与“valid-skill”描述的流程高度相关时，先用它做安装前体验，再决定是否安装。 证据：`lib/crewai/tests/skills/fixtures/valid-skill/SKILL.md` ## 证据索引 - 共索引 83 条证据。 - **Fast and Flexible Multi-Agent Automation Framework**（documentation）：Homepage · Docs · Start Cloud Trial · Blog · Forum 证据：`README.md` - **crewai-cli**（documentation）：CLI for CrewAI — scaffold, run, deploy and manage AI agent crews without installing the full framework. 证据：`lib/cli/README.md` - **AGENTS.md — CrewAI Reference for AI Coding Assistants**（documentation）：AGENTS.md — CrewAI Reference for AI Coding Assistants 证据：`lib/cli/src/crewai_cli/templates/AGENTS.md` - **{{crew name}} Crew**（documentation）：Welcome to the {{crew name}} Crew project, powered by crewAI https://crewai.com . This template is designed to help you set up a multi-agent AI system with ease, leveraging the powerful and flexible framework provided by crewAI. Our goal is to enable your agents to collaborate effectively on complex tasks, maximizing their collective intelligence and capabilities. 证据：`lib/cli/src/crewai_cli/templates/crew/README.md` - **{{crew name}} Crew**（documentation）：Welcome to the {{crew name}} Crew project, powered by crewAI https://crewai.com . This template is designed to help you set up a multi-agent AI system with ease, leveraging the powerful and flexible framework provided by crewAI. Our goal is to enable your agents to collaborate effectively on complex tasks, maximizing their collective intelligence and capabilities. 证据：`lib/cli/src/crewai_cli/templates/flow/README.md` - **{{folder name}}**（documentation）：{{folder name}} is a CrewAI Tool. This template is designed to help you create custom tools to power up your crews. 证据：`lib/cli/src/crewai_cli/templates/tool/README.md` - **crewai-core**（documentation）：Shared utilities used by both crewai and crewai-cli : version lookup, storage paths, user-data helpers, telemetry, and the printer. 证据：`lib/crewai-core/README.md` - **crewai-files**（documentation）：File handling utilities for CrewAI multimodal inputs. 证据：`lib/crewai-files/README.md` - **CrewAI Tools**（documentation）：! Logo of crewAI, two people rowing on a boat ./assets/crewai logo.png 证据：`lib/crewai-tools/README.md` - **BedrockInvokeAgentTool**（documentation）：The BedrockInvokeAgentTool enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows. 证据：`lib/crewai-tools/src/crewai_tools/aws/bedrock/agents/README.md` - **AWS Bedrock Browser Tools**（documentation）：This toolkit provides a set of tools for interacting with web browsers through AWS Bedrock Browser. It enables your CrewAI agents to navigate websites, extract content, click elements, and more. 证据：`lib/crewai-tools/src/crewai_tools/aws/bedrock/browser/README.md` - **AWS Bedrock Code Interpreter Tools**（documentation）：This toolkit provides a set of tools for interacting with the AWS Bedrock Code Interpreter environment. It enables your CrewAI agents to execute code, run shell commands, manage files, and perform computational tasks in a secure, isolated environment. 证据：`lib/crewai-tools/src/crewai_tools/aws/bedrock/code_interpreter/README.md` - **BedrockKBRetrieverTool**（documentation）：The BedrockKBRetrieverTool enables CrewAI agents to retrieve information from Amazon Bedrock Knowledge Bases using natural language queries. 证据：`lib/crewai-tools/src/crewai_tools/aws/bedrock/knowledge_base/README.md` - **AWS S3 Tools**（documentation）：These tools provide a way to interact with Amazon S3, a cloud storage service. 证据：`lib/crewai-tools/src/crewai_tools/aws/s3/README.md` - **AIMind Tool**（documentation）：Minds https://mindsdb.com/minds are AI systems provided by MindsDB https://mindsdb.com/ that work similarly to large language models LLMs but go beyond by answering any question from any data. 证据：`lib/crewai-tools/src/crewai_tools/tools/ai_mind_tool/README.md` - **ApifyActorsTool**（documentation）：Integrate Apify Actors https://apify.com/actors into your CrewAI workflows. 证据：`lib/crewai-tools/src/crewai_tools/tools/apify_actors_tool/README.md` - **ArxivPaperTool**（documentation）：The ArxivPaperTool is a utility for fetching metadata and optionally downloading PDFs of academic papers from the arXiv https://arxiv.org platform using its public API. It supports configurable queries, batch retrieval, PDF downloading, and clean formatting for summaries and metadata. This tool is particularly useful for researchers, students, academic agents, and AI tools performing automated literature reviews. 证据：`lib/crewai-tools/src/crewai_tools/tools/arxiv_paper_tool/README.md` - **BraveSearchTool Documentation**（documentation）：Description This tool is designed to perform a web search for a specified query from a text's content across the internet. It utilizes the Brave Web Search API, which is a REST API to query Brave Search and get back search results from the web. The following sections describe how to curate requests, including parameters and headers, to Brave Web Search API and get a JSON response back. 证据：`lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/README.md` - **BrightData Tools Documentation**（documentation）：A comprehensive suite of CrewAI tools that leverage Bright Data's powerful infrastructure for web scraping, data extraction, and search operations. These tools provide three distinct capabilities: 证据：`lib/crewai-tools/src/crewai_tools/tools/brightdata_tool/README.md` - **BrowserbaseLoadTool**（documentation）：Browserbase https://browserbase.com is a developer platform to reliably run, manage, and monitor headless browsers. 证据：`lib/crewai-tools/src/crewai_tools/tools/browserbase_load_tool/README.md` - **CodeDocsSearchTool**（documentation）：Description The CodeDocsSearchTool is a powerful RAG Retrieval-Augmented Generation tool designed for semantic searches within code documentation. It enables users to efficiently find specific information or topics within code documentation. By providing a docs url during initialization, the tool narrows down the search to that particular documentation site. Alternatively, without a specific docs url , it searches across a wide array of code documentation known or discovered throughout its execution, making it versatile for various documentation search needs. 证据：`lib/crewai-tools/src/crewai_tools/tools/code_docs_search_tool/README.md` - **ComposioTool Documentation**（documentation）：This tools is a wrapper around the composio toolset and gives your agent access to a wide variety of tools from the composio SDK. 证据：`lib/crewai-tools/src/crewai_tools/tools/composio_tool/README.md` - **ContextualAICreateAgentTool**（documentation）：Description This tool is designed to integrate Contextual AI's enterprise-grade RAG agents with CrewAI. This tool enables you to create a new Contextual RAG agent. It uploads your documents to create a datastore and returns the Contextual agent ID and datastore ID. 证据：`lib/crewai-tools/src/crewai_tools/tools/contextualai_create_agent_tool/README.md` - **ContextualAIParseTool**（documentation）：Description This tool is designed to integrate Contextual AI's enterprise-grade document parsing capabilities with CrewAI, enabling you to leverage advanced AI-powered document understanding for complex layouts, tables, and figures. Use this tool to extract structured content from your documents using Contextual AI's powerful document parser. 证据：`lib/crewai-tools/src/crewai_tools/tools/contextualai_parse_tool/README.md` - **ContextualAIQueryTool**（documentation）：Description This tool is designed to integrate Contextual AI's enterprise-grade RAG agents with CrewAI. Run this tool to query existing Contextual AI RAG agents that have been pre-configured with documents and knowledge bases. 证据：`lib/crewai-tools/src/crewai_tools/tools/contextualai_query_tool/README.md` - **ContextualAIRerankTool**（documentation）：Description This tool is designed to integrate Contextual AI's enterprise-grade instruction-following reranker with CrewAI, enabling you to intelligently reorder documents based on relevance and custom criteria. Use this tool to enhance search result quality and document retrieval for RAG systems using Contextual AI's reranking models that understand context and follow specific instructions for optimal document ordering. 证据：`lib/crewai-tools/src/crewai_tools/tools/contextualai_rerank_tool/README.md` - **CouchbaseFTSVectorSearchTool**（documentation）：CouchbaseFTSVectorSearchTool Description Couchbase is a NoSQL database with vector search capabilities. Users can store and query vector embeddings. You can learn more about Couchbase vector search here: https://docs.couchbase.com/cloud/vector-search/vector-search.html 证据：`lib/crewai-tools/src/crewai_tools/tools/couchbase_tool/README.md` - **CSVSearchTool**（documentation）：This tool is used to perform a RAG Retrieval-Augmented Generation search within a CSV file's content. It allows users to semantically search for queries in the content of a specified CSV file. This feature is particularly useful for extracting information from large CSV datasets where traditional search methods might be inefficient. All tools with "Search" in their name, including CSVSearchTool, are RAG tools designed for searching different sources of data. 证据：`lib/crewai-tools/src/crewai_tools/tools/csv_search_tool/README.md` - **DALL-E Tool**（documentation）：Description This tool is used to give the Agent the ability to generate images using the DALL-E model. It is a transformer-based model that generates images from textual descriptions. This tool allows the Agent to generate images based on the text input provided by the user. 证据：`lib/crewai-tools/src/crewai_tools/tools/dalle_tool/README.MD` - **Databricks Query Tool**（documentation）：This tool allows AI agents to execute SQL queries against Databricks workspace tables and retrieve the results. It provides a simple interface for querying data from Databricks tables using SQL, making it easy for agents to access and analyze data stored in Databricks. 证据：`lib/crewai-tools/src/crewai_tools/tools/databricks_query_tool/README.md` - **Daytona Sandbox Tools**（documentation）：Run shell commands, execute Python, and manage files inside a Daytona https://www.daytona.io/ sandbox. Daytona provides isolated, ephemeral compute environments suitable for agent-driven code execution. 证据：`lib/crewai-tools/src/crewai_tools/tools/daytona_sandbox_tool/README.md` - **DirectoryReadTool**（documentation）：Description The DirectoryReadTool is a highly efficient utility designed for the comprehensive listing of directory contents. It recursively navigates through the specified directory, providing users with a detailed enumeration of all files, including those nested within subdirectories. This tool is indispensable for tasks requiring a thorough inventory of directory structures or for validating the organization of files within directories. 证据：`lib/crewai-tools/src/crewai_tools/tools/directory_read_tool/README.md` - **DirectorySearchTool**（documentation）：Description This tool is designed to perform a semantic search for queries within the content of a specified directory. Utilizing the RAG Retrieval-Augmented Generation methodology, it offers a powerful means to semantically navigate through the files of a given directory. The tool can be dynamically set to search any directory specified at runtime or can be pre-configured to search within a specific directory upon initialization. 证据：`lib/crewai-tools/src/crewai_tools/tools/directory_search_tool/README.md` - **DOCXSearchTool**（documentation）：Description The DOCXSearchTool is a RAG tool designed for semantic searching within DOCX documents. It enables users to effectively search and extract relevant information from DOCX files using query-based searches. This tool is invaluable for data analysis, information management, and research tasks, streamlining the process of finding specific information within large document collections. 证据：`lib/crewai-tools/src/crewai_tools/tools/docx_search_tool/README.md` - **E2B Sandbox Tools**（documentation）：Run shell commands, execute Python, and manage files inside an E2B https://e2b.dev/ sandbox. E2B provides isolated, ephemeral VMs suitable for agent-driven code execution, with a Jupyter-style code interpreter for rich Python results. 证据：`lib/crewai-tools/src/crewai_tools/tools/e2b_sandbox_tool/README.md` - **ExaSearchTool Documentation**（documentation）：Description This tool lets CrewAI agents search the web using Exa https://exa.ai/ , the fastest and most accurate web search API. By default the tool returns token-efficient highlights of the most relevant results for any query; you can also opt in to full page content. 证据：`lib/crewai-tools/src/crewai_tools/tools/exa_tools/README.md` - **FileReadTool**（documentation）：The FileReadTool is a versatile component of the crewai tools package, designed to streamline the process of reading and retrieving content from files. It is particularly useful in scenarios such as batch text file processing, runtime configuration file reading, and data importation for analytics. This tool supports various text-based file formats including .txt , .csv , .json , and adapts its functionality based on the file type, for instance, converting JSON content into a Python dictionary for easy use. 证据：`lib/crewai-tools/src/crewai_tools/tools/file_read_tool/README.md` - **FileWriterTool Documentation**（documentation）：Here's the rewritten README for the FileWriterTool : 证据：`lib/crewai-tools/src/crewai_tools/tools/file_writer_tool/README.md` - **📦 FileCompressorTool**（documentation）：The FileCompressorTool is a utility for compressing individual files or entire directories including nested subdirectories into different archive formats, such as .zip or .tar including .tar.gz , .tar.bz2 , and .tar.xz . This tool is useful for archiving logs, documents, datasets, or backups in a compact format, and ensures flexibility in how the archives are created. 证据：`lib/crewai-tools/src/crewai_tools/tools/files_compressor_tool/README.md` - **FirecrawlCrawlWebsiteTool**（documentation）：Firecrawl https://firecrawl.dev is a platform for crawling and convert any website into clean markdown or structured data. 证据：`lib/crewai-tools/src/crewai_tools/tools/firecrawl_crawl_website_tool/README.md` - **FirecrawlScrapeWebsiteTool**（documentation）：Firecrawl https://firecrawl.dev is a platform for crawling and convert any website into clean markdown or structured data. 证据：`lib/crewai-tools/src/crewai_tools/tools/firecrawl_scrape_website_tool/README.md` - **FirecrawlSearchTool**（documentation）：Firecrawl https://firecrawl.dev is a platform for crawling and convert any website into clean markdown or structured data. 证据：`lib/crewai-tools/src/crewai_tools/tools/firecrawl_search_tool/README.md` - **GenerateCrewaiAutomationTool**（documentation）：The GenerateCrewaiAutomationTool integrates with CrewAI Studio API to generate complete CrewAI automations from natural language descriptions. It translates high-level requirements into functional CrewAI implementations and returns direct links to Studio projects. 证据：`lib/crewai-tools/src/crewai_tools/tools/generate_crewai_automation_tool/README.md` - **GithubSearchTool**（documentation）：Description The GithubSearchTool is a Retrieval Augmented Generation RAG tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub. 证据：`lib/crewai-tools/src/crewai_tools/tools/github_search_tool/README.md` - **HyperbrowserLoadTool**（documentation）：Hyperbrowser https://hyperbrowser.ai is a platform for running and scaling headless browsers. It lets you launch and manage browser sessions at scale and provides easy to use solutions for any webscraping needs, such as scraping a single page or crawling an entire site. 证据：`lib/crewai-tools/src/crewai_tools/tools/hyperbrowser_load_tool/README.md` - **InvokeCrewAIAutomationTool**（documentation）：The InvokeCrewAIAutomationTool provides CrewAI Platform API integration with external crew services. This tool allows you to invoke and interact with CrewAI Platform automations from within your CrewAI agents, enabling seamless integration between different crew workflows. 证据：`lib/crewai-tools/src/crewai_tools/tools/invoke_crewai_automation_tool/README.md` - **JinaScrapeWebsiteTool**（documentation）：Description A tool designed to extract and read the content of a specified website by using Jina.ai reader. It is capable of handling various types of web pages by making HTTP requests and parsing the received HTML content. This tool can be particularly useful for web scraping tasks, data collection, or extracting specific information from websites. 证据：`lib/crewai-tools/src/crewai_tools/tools/jina_scrape_website_tool/README.md` - **JSONSearchTool**（documentation）：Description This tool is used to perform a RAG search within a JSON file's content. It allows users to initiate a search with a specific JSON path, focusing the search operation within that particular JSON file. If the path is provided at initialization, the tool restricts its search scope to the specified JSON file, thereby enhancing the precision of search results. 证据：`lib/crewai-tools/src/crewai_tools/tools/json_search_tool/README.md` - **Linkup Search Tool**（documentation）：The LinkupSearchTool is a tool designed for integration with the CrewAI framework. It provides the ability to query the Linkup API for contextual information and retrieve structured results. This tool is ideal for enriching workflows with up-to-date and reliable information from Linkup. 证据：`lib/crewai-tools/src/crewai_tools/tools/linkup/README.md` - **LlamaIndexTool Documentation**（documentation）：Description This tool is designed to be a general wrapper around LlamaIndex tools and query engines, enabling you to leverage LlamaIndex resources in terms of RAG/agentic pipelines as tools to plug into CrewAI agents. 证据：`lib/crewai-tools/src/crewai_tools/tools/llamaindex_tool/README.md` - **MDXSearchTool**（documentation）：Description The MDX Search Tool, a key component of the crewai tools package, is designed for advanced market data extraction, offering invaluable support to researchers and analysts requiring immediate market insights in the AI sector. With its ability to interface with various data sources and tools, it streamlines the process of acquiring, reading, and organizing market data efficiently. 证据：`lib/crewai-tools/src/crewai_tools/tools/mdx_search_tool/README.md` - **MergeAgentHandlerTool Documentation**（documentation）：MergeAgentHandlerTool Documentation 证据：`lib/crewai-tools/src/crewai_tools/tools/merge_agent_handler_tool/README.md` - **MongoDBVectorSearchTool**（documentation）：Description This tool is specifically crafted for conducting vector searches within docs within a MongoDB database. Use this tool to find semantically similar docs to a given query. 证据：`lib/crewai-tools/src/crewai_tools/tools/mongodb_vector_search_tool/README.md` - **MultiOnTool Documentation**（documentation）：Description The MultiOnTool, integrated within the crewai tools package, empowers CrewAI agents with the capability to navigate and interact with the web through natural language instructions. Leveraging the Multion API, this tool facilitates seamless web browsing, making it an essential asset for projects requiring dynamic web data interaction. 证据：`lib/crewai-tools/src/crewai_tools/tools/multion_tool/README.md` - **MySQLSearchTool**（documentation）：Description This tool is designed to facilitate semantic searches within MySQL database tables. Leveraging the RAG Retrieve and Generate technology, the MySQLSearchTool provides users with an efficient means of querying database table content, specifically tailored for MySQL databases. It simplifies the process of finding relevant data through semantic search queries, making it an invaluable resource for users needing to perform advanced queries on extensive datasets within a MySQL database. 证据：`lib/crewai-tools/src/crewai_tools/tools/mysql_search_tool/README.md` - **NL2SQL Tool**（documentation）：This tool is used to convert natural language to SQL queries. When passed to the agent it will generate queries and then use them to interact with the database. 证据：`lib/crewai-tools/src/crewai_tools/tools/nl2sql/README.md` - **OCR Tool**（documentation）：This tool performs Optical Character Recognition OCR on images using supported LLMs. It can extract text from both local image files and images available via URLs. The tool leverages the LLM's vision capabilities to provide accurate text extraction from images. 证据：`lib/crewai-tools/src/crewai_tools/tools/ocr_tool/README.md` - **OxylabsAmazonProductScraperTool**（documentation）：Scrape any website with OxylabsAmazonProductScraperTool 证据：`lib/crewai-tools/src/crewai_tools/tools/oxylabs_amazon_product_scraper_tool/README.md` - **OxylabsAmazonSearchScraperTool**（documentation）：Scrape any website with OxylabsAmazonSearchScraperTool 证据：`lib/crewai-tools/src/crewai_tools/tools/oxylabs_amazon_search_scraper_tool/README.md` - **OxylabsGoogleSearchScraperTool**（documentation）：Scrape any website with OxylabsGoogleSearchScraperTool 证据：`lib/crewai-tools/src/crewai_tools/tools/oxylabs_google_search_scraper_tool/README.md` - 其余 23 条证据见 `AI_CONTEXT_PACK.json` 或 `EVIDENCE_INDEX.json`。 ## 宿主 AI 必须遵守的规则 - **把本资产当作开工前上下文，而不是运行环境。**：AI Context Pack 只包含证据化项目理解，不包含目标项目的可执行状态。 证据：`README.md`, `lib/cli/README.md`, `lib/cli/src/crewai_cli/templates/AGENTS.md` - **回答用户时区分可预览内容与必须安装后才能验证的内容。**：安装前体验的消费者价值来自降低误装和误判，而不是伪装成真实运行。 证据：`README.md`, `lib/cli/README.md`, `lib/cli/src/crewai_cli/templates/AGENTS.md` ## 用户开工前应该回答的问题 - 你准备在哪个宿主 AI 或本地环境中使用它？ - 你只是想先体验工作流，还是准备真实安装？ - 你最在意的是安装成本、输出质量、还是和现有规则的冲突？ ## 验收标准 - 所有能力声明都能回指到 evidence_refs 中的文件路径。 - AI_CONTEXT_PACK.md 没有把预览包装成真实运行。 - 用户能在 3 分钟内看懂适合谁、能做什么、如何开始和风险边界。 --- ## Doramagic Context Augmentation 下面内容用于强化 Repomix/AI Context Pack 主体。Human Manual 只提供阅读骨架；踩坑日志会被转成宿主 AI 必须遵守的工作约束。 ## Human Manual 骨架 使用规则：这里只是项目阅读路线和显著性信号，不是事实权威。具体事实仍必须回到 repo evidence / Claim Graph。 宿主 AI 硬性规则： - 不得把页标题、章节顺序、摘要或 importance 当作项目事实证据。 - 解释 Human Manual 骨架时，必须明确说它只是阅读路线/显著性信号。 - 能力、安装、兼容性、运行状态和风险判断必须引用 repo evidence、source path 或 Claim Graph。 - **crewAI 简介与快速入门**：importance `high` - source_paths: README.md, lib/crewai/README.md, lib/cli/src/crewai_cli/create_crew.py, lib/cli/src/crewai_cli/create_flow.py - **系统架构与模块设计**：importance `high` - source_paths: lib/crewai/pyproject.toml, lib/crewai/src/crewai/__init__.py, lib/crewai/src/crewai/crew.py, lib/crewai/src/crewai/flow/flow.py, lib/cli/pyproject.toml - **Agent 智能体系统**：importance `high` - source_paths: lib/crewai/src/crewai/agents/agent_builder/base_agent.py, lib/crewai/src/crewai/agent/core.py, lib/crewai/src/crewai/agents/crew_agent_executor.py, lib/crewai/src/crewai/agents/step_executor.py, lib/crewai/src/crewai/tools/agent_tools/agent_tools.py - **Crew 智能体团队**：importance `high` - source_paths: lib/crewai/src/crewai/crew.py, lib/crewai/src/crewai/process.py, lib/crewai/src/crewai/crews/crew_output.py, lib/crewai/src/crewai/agents/tools_handler.py, lib/cli/src/crewai_cli/templates/crew/crew.py - **Flow 事件驱动工作流**：importance `high` - source_paths: lib/crewai/src/crewai/flow/flow.py, lib/crewai/src/crewai/flow/flow_config.py, lib/crewai/src/crewai/flow/flow_context.py, lib/crewai/src/crewai/flow/persistence/decorators.py, lib/crewai/src/crewai/flow/persistence/sqlite.py - **Task 任务系统**：importance `high` - source_paths: lib/crewai/src/crewai/task.py, lib/crewai/src/crewai/tasks/__init__.py, lib/crewai/src/crewai/tasks/conditional_task.py, lib/crewai/src/crewai/tasks/task_output.py, lib/crewai/src/crewai/tasks/llm_guardrail.py - **LLM 集成与提供者**：importance `high` - source_paths: lib/crewai/src/crewai/llm.py, lib/crewai/src/crewai/llms/base_llm.py, lib/crewai/src/crewai/llms/providers/openai/completion.py, lib/crewai/src/crewai/llms/providers/anthropic/completion.py, lib/crewai/src/crewai/llms/providers/bedrock/completion.py - **工具系统与 MCP 集成**：importance `high` - source_paths: lib/crewai/src/crewai/tools/base_tool.py, lib/crewai/src/crewai/tools/structured_tool.py, lib/crewai/src/crewai/tools/tool_calling.py, lib/crewai/src/crewai/mcp/__init__.py, lib/crewai/src/crewai/mcp/client.py ## Repo Inspection Evidence / 源码检查证据 - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `ba523f46c06289074b0267ab2689571398c7cc7b` - inspected_files: `pyproject.toml`, `README.md`, `uv.lock`, `docs/enterprise-api.en.yaml`, `docs/reo-tracking.js`, `docs/enterprise-api.pt-BR.yaml`, `docs/enterprise-api.base.yaml`, `docs/index.mdx`, `docs/common-room-tracking.js`, `docs/docs.json`, `docs/enterprise-api.ko.yaml`, `docs/pt-BR/telemetry.mdx`, `docs/pt-BR/index.mdx`, `docs/pt-BR/installation.mdx`, `docs/pt-BR/quickstart.mdx`, `docs/pt-BR/changelog.mdx`, `docs/pt-BR/introduction.mdx`, `docs/pt-BR/skills.mdx`, `docs/ar/telemetry.mdx`, `docs/ar/index.mdx` 宿主 AI 硬性规则： - 没有 repo_clone_verified=true 时，不得声称已经读过源码。 - 没有 repo_inspection_verified=true 时，不得把 README/docs/package 文件判断写成事实。 - 没有 quick_start_verified=true 时，不得声称 Quick Start 已跑通。 ## Doramagic Pitfall Constraints / 踩坑约束 这些规则来自 Doramagic 发现、验证或编译过程中的项目专属坑点。宿主 AI 必须把它们当作工作约束，而不是普通说明文字。 ### Constraint 1: 来源证据：[FEATURE] Implement Process.consensual with a pluggable ConsensusEngine - Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[FEATURE] Implement Process.consensual with a pluggable ConsensusEngine - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_a7c38215ebb04a4fbc6e7c6d2fdb2469 | https://github.com/crewAIInc/crewAI/issues/5708 | 来源讨论提到 python 相关条件，需在安装/试用前复核。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 2: 来源证据：[BUG] Wrong code in document - Trigger: GitHub 社区证据显示该项目存在一个运行相关的待验证问题：[BUG] Wrong code in document - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_390380af45524e959d558b160597b38b | https://github.com/crewAIInc/crewAI/issues/5378 | 来源讨论提到 python 相关条件，需在安装/试用前复核。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 3: 来源证据：[FEATURE] Enhance the document about @persisit - Trigger: GitHub 社区证据显示该项目存在一个运行相关的待验证问题：[FEATURE] Enhance the document about @persisit - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_effef000d4cf47a892f17850aa033610 | https://github.com/crewAIInc/crewAI/issues/5372 | 来源类型 github_issue 暴露的待验证使用条件。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 4: 来源证据：[FEATURE] GuardrailProvider interface for pre-tool-call authorization - Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：[FEATURE] GuardrailProvider interface for pre-tool-call authorization - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能阻塞安装或首次运行。 - Evidence: community_evidence:github | cevd_858a1a8bead2456289d686ec0d2d802c | https://github.com/crewAIInc/crewAI/issues/4877 | 来源讨论提到 python 相关条件，需在安装/试用前复核。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 5: 仓库名和安装名不一致 - Trigger: 仓库名 `crewai` 与安装入口 `skills` 不完全一致。 - Host AI rule: 在 npm/PyPI/GitHub 上确认包名映射和官方 README 说明。 - Why it matters: 用户照着仓库名搜索包或照着包名找仓库时容易走错入口。 - Evidence: identity.distribution | github_repo:710601088 | https://github.com/crewAIInc/crewAI | repo=crewai; install=skills - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 6: 来源证据：1.14.4 - Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：1.14.4 - Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_dcfa2a852812414a82683392c2888795 | https://github.com/crewAIInc/crewAI/releases/tag/1.14.4 | 来源类型 github_release 暴露的待验证使用条件。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 7: 来源证据：1.14.4a1 - Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：1.14.4a1 - Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_0de86b993ffa4d9298726daa189abf49 | https://github.com/crewAIInc/crewAI/releases/tag/1.14.4a1 | 来源类型 github_release 暴露的待验证使用条件。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 8: 来源证据：1.14.5a4 - Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：1.14.5a4 - Host AI rule: 来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_6db6cd94b6ef4bffa23da215458565b4 | https://github.com/crewAIInc/crewAI/releases/tag/1.14.5a4 | 来源类型 github_release 暴露的待验证使用条件。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 9: 来源证据：Scans the client database to extract existing policy details. - Trigger: GitHub 社区证据显示该项目存在一个配置相关的待验证问题：Scans the client database to extract existing policy details. - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_8201c73155314e67801bd0b81ea9820d | https://github.com/crewAIInc/crewAI/issues/5760 | 来源类型 github_issue 暴露的待验证使用条件。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 10: 能力判断依赖假设 - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: 将假设转成下游验证清单。 - Why it matters: 假设不成立时，用户拿不到承诺的能力。 - Evidence: capability.assumptions | github_repo:710601088 | https://github.com/crewAIInc/crewAI | README/documentation is current enough for a first validation pass. - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。