write-connector

作者: langchain-ai

Add a new built-in OpenWiki source connector. Use when a user asks to create or implement an OpenWiki connector.

npx skills add https://github.com/langchain-ai/openwiki --skill write-connector

Write An OpenWiki Connector

OpenWiki connectors are built-in TypeScript modules in the OSS repository. Do not create a plugin marketplace, dynamic connector package, or runtime-loaded untrusted connector. Add normal source files and tests.

Prefer Custom MCP For Arbitrary Servers

If the knowledge source already exposes a read-only MCP server (HTTP or stdio), use the built-in custom-mcp connector instead of adding a new ConnectorId:

  • Configure ~/.openwiki/connectors/custom-mcp/config.json with enabled, transport, optional allowedTools, and optional readOnlyOperations.
  • Put secrets in ~/.openwiki/.env and reference them as ${ENV_NAME} in transport headers/env.
  • Agent tools openwiki_list_mcp_tools / openwiki_call_mcp_tool accept custom-mcp.

Add a dedicated built-in connector only when you need provider-specific auth, scoping UI, or deterministic API pulls that MCP cannot express.

Required Shape

  • Add the connector to src/connectors/types.ts and src/connectors/registry.ts.
  • Implement the connector under src/connectors/sources/.ts.
  • The connector must expose a ConnectorRuntime with id, displayName, description, backend, requiredEnv, supportsAgenticDiscovery, and ingest().
  • Ingestion writes raw JSON/manifests under ~/.openwiki/connectors//raw//.
  • State lives in ~/.openwiki/connectors//state.json.
  • Config lives in ~/.openwiki/connectors//config.json.
  • Secrets live in ~/.openwiki/.env and are referenced only by env var name.

Security Rules

  • Never read, print, log, return, or hardcode secret values.
  • Do not store credentials in connector config, raw files, state, logs, or tests.
  • Validate connector IDs and raw file paths so reads and writes stay inside ~/.openwiki/connectors//.
  • Use deterministic ingestion code for credentialed external fetching.
  • If wrapping MCP, treat the MCP server as read-only and call only allowlisted read/dump operations from connector config.
  • Do not let untrusted connector manifests instantiate arbitrary commands or arbitrary network endpoints without explicit built-in code review.
  • For custom-mcp, users configure a reviewed built-in wrapper; still require allowedTools and/or MCP readOnlyHint before agentic tool calls (no mutating-tool heuristics beyond Notion's hosted endpoint).

Ingestion Rules

  • Git/local repos should write compact manifests and let the agent inspect the local repo as the source of truth.
  • Sources with timestamps should store per-stream cursors.
  • Sources with object metadata should store IDs, last edited timestamps, and content hashes.
  • Sources with pagination should store enough state to continue without refetching everything.
  • Raw dumps should preserve source IDs, timestamps, URLs, authors, and enough provenance for citations.

User-Facing Finish

When done, tell the user:

  • which connector files changed,
  • which env vars to set in ~/.openwiki/.env,
  • what config file to create or edit,
  • how to run openwiki personal --update to trigger ingestion,
  • which scopes/permissions the source provider requires.

来自 langchain-ai 的更多技能

langgraph-docs
langchain-ai
访问LangGraph文档,构建有状态代理和多代理工作流。获取官方LangGraph Python文档,涵盖状态机、基于图的代理设计以及人机协同模式。根据查询类型优先提供相关文档:实现指南解答操作问题,概念页面讲解理论,教程提供端到端示例,API参考提供技术细节。自动选择2–4个最相关的文档URL并检索其内容以回答...
official
langgraph-human-in-the-loop
langchain-ai
暂停图执行以进行人工审查、批准或验证,随后根据其输入恢复执行。需要三个组件:检查点存储器(InMemorySaver 或 PostgresSaver)、配置中的线程 ID 以及 JSON 可序列化的中断负载。interrupt(value) 暂停执行并展示数据;Command(resume=value) 恢复执行并将该值返回给暂停的节点。恢复时,interrupt() 之前的所有代码会重新执行,因此副作用必须具有幂等性(使用 upsert 而非 insert)。支持审批工作流,...
official
web-research
langchain-ai
用于处理与网络研究相关的请求;它提供了一种结构化的方法来进行全面的网络研究
official
langchain-oss-primer
langchain-ai
任何LangChain、Deep Agents或LangGraph代理构建项目都请始终从这里开始。在选择其他技能或编写任何内容之前,这是必需的起点。
official
skill-creator
langchain-ai
创建有效技能的指南,通过专业知识、工作流程或工具集成来扩展代理能力。当用户……时使用此技能。
official
social-media
langchain-ai
根据研究内容起草特定平台的社交媒体帖子,并生成配套图片。支持领英帖子(1300字符,专业语气)和推特/X话题(每条推文280字符,采用1/🧵格式)。需在撰写前将研究任务委托给子代理,随后阅读研究结果以确保准确性和相关性。使用generate_social_image工具自动生成引人注目的社交图片,采用粗体高对比度构图,针对小屏幕进行优化...
official
deep-agents-memory
langchain-ai
为Deep Agents提供可插拔的内存与文件后端,支持临时、持久化和混合路由选项。四种后端类型:StateBackend(线程作用域,临时)、StoreBackend(跨会话持久化)、FilesystemBackend(本地开发时真实磁盘访问)和CompositeBackend(将不同路径路由到不同后端)。FilesystemMiddleware提供六种文件操作工具:ls、read_file、write_file、edit_file、glob、grep。CompositeBackend使用最长前缀匹配进行路由...
official
deep-agents-orchestration
langchain-ai
编排子代理,规划多步骤任务,并对敏感操作要求人工审批。通过任务工具将工作委派给专业子代理;自定义子代理支持独立的工具集和系统提示,而默认的“通用”子代理继承主代理配置。使用write_todos规划并跟踪复杂工作流,将任务组织为待处理、进行中和已完成状态;需要thread_id以实现跨调用的持久化。实现...
official