跳到正文
cccskills
免费在 GitHub 公开

write-connector

Build a built-in connector that brings a new information source into OpenWiki. It guides the choice between an existing MCP server connection and custom code, covering authentication, incremental fetching, stored data, and tests.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

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

查看安装方法

适用场景

  • Add a new information source to OpenWiki
  • Decide whether to use an existing read-only MCP server
  • Implement incremental fetching and resumable pagination
  • Review connector credentials and file storage

包含的文件(1)

  • SKILL.md3.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

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/<connector>.ts.
  • The connector must expose a ConnectorRuntime with id, displayName, description, backend, requiredEnv, supportsAgenticDiscovery, and ingest().
  • Ingestion writes raw JSON/manifests under ~/.openwiki/connectors/<id>/raw/<run-id>/.
  • State lives in ~/.openwiki/connectors/<id>/state.json.
  • Config lives in ~/.openwiki/connectors/<id>/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/<id>/.
  • 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.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Add Mermaid diagrams to generated wiki pages to explain request flows, state changes, data relationships, and branching logic. Keep diagrams aligned with inspected source code and repair syntax problems in diagrams degraded during earlier runs.

中文简介正在准备中。当前显示英语简介。

  • Illustrate requests passing between components
  • Show job lifecycles and state transitions
  • Document relationships between data entities
langchain-ai/openwiki1.7万2026年10月19日 更新

openwiki

免费

Search an existing repository OpenWiki to clarify architecture and dependencies, or create and update its documentation. Pages explain system behavior using source evidence, with a resumable workflow that tracks progress one page at a time.

中文简介正在准备中。当前显示英语简介。

  • Look up architecture and dependency behavior in an existing wiki
  • Create repository documentation grounded in source code
  • Update wiki explanations after source changes
langchain-ai/openwiki1.7万2026年10月19日 更新

查看 langchain-ai 的全部技能

报告此技能的问题