write-connector

by 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
Download ZIPGitHub
15.1k

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.

More skills from langchain-ai

langgraph-docs
langchain-ai
Access LangGraph documentation to build stateful agents and multi-agent workflows. Fetches official LangGraph Python docs covering state machines, graph-based agent design, and human-in-the-loop patterns Prioritizes relevant documentation by query type: implementation guides for how-to questions, concept pages for theory, tutorials for end-to-end examples, and API references for technical details Automatically selects 2–4 most relevant documentation URLs and retrieves their content to answer...
official
langgraph-human-in-the-loop
langchain-ai
Pause graph execution for human review, approval, or validation, then resume with their input. Requires three components: a checkpointer (InMemorySaver or PostgresSaver), a thread ID in config, and JSON-serializable interrupt payloads interrupt(value) pauses and surfaces data; Command(resume=value) resumes and returns that value to the paused node All code before interrupt() re-executes on resume, so side effects must be idempotent (use upsert, not insert) Supports approval workflows,...
official
web-research
langchain-ai
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
official
langchain-oss-primer
langchain-ai
ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any…
official
skill-creator
langchain-ai
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user…
official
social-media
langchain-ai
Drafts platform-specific social media posts with research-backed content and generated companion images. Supports LinkedIn posts (1,300 characters with professional tone) and Twitter/X threads (280 characters per tweet with 1/🧵 format) Requires delegating research to a subagent before writing, then reading findings to ensure accuracy and relevance Generates eye-catching social images automatically using generate_social_image tool with bold, high-contrast compositions optimized for small...
official
deep-agents-memory
langchain-ai
Pluggable memory and file backends for Deep Agents with ephemeral, persistent, and hybrid routing options. Four backend types: StateBackend (thread-scoped, ephemeral), StoreBackend (cross-session persistent), FilesystemBackend (real disk access for local dev), and CompositeBackend (route different paths to different backends) FilesystemMiddleware provides six file operation tools: ls , read_file , write_file , edit_file , glob , grep CompositeBackend uses longest-prefix matching to route...
official
deep-agents-orchestration
langchain-ai
Orchestrate subagents, plan multi-step tasks, and require human approval for sensitive operations. Delegate work to specialized subagents via the task tool; custom subagents support isolated tool sets and system prompts, while the default "general-purpose" subagent inherits main agent configuration Plan and track complex workflows with write_todos , organizing tasks across pending, in-progress, and completed states; requires a thread_id for persistence across invocations Implement...
official