deepwiki-ask
通过 DeepWiki MCP 查询仓库信息。支持提问、获取结构、获取文档内容。Query a repository via DeepWiki MCP: ask questions, get structure, get documentation. 用户提供 owner/repo 时触发。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/autoxj/deepwiki-askWhat This Skill Does
The deepwiki-ask skill serves as a sophisticated interface between the OpenClaw AI agent and DeepWiki MCP repositories. It is designed to streamline the information retrieval process for technical documentation and source code repositories. By leveraging this skill, users can interact with remote repositories to extract structured data, get comprehensive answers to specific technical questions, or retrieve detailed documentation pages without manually navigating GitHub or local documentation files. It effectively acts as a research assistant, parsing repository metadata and content into actionable insights.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/autoxj/deepwiki-ask
Ensure your config.json is updated to reflect the desired request_timeout_seconds and request_max_retries for optimal performance based on your network environment.
Use Cases
- Onboarding for New Repositories: Developers can use the structure mode to understand the project architecture and main entry points.
- Technical Research: Ask complex architectural questions about a repository (e.g., "How is the authentication module implemented in this repo?") and receive synthesized explanations.
- Rapid Documentation Access: Quickly retrieve specific READMEs or documentation files using the topic-based content retrieval mode, allowing for hands-free study of project libraries.
Example Prompts
- "@deepwiki-ask what is the main objective of openclaw/core and what are its key components?"
- "@deepwiki-ask show me the directory structure of openclaw/skills so I know how to navigate the codebase."
- "@deepwiki-ask get the content for the 'installation' topic in openclaw/docs to help me set up the dev environment."
Tips & Limitations
- Performance: Requests typically take between 30 to 120 seconds. Patience is advised for large repositories.
- Precision: When using the --topic flag, ensure the topic name matches the document structure found via the --structure mode for the most accurate retrieval.
- Error Handling: If you encounter a network timeout, the tool will attempt retries automatically; however, if a persistent error occurs, verify your connection to the DeepWiki MCP endpoint.
- Encoding: On Windows systems, if you face issues with non-English characters in questions, it is recommended to pipe your question into a UTF-8 text file and point the skill to that file using the
@syntax.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-autoxj-deepwiki-ask": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-read, external-api
Related Skills
gitcode-release-notes
Generate release notes for GitCode repositories from commits (by tag range or since-date), grouped as feat/fix/docs/other, output Markdown for Release pages. 按 tag 区间或日期拉取提交并生成版本发布公告 Markdown。Python 3.7+ standard library only.
skill-everyday
每天抓取 Clawhub 热门技能，深入分析并生成报告。每次执行获取一个未分析过的热门技能，避免重复。
gitcode-pr-audit
Quality audit for merged GitCode PRs: sample by time range or repo list, check compliance (labels, comments, tests, size, etc.), output table. Use when user asks to 抽检/质量检查 已合入的 PR 规范性、多仓库 PR、或 将结果整理成表格. Multi-repo (owner/repo). Python 3.7+ stdlib only.
gitcode
Fetch and query data from GitCode platform via its REST API: repositories, branches, issues, pull requests, commits, tags, users, organizations, search, webhooks, members, releases and more. 查询 GitCode 上的仓库、分支、议题、PR、提交、标签、用户、组织等数据。Python 3.7+ standard library only.
pr-comment-fix
按 GitCode PR 检视意见修改代码。需 GITCODE_TOKEN。Use when 用户要修改 PR 检视意见。