← Back to Skills Marketplace
quincygunter

deepwiki

by QuincyGunter · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
83
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install abe-deepwiki
Description
Query GitHub repository documentation, wiki structure, and ask AI-powered questions via SkillBoss API Hub.
README (SKILL.md)

DeepWiki

Use this skill to access documentation for public GitHub repositories via SkillBoss API Hub. You can retrieve repository wiki pages, get structure, and ask complex questions grounded in the repository's documentation. All requests are routed through SkillBoss API Hub using a single API key.

Commands

Ask Question

Ask any question about a GitHub repository and get an AI-powered, context-grounded response.

node ./scripts/deepwiki.js ask \x3Cowner/repo> "your question"

Read Wiki Structure

Get a list of documentation topics for a GitHub repository.

node ./scripts/deepwiki.js structure \x3Cowner/repo>

Read Wiki Contents

View documentation about a specific path in a GitHub repository's wiki.

node ./scripts/deepwiki.js contents \x3Cowner/repo> \x3Cpath>

Examples

Ask about Devin's MCP usage:

node ./scripts/deepwiki.js ask cognitionlabs/devin "How do I use MCP?"

Get the structure for the React docs:

node ./scripts/deepwiki.js structure facebook/react

Setup

Set the following environment variable before running:

export SKILLBOSS_API_KEY=your_skillboss_api_key

Notes

  • Powered by SkillBoss API Hub (https://api.heybossai.com/v1/pilot).
  • Web scraping fetches content from https://deepwiki.com/\x3Cowner>/\x3Crepo>.
  • Works for public repositories only.
  • The ask command uses SkillBoss API Hub's web scraping + LLM chat for AI-powered answers.
Usage Guidance
This skill sends repository documentation to a third-party API (api.heybossai.com) using the SKILLBOSS_API_KEY. Before installing: (1) verify the SkillBoss service and the deepwiki homepage/privacy policy; (2) ensure you supply a minimal-scope API key (do not reuse high-privilege or broadly-scoped credentials); (3) avoid using the skill on repositories containing sensitive data because their contents will be transmitted to the LLM provider; (4) note the registry metadata incorrectly lists no required env vars—confirm the platform will surface the SKILLBOSS_API_KEY requirement; (5) consider testing with a public, non-sensitive repo in an isolated environment first and monitor network calls (or run inside a sandbox). If you need higher assurance, request the publisher correct the registry metadata and provide an auditable privacy/processing statement for data sent to SkillBoss.
Capability Analysis
Type: OpenClaw Skill Name: abe-deepwiki Version: 1.0.0 The skill provides a legitimate interface for querying GitHub repository documentation using the SkillBoss API Hub. The code in `scripts/deepwiki.js` implements standard HTTPS requests to `api.heybossai.com` for scraping and LLM processing, strictly following the functionality described in `SKILL.md`. No evidence of data exfiltration, unauthorized file access, or malicious execution was found.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The name/description state that it queries GitHub documentation via SkillBoss API Hub and the code + SKILL.md implement exactly that: scraping deepwiki.com/<owner>/<repo> and calling https://api.heybossai.com/v1/pilot. The required API key (SKILLBOSS_API_KEY) is appropriate for the stated integration.
Instruction Scope
Runtime instructions and the script stay within the declared purpose: they only call the SkillBoss pilot endpoint to scrape pages and run a chat LLM, and print the returned markdown or answer. The skill does not read local files, other env vars, or unrelated system paths.
Install Mechanism
There is no install spec (instruction-only with a single included Node script). No external archives or installers are downloaded. This is low-risk from an install perspective.
Credentials
The script legitimately requires SKILLBOSS_API_KEY to call SkillBoss. However, the registry metadata at the top of the report claims "Required env vars: none" while SKILL.md and the script require SKILLBOSS_API_KEY — this metadata mismatch should be corrected before trusting automated tooling that relies on registry fields.
Persistence & Privilege
The skill does not request permanent/always-on presence, does not modify other skills or system configs, and does not attempt to escalate privileges. Autonomous invocation is allowed (platform default) and appropriate for this tool.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install abe-deepwiki
  3. After installation, invoke the skill by name or use /abe-deepwiki
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of DeepWiki skill. - Query and retrieve documentation, wiki structure, and specific pages from public GitHub repositories. - Ask AI-powered questions about repositories with responses grounded in their documentation. - All interactions are routed through the SkillBoss API Hub using a single API key. - Supports three main commands: ask questions, get wiki structure, and read wiki contents. - Requires SKILLBOSS_API_KEY environment variable for use.
Metadata
Slug abe-deepwiki
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is deepwiki?

Query GitHub repository documentation, wiki structure, and ask AI-powered questions via SkillBoss API Hub. It is an AI Agent Skill for Claude Code / OpenClaw, with 83 downloads so far.

How do I install deepwiki?

Run "/install abe-deepwiki" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is deepwiki free?

Yes, deepwiki is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does deepwiki support?

deepwiki is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created deepwiki?

It is built and maintained by QuincyGunter (@quincygunter); the current version is v1.0.0.

💬 Comments