deepwiki
DeepWiki: Codebase Intelligence Data Source
Execute this skill to retrieve structured, AI-grounded codebase understanding from Devin's DeepWiki. Use it as an optional data source when Glob/Grep/Read gives you file contents but not architectural intent, or when QMD doesn't have the repository indexed.
What DeepWiki Provides
DeepWiki indexes GitHub repositories and generates structured documentation — architecture, component relationships, design decisions, API contracts — then exposes it through three MCP tools:
| Tool | Purpose | When to use |
|---|---|---|
read_wiki_structure |
Lists all documentation topics for a repo | Explore what's documented — find the right topic before reading |
read_wiki_contents |
Retrieves documentation for a specific topic | Read architectural intent, component descriptions, design decisions |
ask_question |
Natural-language Q&A grounded in the indexed repo | Get answers that synthesize across multiple parts of the codebase |
vs. Glob/Grep/Read: Those tools give you raw file contents. DeepWiki gives you synthesized understanding — what the code means, not just what it says.
vs. QMD: QMD indexes your local markdown documents (specs, ADRs, docs). DeepWiki indexes the codebase itself and generates documentation from it. Complementary, not overlapping.
More from mikeng-io/agent-skills
perplexity
Optional AI-synthesized web search via Perplexity MCP. Returns AI-grounded answers with inline citations rather than raw search results — best for synthesis-heavy questions, current consensus queries, and cross-validation of research findings. Non-blocking — falls back to other search tools if unavailable.
10brave-search
Optional web search enrichment via Brave Search MCP. Provides web, news, and local search with an independent index (no Google dependency). Invokable standalone or called by deep-research, deep-explorer, or any skill needing web search. Non-blocking — falls back to other search tools if unavailable.
9deep-audit
Multi-agent standards and compliance auditing with pass/fail verdicts. Checks against security, accessibility, code standards, regulatory requirements, and performance benchmarks.
9deep-review
Multi-agent quality improvement review with constructive feedback. Provides suggestions for best practices, code quality, alternatives, and performance optimization.
8deep-research
Generic multi-domain research framework with domain-aware scheduling. Model-agnostic and domain-agnostic - perform comprehensive research on any topic.
8context
Analyze conversation context to classify what is being discussed, detect relevant domains from domain-registry, and determine optimal routing (parallel-workflow vs debate-protocol vs deep-council). Can be invoked directly or called by other skills as a pre-flight step.
7