Stats
Actions
Tags
From asi
Retrieves AI-generated wiki structure, topic contents, and answers questions about public GitHub repositories via DeepWiki MCP tools.
How this skill is triggered — by the user, by Claude, or both
Slash command
/asi:deepwiki-mcpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> AI-powered documentation and Q&A for any public GitHub repository
AI-powered documentation and Q&A for any public GitHub repository
Version: 1.0.0 Trit: 0 (Ergodic - coordinates knowledge retrieval) Bundle: research Provider: Cognition (Devin AI) - Official, Free, No Auth Required
DeepWiki MCP provides programmatic access to AI-generated documentation for any public GitHub repository indexed on DeepWiki.com. It enables:
https://mcp.deepwiki.com/
| Protocol | URL | Best For |
|---|---|---|
| SSE | https://mcp.deepwiki.com/sse | Claude, most clients |
| Streamable HTTP | https://mcp.deepwiki.com/mcp | OpenAI, Cloudflare, Amp |
read_wiki_structureGet the documentation topic tree for a GitHub repository.
{
"tool": "read_wiki_structure",
"params": {
"repo_owner": "AlgebraicJulia",
"repo_name": "ACSets.jl"
}
}
Returns: List of documentation topics/sections
read_wiki_contentsRead documentation for a specific topic.
{
"tool": "read_wiki_contents",
"params": {
"repo_owner": "AlgebraicJulia",
"repo_name": "ACSets.jl",
"topic": "Overview"
}
}
Returns: AI-generated documentation content
ask_questionAsk any question about a repository with AI-powered, context-grounded response.
{
"tool": "ask_question",
"params": {
"repo_owner": "AlgebraicJulia",
"repo_name": "Catlab.jl",
"question": "How do wiring diagrams compose?"
}
}
Returns: AI-powered answer with repository context
{
"mcpServers": {
"deepwiki": {
"serverUrl": "https://mcp.deepwiki.com/mcp"
}
}
}
{
"mcpServers": {
"deepwiki": {
"serverUrl": "https://mcp.deepwiki.com/sse"
}
}
}
claude mcp add -s user -t http deepwiki https://mcp.deepwiki.com/mcp
Add to .cursor/mcp.json:
{
"mcpServers": {
"deepwiki": {
"serverUrl": "https://mcp.deepwiki.com/sse"
}
}
}
| Trit | Skill | Role |
|---|---|---|
| -1 | hatchery-papers | Validates academic sources |
| 0 | deepwiki-mcp | Coordinates repo knowledge |
| +1 | bmorphism-stars | Generates from starred repos |
Conservation: (-1) + (0) + (+1) = 0 ✓
hatchery-papers (-1) ⊗ deepwiki-mcp (0) ⊗ bmorphism-stars (+1) = 0 ✓ [Research]
persistent-homology (-1) ⊗ deepwiki-mcp (0) ⊗ gay-mcp (+1) = 0 ✓ [Documentation]
sheaf-cohomology (-1) ⊗ deepwiki-mcp (0) ⊗ topos-generate (+1) = 0 ✓ [Knowledge]
three-match (-1) ⊗ deepwiki-mcp (0) ⊗ cider-clojure (+1) = 0 ✓ [Clojure Repos]
polyglot-spi (-1) ⊗ deepwiki-mcp (0) ⊗ gay-mcp (+1) = 0 ✓ [Cross-Lang Docs]
"Read the documentation structure for react/react and explain the hooks system"
"How does Catlab.jl implement natural transformations?"
"Compare how ACSets.jl and Catlab.jl handle graph homomorphisms"
"What topics are covered in AlgebraicJulia/AlgebraicDynamics.jl documentation?"
To make your public GitHub repo available via DeepWiki MCP:
[](https://deepwiki.com/owner/repo)
Both deepwiki-mcp and acsets-algebraic-databases are ERGODIC (trit 0) — they substitute for each other in triads and coordinate knowledge transport.
| Phase | deepwiki-mcp | acsets skill | Verification |
|---|---|---|---|
| Discovery | read_wiki_structure | Schema patterns | ✓ Catlab.jl has 16 topic pages |
| Q&A | ask_question | Formal definitions | ✓ ACSet = Functor C → Set confirmed |
| Apply | Code examples | Specter navigation | ✓ oapply documented in Catlab |
| Debug | "Why does X fail?" | Check naturality | ✓ HomSearch uses BacktrackingSearch |
From DeepWiki ask_question("AlgebraicJulia/Catlab.jl", "How do ACSets work..."):
| DeepWiki Response | ACSets Skill | Match |
|---|---|---|
| "ACSet represents a functor from schema to Set" | C-set = Functor X: C → Set | ✓ |
| "ACSetFunctor wraps ACSet for functorial view" | ∫G category of elements | ✓ |
| "BacktrackingSearch (CSP-based, MRV heuristic)" | homomorphisms(G, complete_graph(k)) | ✓ |
| "VMSearch (compiled virtual machine)" | Specter zero-overhead navigation | ✓ |
| Repository | DeepWiki Status | Topics |
|---|---|---|
AlgebraicJulia/Catlab.jl | ✅ Indexed | 16 pages (GATs, CSets, HomSearch, WiringDiagrams...) |
AlgebraicJulia/ACSets.jl | ❌ Needs indexing | Visit https://deepwiki.com/AlgebraicJulia/ACSets.jl |
AlgebraicJulia/AlgebraicDynamics.jl | ❌ Needs indexing | Visit https://deepwiki.com/AlgebraicJulia/AlgebraicDynamics.jl |
AlgebraicJulia/StructuredDecompositions.jl | ❌ Needs indexing | Visit https://deepwiki.com/AlgebraicJulia/StructuredDecompositions.jl |
redplanetlabs/agent-o-rama | ✅ Indexed | 28 pages (Rama PStates, Agent Topologies, Tool Calling...) |
discopy/discopy | ✅ Indexed | 23 pages (Monoidal Categories, Quantum Circuits, QNLP...) |
Example 1: ACSets + Catlab.jl
# 1. Query DeepWiki for oapply semantics
mcp__deepwiki__ask_question("AlgebraicJulia/Catlab.jl",
"How does oapply compose undirected wiring diagrams?")
# 2. Apply via ACSets skill patterns
@present SchUWD(FreeSchema) begin
Box::Ob; Port::Ob; Junction::Ob; OuterPort::Ob
box::Hom(Port, Box)
junction::Hom(Port, Junction)
outer_junction::Hom(OuterPort, Junction)
end
# 3. oapply = colimit of component diagram (verified by DeepWiki)
composite = oapply(wiring_diagram, components)
Example 2: DisCoPy for Quantum/Categorical Diagrams
# Query DisCoPy documentation
mcp__deepwiki__ask_question("discopy/discopy",
"How do monoidal categories compose with tensor products?")
# DisCoPy has 23 pages covering:
# - Monoidal, Rigid, Symmetric, Frobenius categories
# - Quantum circuits and gates
# - QNLP (Quantum Natural Language Processing)
# - Tensor network backends
Example 3: Agent-o-rama for Rama Integration
;; Query agent-o-rama patterns
mcp__deepwiki__ask_question("redplanetlabs/agent-o-rama",
"How do PStates store agent invocation state?")
;; 28 pages covering:
;; - Agent Modules and Topology
;; - PStates and Depots storage
;; - Tool Calling Integration
;; - Human-in-the-Loop Workflows
hatchery-papers - Academic paper researchbmorphism-stars - GitHub stars indexlibrarian - Codebase understanding agentexa - Web search MCPacsets-algebraic-databases - ACSet computational patterns (trit 0, substitutes in triads)Skill Name: deepwiki-mcp Type: Repository Documentation / Q&A Trit: 0 (ERGODIC) GF(3): Coordinates knowledge flow Auth: None required (free) Scope: All public GitHub repos indexed on DeepWiki.com Qualified: 2025-12-22 (verified against acsets skill)
This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:
general: 734 citations in bib.duckdbThis skill maps to Cat# = Comod(P) as a bicomodule in the equipment structure:
Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826
The skill participates in triads satisfying:
(-1) + (0) + (+1) ≡ 0 (mod 3)
This ensures compositional coherence in the Cat# equipment structure.
npx claudepluginhub plurigrid/asi --plugin asiGenerates AI-powered wiki documentation for public GitHub repositories to answer questions on architecture, APIs, internals, or library workings without cloning locally.
Analyzes code repositories to generate hierarchical wiki catalogs and onboarding guides for contributors, staff engineers, executives, and more.
Retrieves code context summaries, API docs, and examples from GitHub repos, npm/pip libraries, code searches, and clones using isolated agents.