Agent skill
wiki-query
Query the wiki to answer questions. Searches wiki pages, synthesizes answers with citations, and optionally files valuable answers back as new wiki pages. Use when the user asks a question about the knowledge base.
Install this agent skill to your Project
npx add-skill https://github.com/open-gitagent/gitagent/tree/main/examples/llm-wiki/skills/wiki-query
SKILL.md
Wiki Query
Answer questions by searching and synthesizing from the wiki.
Workflow
Step 1: Search the wiki
- Read
memory/wiki/index.mdto find relevant pages - Use Grep to search for specific terms across
memory/wiki/ - Read the most relevant pages (usually 3-10)
Step 2: Synthesize an answer
- Combine information from multiple wiki pages
- Cite sources: reference both wiki pages and the underlying raw documents
- Note confidence level — distinguish well-sourced claims from inferences
- Flag if the wiki has gaps on this topic
Step 3: Present the answer
Format depends on the question:
- Factual question — direct answer with citations
- Comparison — markdown table comparing entities/concepts
- Overview — structured summary with sections
- Analysis — synthesis with explicit reasoning chain
Step 4: File back (if valuable)
If the answer represents a useful synthesis that doesn't exist as a wiki page:
- Ask the user: "This answer synthesizes information that isn't captured in the wiki yet. Should I file it as a new page?"
- If yes: create a new wiki page in
memory/wiki/ - Update
memory/wiki/index.md - Append to
memory/log.md:## [YYYY-MM-DD] query-filed | Page Title - Question: [original question] - Pages referenced: [list] - New page: memory/wiki/page-name.md
Key Insight
Good answers should not disappear into chat history. A comparison you asked for, an analysis, a connection you discovered — these are valuable wiki content. Filing them back means your explorations compound in the knowledge base just like ingested sources do.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
paper-search
Academic paper search via Google Scholar using Serper API
web-search
Advanced web search using Tavily API for current information retrieval
knowledge-retrieval
Semantic search over ingested documents using RAG (LlamaIndex/ChromaDB or Foundational RAG)
wiki-ingest
Ingest a raw source document into the wiki. Reads the source, extracts key information, creates or updates wiki pages, maintains cross-references, and logs the operation. Use when the user adds a new source or says 'ingest this'.
wiki-lint
Health-check the wiki for contradictions, stale claims, orphan pages, missing cross-references, and knowledge gaps. Use periodically or when the user says 'lint the wiki' or 'check wiki health'.
get-started
Guides installation of gitagent and creation of first agent with scaffolding, configuration, and validation. Use when the user is new to gitagent, asks how to get started, wants to install gitagent, set up their first agent, or says 'how do I start?'
Didn't find tool you were looking for?