wiki_asklisted

# LLM Wiki — Knowledge Base Q&A Skill (wiki_ask) > **CLI (read first):** This skill drives the `magi` CLI (MAGI research workspace tool, assumed installed on PATH). If unsure of your surroundings, run `magi sync` first to locate the workspace. For the full syntax of any command: `magi <command> --help`. This skill transforms the agent into a conversational interface for the knowledge base. When the user asks a question, you must intelligently deploy a combination of deterministic search tools to retrieve context and provide a highly rigorous, cited answer. > **Tooling (framework-agnostic):** This skill is written tool-agnostic. Where it says *file-read tool*, use your agent's equivalent (`Read` in Claude Code, `view_file` in Antigravity, `cat`/open elsewhere). Shell commands run via `Bash`/`PowerShell` (Claude Code) or your framework's shell tool. ## Core Rule: Zero Hallucination > **CRITICAL INSTRUCTION**: Do NOT answer questions using your parametric memory. Every factual claim or summary you provide MUST be grounded in the local knowledge base and explicitly cited using Obsidian wikilinks (e.g., `[[Concept Name]]` or `[[Paper Title]]`). ## Execution Flow When tasked with answering a question, follow these strategies depending on the nature of the inquiry: ### Strategy 0: Hybrid Retrieval (start here for most questions) 0. Scope note: `magi search` federates over the current workspace PLUS any enabled globally-registered KBs (results carry a `kb` field / `[kb:name]`