Use when asked to find contradictions or inconsistencies in thinking, or when /contradict is invoked.
Delegate to Gemma via the stepped execution protocol. Claude orchestrates; Gemma executes.
mcp__ollama-agent__gemma_start with:
task: "Vault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md). Find logical tensions, contradictions, or inconsistencies in the vault related to '[argument]' (or across the full vault). Where does Shane contradict himself or hold competing beliefs?"skill: "contradict"context: any relevant context from the current conversationstatus is "running", call mcp__ollama-agent__gemma_continue with session_id; repeat until status is "done" or "error"result, synthesize if needed, and present to ShaneVault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md).
Find logical tensions, contradictions, or inconsistencies in the vault related to '[argument]' (or across the full vault). Where does Shane contradict himself or hold competing beliefs?
Execute the skill directly:
obsidian search query='[argument]' limit=15 via bash; if no argument, run broad searches via bash: obsidian search query='believe' limit=10, obsidian search query='value' limit=10, obsidian search query='decided' limit=10obsidian read file='[note name]' via bash for each, prioritizing notes that state positions or make claims