slm-show-patterns

To check captured workflow sequences, extract structured pattern outputs from your memory data. This surfaces active project context and long-term preferences, enabling targeted debugging of memory-based insights.

Yes, extracting learned coding patterns requires SuperLocalMemory V3 with learning features enabled. You must also have access to memory data to generate the structured pattern outputs for auditing.

The best way to audit AI memory for coding identity is to extract and surface learned patterns. This reveals your tech preferences and workflow sequences, helping you recall long-term behaviors before onboarding new tools.

Yes, you can debug memory-based insights by reviewing extracted patterns and active project context. This helps identify what the AI has captured across sessions, enabling targeted debugging of workflow sequences and preferences.

Extracting memory patterns fails without learning features enabled because the Skill relies on SuperLocalMemory V3 to store tech preferences and workflow sequences. Without this underlying data access, structured pattern outputs cannot be generated.