Distill Memory

nowledge-co/community/nowledge-mem-cursor-plugin/skills/distill-memory

by nowledge-co1f4d7eb61466dbfc93ce8d7a0a806c4d4a196dd0No licenseListed Oct 9, 2026Updated Oct 9, 2026

Capture durable decisions, lessons, and procedures from Cursor work into atomic memories.

AI-generated overview

Captures durable decisions, lessons, and procedures from agent work sessions into atomic memory entries.

What it does
This skill instructs an agent to proactively save durable facts, preferences, decisions, plans, procedures, learnings, events, and context that arise during work sessions. It defines which items are worth saving, when to add a new memory versus update an existing one, and how to keep memories atomic and standalone with strong titles. It also lists the unit_type values to pass when saving directly.
When to use it
Use it during or after substantial work sessions when a durable decision, repeatable procedure, debugging lesson, preference, constraint, or resumable plan emerges. It is meant to run proactively rather than waiting for an explicit request, while skipping routine fixes, work in progress, simple Q&A, and generic information.
Requirements
Requires access to memory tools such as memory_add and memory_update. Ships no scripts; instructions only.

Distill Memory

Save proactively when the conversation produces a durable fact, preference, decision, plan, procedure, learning, event, or important context. Do not wait to be asked.

When To Save

Good candidates:

  • decisions with rationale
  • repeatable procedures
  • lessons from debugging or incident work
  • durable preferences or constraints
  • plans that future sessions will need to resume

Skip routine fixes, work in progress, simple Q&A, and generic information.

Add vs Update

  • Use memory_add when the insight is genuinely new.
  • If recall already surfaced the same decision, workflow, or preference and the new information refines it, use memory_update instead of creating a duplicate.
  • At the end of substantial work, explicitly review whether one durable memory should be added or updated.

Prefer atomic, standalone memories with strong titles and clear meaning. Focus on what was learned or decided, not routine chatter.

When saving directly, pass unit_type when you know it: fact, preference, decision, plan, procedure, learning, context, or event.

Source and attribution

Source:nowledge-co/communityinnowledge-mem-cursor-plugin/skills/distill-memoryat commit1f4d7eb

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal