Distill Memory

Catches the moments worth remembering across coding sessions: when you finally debug that memory leak, pick PostgreSQL over MongoDB with clear reasoning, or discover a counterintuitive fix. Instead of losing context between conversations, it prompts you to distill decisions and breakthroughs into searchable memories using the nmem CLI. The skill focuses on quality over quantity, aiming for one to three saves per session and skipping routine work. What makes it click is the moment detection: it recognizes relief signals like "Finally!" or pattern shifts that indicate something worth preserving. Memories stay atomic and actionable, not vague summaries or chat transcripts.

skills.sh installs: 731
GitHub stars: 204
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add nowledge-co/community --skill distill-memory --agent claude-code

Installs into .claude/skills of the current project.

Files

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 include:

decisions with rationale ("we chose PostgreSQL because ACID is required")
repeatable procedures or workflows
lessons from debugging, incidents, or root cause analysis
durable preferences or constraints
plans that future sessions will need to resume cleanly
important context that would be lost when the session ends

Skip routine fixes with no generalizable lesson, work in progress that will change, simple Q&A answerable from documentation, and generic information already widely known.

Add vs Update

Use nmem --json m add when the insight is genuinely new.
If an existing memory already captures the same decision, workflow, or preference and the new information refines it, use nmem m update <id> ... instead of creating a duplicate.
At the end of a substantial task, explicitly check whether one durable memory should be added or updated.

SKILL.md on GitHub