Distill Memory
- 694 installs
- 148 repo stars
- Updated August 3, 2026
- nowledge-co/community
distill-memory is a Claude Code skill that proactively captures decisions, procedures, lessons, and context from agent conversations into a searchable personal knowledge base for developers who need durable memory across
About
distill-memory is a community skill from nowledge-co/community that saves high-value insights from agent conversations without waiting for explicit requests. It detects breakthrough moments such as resolved debugging sessions, design decisions with trade-off rationale, and research conclusions after comparing multiple approaches, then suggests distillation when the conversation produces durable facts, preferences, plans, procedures, or learnings. Developers reach for distill-memory when long-running agent projects lose context between sessions and repeated explanations waste time. The skill emphasizes moment detection over routine logging, targeting searchable personal knowledge that preserves blocking resolutions and architectural choices for future agent invocations.
- Proactive capture of breakthrough moments instead of waiting to be asked
- Distinguishes new memories (add) from refinements (update) to prevent duplicates
- Structured saves using unit-type (decision, procedure, learning, preference, event), labels, and importance scores
- Focuses exclusively on atomic, standalone memories with strong titles and clear meaning
- Explicit end-of-task review to decide whether to add or update durable memories
Distill Memory by the numbers
- 694 all-time installs (skills.sh)
- +16 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #611 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/nowledge-co/community --skill distill-memoryAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 694 |
|---|---|
| repo stars | ★ 148 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 3, 2026 |
| Repository | nowledge-co/community ↗ |
How do agents save decisions to a knowledge base?
Proactively capture decisions, procedures, lessons, and context from agent conversations into a searchable personal knowledge base.
Who is it for?
Developers running long-lived Claude or Cursor agent sessions who need proactive capture of debugging breakthroughs and design decisions.
Skip if: Developers who only need ephemeral chat history or formal ticket tracking in Jira should skip distill-memory for those systems.
When should I use this skill?
Trigger when a conversation resolves a blocker, records a design decision, or concludes multi-approach research worth preserving.
What you get
Searchable memory entries for decisions, procedures, lessons, preferences, and resolved blocking issues
- Memory entries
- Decision records
- Procedure and lesson notes
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 Suggest (Moment Detection)
Breakthrough: Extended debugging resolves, user relief ("Finally!", "Aha!"), root cause found
Decision: Compared options, chose with rationale, trade-off resolved
Research: Investigated multiple approaches, conclusion reached, optimal path determined
Twist: Unexpected cause-effect, counterintuitive solution, assumption challenged
Lesson: "Next time do X", preventive measure, pattern recognized
Skip: Routine fixes, work in progress, simple Q&A, generic info
Memory Quality
Good (atomic + actionable):
- "React hooks cleanup must return function. Caused leaks."
- "PostgreSQL over MongoDB: ACID needed for transactions."
Poor: Vague "Fixed bugs", conversation transcript
Tool Usage
Use nmem CLI to create memories:
nmem m add "Insight + context for future use" \
-t "Searchable title (50-60 chars)" \
-i 0.8Add --unit-type fact|preference|decision|plan|procedure|learning|context|event when the type is clear.
If an existing memory already captures the same decision, workflow, or preference and the new information refines it, update that memory instead of creating a duplicate:
nmem m update <id> -t "Updated title"Content: Outcome/insight focus, include "why", enough context
Importance: 0.8-1.0 major | 0.5-0.7 useful | 0.3-0.4 minor
Note: For programmatic use, add --json flag to get JSON response
Examples:
# High-value insight
nmem m add "React hooks cleanup must return function. Caused memory leaks in event listeners." \
-t "React Hooks Cleanup Pattern" \
-i 0.9
# Decision with context
nmem m add "Chose PostgreSQL over MongoDB for ACID compliance and complex queries" \
-t "Database: PostgreSQL" \
-i 0.9Suggestion
Timing: After resolution/decision, when user pauses
Pattern: "This [type] seems valuable - [essence]. Distill into memory?"
Frequency: 1-3 per session typical, quality over quantity
Troubleshooting
If nmem is not in PATH: pip install nmem-cli, or on Arch Linux yay -S nmem-cli / paru -S nmem-cli
For remote servers: run nmem config client set url https://... and nmem config client set api-key ... once on this machine.
Run /status to check server connection.
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kFAQ
What moments does distill-memory detect for saving?
distill-memory detects breakthrough debugging resolutions, design decisions with compared options and rationale, and research conclusions after investigating multiple approaches. It also captures durable facts, preferences, plans, procedures, and important context from agent conv
Does distill-memory wait for explicit save requests?
distill-memory proactively suggests distillation at valuable moments instead of waiting to be asked. The skill targets high-value insights that save future time, not routine operational chatter, and writes them into a searchable personal knowledge base.
Is Distill Memory safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.