Capture Learnings
Capture and apply accumulated knowledge via structured memory.
Install
npx skills add BuilderIO/agent-native --skill capture-learnings -g -a claude-code -y- Repository
- BuilderIO/agent-native7.6k
- Category
- Engineering
- Updated
- 3d ago
- License
- MIT
- Context cost
- Lightabout 1,278 tokens
- Runs scripts
- No, instructions only
What it does
Capture and apply accumulated knowledge via structured memory. Use when the user gives feedback, shares preferences, corrects a mistake, or when you discover something worth remembering for future conversations.
Capture Learnings
This is background knowledge, not a slash command. Organization learnings and your personal memory index are loaded at the start of every conversation, including Slack/integration turns. Capture durable context proactively when you learn something worth remembering.
How to Read & Write Memories
Memories are stored as resources in the SQL database, not as files on disk.
-
Team/organization knowledge: shared
LEARNINGS.md. Read it first, merge the new fact, then write the full updated file with theresourcestool usingscope: "shared". Shared scope resolves to the active organization; it must never leak to another organization in the same deployment. -
Personal knowledge:
memory/MEMORY.mdplusmemory/<name>.md, written withsave-memory. -
Save a memory:
save-memory --name <name> --type <type> --description "..." --content "..." -
Read a memory:
resource-read --path memory/<name>.md -
Delete a memory:
delete-memory --name <name> -
List all memories:
resource-list --prefix memory/
Memory Types
| Type | Use for |
|---|---|
user | Preferences, role, personal context, contacts |
feedback | Corrections, confirmed approaches, things to avoid or repeat |
project | Ongoing work context, decisions, deadlines, status |
reference | Pointers to external systems, URLs, API details |
When to Capture
Follow the user's personal memory/INSTRUCTIONS.md when deciding what to
preserve or leave out. It is loaded automatically with the user's personal
AGENTS.md instructions.
At the natural stopping point of a meaningful multi-turn task, review the conversation for durable preferences, corrections, decisions, conventions, or project context that would improve a future thread. Save only new, supported facts; completed task details and temporary debugging notes stay in the thread.
