mem0/mem0-plugin/skills/pin/SKILL.md

name, description

name	description
pin	Pin a memory to protect it from consolidation

Mem0 Pin

Pin a memory to mark it as high-priority and protect from pruning.

Execution

Step 1: Find the memory

The user provides either a search query or memory ID.

If memory ID:

• Call get_memory with the ID.

If search query:

• Call search_memories with the query, filters={"AND": [{"user_id": "<id>"}, {"app_id": "<pid>"}]}, top_k=5.
• Show numbered list with content previews.
• Ask: "Which memory to pin? Enter a number."

Step 2: Read current content

Call get_memory with the selected memory ID. Store:

• original_text — the memory's text content
• original_metadata — the existing metadata dict

Step 3: Pin it

3a: Pinning a new memory (full protection)

Use add_memory with immutable: true:

add_memory(
    messages=[{"role": "user", "content": "<text to pin>"}],
    user_id=<user_id>,
    immutable=True,
    metadata={"pinned": True},
)

3b: Pinning an existing memory

Call update_memory with:

• memory_id=<selected_id>
• text=<original_text> (preserve existing content)
• metadata= merge original_metadata with {"pinned": true}

updated_meta = {**original_metadata, "pinned": True}
update_memory(memory_id=<selected_id>, text=<original_text>, metadata=updated_meta)

Important: update_memory requires the text parameter. Passing only metadata may error or wipe content.

Step 4: Confirm

Pinned: "<memory content, first 80 chars>..."
Memory ID: <id>

Unpin

If the user says "unpin":

1. Call get_memory to read current content and metadata.
2. Set metadata.pinned = false:

   updated_meta = {**original_metadata, "pinned": False}
   update_memory(memory_id=<id>, text=<original_text>, metadata=updated_meta)
   

3. Print: Unpinned: "<content>..."