mem0-pin

Pins or unpins a memory to protect it from pruning during dream consolidation. Use when a memory is critical and must never be removed, such as architecture decisions, security constraints, or immutable team conventions.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, actionable skill body with executable code and a clear step sequence. Its main weakness is workflow verification: the confirm step assumes success rather than re-reading the memory to confirm the pin persisted, and there is a minor parameter-name inconsistency between the pin and unpin code.

Suggestions

Add a verification step after update_memory (e.g., re-call get_memory and check the text starts with '[PINNED]') before printing the confirm message, so success is verified rather than assumed.

Fix the parameter-name inconsistency: the pin path uses update_memory(id=...) while the unpin path uses update_memory(memory_id=...) — pick one consistent parameter name so both snippets are copy-paste correct.

For new memories, the get_event_status polling is documented as 'once' — note that event processing may not be complete immediately and retry briefly if the memory ID is not yet available.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, jumping straight to tool calls and executable code; the one rationale line ('append a pin marker… so it travels with the memory') earns its place by justifying a non-obvious design choice.	3 / 3
Actionability	Provides fully executable Python with concrete tool calls and complete parameters (update_memory, add_memory with metadata/infer, get_event_status), copy-paste ready.	3 / 3
Workflow Clarity	Steps 1–4 are clearly sequenced with a confirm checkpoint, but the confirm step prints assumed content rather than re-fetching to verify the pin marker persisted — a validation gap for a content-mutating operation, which caps this at 2 per the destructive-operation guideline.	2 / 3
Progressive Disclosure	A self-contained single-purpose skill with no bundle files and no need for external references, organized into clear sections (Execution steps, Unpin, Output formatting).	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, third-person description that clearly states the capability and provides an explicit 'Use when…' trigger with concrete example scenarios. It is specific, complete, and distinct from other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Pins or unpins a memory to protect it from pruning' — rather than vague abstractions, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (pin/unpin/protect from pruning) and 'when' via an explicit 'Use when…' trigger, the top anchor.	3 / 3
Trigger Term Quality	The 'Use when a memory is critical and must never be removed, such as architecture decisions, security constraints, or immutable team conventions' clause gives natural scenarios a user would actually voice.	3 / 3
Distinctiveness Conflict Risk	A clear niche — durable memory pinning during 'dream consolidation' — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mem0ai/mem0
Path: integrations/mem0-plugin/.opencode-plugin/opencode-skills/mem0-pin/SKILL.md
Commit: b357a5a

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.