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 core preferences, important decisions, or immutable personal facts.

Quality

81%

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 compact, highly actionable skill body with exact tool-call specifications and clean sectioning. Its only real weakness is workflow safety: the original memory is deleted before any confirmation that the pinned replacement succeeded.

Suggestions

Add a validation checkpoint in Step 2: after `action="add"` of the pinned memory, confirm the add succeeded (e.g. re-search and verify the `[PINNED]` copy exists) before running `action="delete"` on the original.

Make the destructive ordering explicit in the Unpin flow too — verify the new unpinned memory exists before deleting the pinned version.

Specify error handling if `mem0_memory` search returns no results or multiple matches, so Claude knows how to recover rather than guessing.

Dimension	Reasoning	Score
Conciseness	The body is lean and every line is actionable instruction; the brief '[PINNED] marker tells the dream consolidation to skip it' explanation is system-specific behavior Claude would not already know, so it earns its place rather than being padding.	3 / 3
Actionability	Gives exact, copy-ready tool invocations with concrete parameters (e.g. `mem0_memory` with `action="search"`, `query=<query>` and `action="add"`, `content="[PINNED] <original memory text>"`), matching the fully-executable score-3 anchor rather than vague or pseudocode guidance.	3 / 3
Workflow Clarity	Steps are clearly sequenced (find, pin, confirm) but the destructive `delete` of the original memory runs in Step 2 with no verification that the pinned copy was created first; per the rubric, missing validation on a destructive operation caps this at 2 rather than 3.	2 / 3
Progressive Disclosure	The skill is under 50 lines, performs a single task, and needs no external references; its well-organized sections (Execution, Step 1-3, Unpin) satisfy the simple-skill allowance for a score of 3.	3 / 3
	Total	11 / 12 Passed

Description

75%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 well-constructed description that clearly answers both what and when with an explicit trigger clause and a distinct niche. It is held back from full marks only by limited action variety and some system-internal jargon in the trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain ('memory') and concrete actions ('Pins or unpins'), but the two verbs are near-synonymous rather than multiple distinct concrete actions, matching the score-2 anchor rather than the multi-action score-3 example.	2 / 3
Completeness	Explicitly states what it does ('Pins or unpins a memory to protect it from pruning') and when to use it via a clear 'Use when...' clause with concrete triggers, matching the score-3 anchor; not 2 because the when-guidance is explicit rather than implied.	3 / 3
Trigger Term Quality	Includes natural phrases ('core preferences, important decisions, or immutable personal facts') but leans on jargon ('dream consolidation', 'pruning') and misses common variations, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (memory pinning for dream-pruning protection) with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	10 / 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/pi-agent-plugin/skills/pin/SKILL.md
Commit: b357a5a

Reviewed: 6 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.