forget

Delete the Mem0 memories stored for this repository and this user. Use when the user asks to forget, clear, wipe, or delete memories.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-5

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

An exemplary short, destructive-operation skill: executable command, explicit confirmation gate, result reporting, and clearly stated variant handling, all with no padding. It appropriately treats the destructive risk with validation rather than omitting it.

Dimension	Reasoning	Score
Conciseness	Lean and efficient; it assumes Claude's competence and avoids explaining concepts Claude already knows. Every line is actionable instruction or a project-specific behavioral rule that earns its place.	5 / 5
Actionability	Provides a fully executable, copy-paste-ready command with exact flags and concrete guidance for the local-only and project-memory variants. Specific examples cover the common cases.	5 / 5
Workflow Clarity	Clear sequence with explicit validation: explain scope, gate on user confirmation before adding '--yes', run, then report what was deleted. The destructive-operation cap at 3 does not apply because validation checkpoints are present, and the single-command skill is unambiguous.	5 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, and well-organized with a clear heading — meeting the simple-skill exception for a top score.	5 / 5
	Total	20 / 20 Passed

Description

90%Weight 40%Scale 1-5

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, well-targeted description that clearly states both the capability and its triggers with strong synonym coverage. Its only gap is action breadth — it names a single action (delete) rather than a fuller set.

Dimension	Reasoning	Score
Specificity	Names the domain ('Mem0 memories') and one concrete action ('Delete'), scoped to repository and user, but lists only a single action rather than several. It is not a 4 because there is no set of multiple specific actions, only 'Delete'.	3 / 5
Completeness	Explicitly answers both 'what' ('Delete the Mem0 memories stored for this repository and this user') and 'when' ('Use when the user asks to forget, clear, wipe, or delete memories') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'forget, clear, wipe, or delete memories' provides comprehensive coverage of natural synonyms a user would actually say. It is not below 5 because the synonym set is thorough for this domain.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Mem0 memories for a specific repository/user) with distinct trigger verbs, minimizing overlap with other skills. It is not below 5 because the scope is unambiguous.	5 / 5
	Total	18 / 20 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/codex-plugin/skills/forget/SKILL.md
Commit: 0df3e4b

Reviewed: 2 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.