forget

Deletes memories by search query or memory ID with confirmation before removal. Use when removing outdated decisions, incorrect memories, sensitive data, or cleaning up after experiments. Also handles undo of recent additions.

Quality

100%

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 1-3

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

A well-structured, fully actionable skill body: concrete tool calls with parameters, a clear sequenced workflow with validation checkpoints for a destructive operation, and lean prose that assumes Claude's competence. Progressive disclosure is appropriate for a single self-contained SKILL.md.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept explanations Claude already knows; every block (steps, exact prompts, output templates) earns its place.	3 / 3
Actionability	Provides concrete executable guidance — specific MCP tool calls with exact filter syntax and top_k, a real bash command with plugin-root resolution, and exact confirmation prompts.	3 / 3
Workflow Clarity	Clear 5-step sequence with explicit validation checkpoints for a destructive operation (verify-exists, mandatory confirmation, failure reporting), plus a sub-workflow for undo with empty-state handling.	3 / 3
Progressive Disclosure	No bundle files are provided; the self-contained single-purpose skill is well-organized into Execution and Undo sections with nothing needing to be split out.	3 / 3
	Total	12 / 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 strong, concise description that states concrete capabilities, an explicit 'Use when' trigger, and a distinct niche with no conflict risk. It avoids verbosity and over-claims while covering the what, when, and undo edge case.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Deletes memories by search query or memory ID', 'confirmation before removal', and 'undo of recent additions' — rather than vague abstractions.	3 / 3
Completeness	Explicitly answers what ('Deletes memories by search query or memory ID with confirmation before removal') and when via an explicit 'Use when...' clause.	3 / 3
Trigger Term Quality	Covers natural phrases users would say ('removing outdated decisions, incorrect memories, sensitive data, cleaning up after experiments', 'undo of recent additions') with good scenario coverage.	3 / 3
Distinctiveness Conflict Risk	Clear niche (mem0 memory deletion/undo) with distinct triggers unlikely to collide with other skills; third-person voice is correct.	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/skills/forget/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.