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 Use when removing outdated decisions, incorrect memories, sensitive data, or cleaning up after experiments.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

90%

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

93%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.

The body is an efficient, actionable, well-structured workflow with strong validation for a destructive operation. Its only shortfall is the absence of an explicit retry/feedback loop, which keeps workflow clarity just below the top anchor.

Suggestions

Add a brief retry/handling step when a deletion fails (e.g., re-confirm or surface the error before continuing) to close the feedback-loop gap.

Optionally include a short checklist for the batch-'all' path to strengthen workflow clarity for complex cases.

Dimension	Reasoning	Score
Conciseness	The ~70-line body is lean, assumes Claude's competence, and avoids explaining what mem0 or memory deletion is; every line carries executable or guardrail value.	5 / 5
Actionability	Copy-paste ready API calls with concrete filters and top_k, plus a runnable bash command for session_stats.py peek, fully cover the common cases.	5 / 5
Workflow Clarity	A clear 5-step sequence with an explicit confirmation checkpoint and failure reporting satisfies the destructive-operation validation requirement, but there is no formal retry/feedback loop or checklist to reach the top anchor.	4 / 5
Progressive Disclosure	The compact, well-sectioned overview keeps everything inline at overview level and clearly signals the one external script reference (session_stats.py) one level deep, with no inlined bulk that belongs in a separate file.	5 / 5
	Total	19 / 20 Passed

Description

87%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.

The description is strong: it states concrete capabilities, gives explicit 'Use when' trigger guidance, and occupies a distinct niche. The only weakness is a minor specificity gap around bulk deletion.

Suggestions

Mention bulk/'all' deletion in the description to close the specificity gap with the body's 'all' confirmation option.

Add a synonym such as 'erase' or 'purge' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'Deletes memories by search query or memory ID', 'confirmation before removal', 'handles undo of recent additions' — but omits the bulk/'all' delete path the body supports, a minor coverage gap.	4 / 5
Completeness	Explicitly answers both what ('Deletes memories by search query or memory ID with confirmation', 'handles undo of recent additions') and when with concrete trigger phrases — a clear match for the top anchor.	5 / 5
Trigger Term Quality	'Use when removing outdated decisions, incorrect memories, sensitive data, or cleaning up after experiments' provides good natural-term coverage, though synonyms like erase/purge are absent.	4 / 5
Distinctiveness Conflict Risk	A clear memory-deletion niche with distinct triggers ('forget', 'removing outdated decisions', 'sensitive data') yields minimal conflict risk with unrelated skills.	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/mem0-plugin/skills/forget/SKILL.md
Commit: dae67f7

Reviewed: 14 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.