forget

Delete specific observations from agentmemory after showing them and getting explicit confirmation. Use when the user says "forget this", "delete memory", "remove that note", or wants to scrub specific data for privacy.

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

96%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.

Excellent body content: lean, fully executable MCP guidance with a validation-gated destructive workflow, an explicit confirmation checkpoint, error-recovery handling, and a final checklist. The only minor gap is reliance on an external ../_shared path that sits outside this skill's bundle.

Suggestions

Inline a one-line fallback for when ../_shared/TROUBLESHOOTING.md is unavailable (e.g., check MCP server connection) so the troubleshooting path does not depend on a file outside the skill's directory.

Consider trimming the "See also" section or folding it into the intro, since the body already slightly exceeds the concise single-file ideal.

Dimension	Reasoning	Score
Conciseness	Every section earns its place: a four-line quick start, a terse six-step workflow, a two-sentence "Why", anti-patterns, and a checklist. There is no explanation of concepts Claude already knows and nothing to trim.	5 / 5
Actionability	Copy-paste-ready MCP calls with parameters, types, and defaults ("memoryIds" array or comma-separated string, reason "default `plugin skill request`") plus expected output cover the common cases completely.	5 / 5
Workflow Clarity	The destructive-operation cap is not triggered: validation is explicit (show matches, require an explicit yes, "Do not proceed on silence or a vague 'sure, whatever'"), with a checklist and an error-recovery loop (a count of 0 means the ids did not exist; say so).	5 / 5
Progressive Disclosure	A well-organized, self-contained body with clearly signaled one-level-deep references ("../_shared/TROUBLESHOOTING.md", See also). The body exceeds the under-50-line simple-skill exception and the external reference points outside the bundle where its existence cannot be confirmed, leaving a minor organization gap.	4 / 5
	Total	19 / 20 Passed

Description

91%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 strong description: concrete third-person actions paired with an explicit, natural-language trigger clause covering multiple user phrasings. The only weakness is slight trigger overlap with closely related memory-management skills and scope details (lessons, whole sessions) left to the body.

Suggestions

Add a disambiguating phrase such as "not for lessons or sessions" or "the undo of remember" to reduce overlap with sibling memory skills.

Optionally mention whole-session or lesson deletion scope in the description so users know the full range of deletion supported.

Dimension	Reasoning	Score
Specificity	"Delete specific observations from agentmemory after showing them and getting explicit confirmation" names the domain and several concrete actions (show, confirm, delete), but coverage has minor gaps — lesson and session-level deletion scope appear only in the body, not the description.	4 / 5
Completeness	It explicitly answers both what ("Delete specific observations from agentmemory after showing them and getting explicit confirmation") and when ("Use when the user says..."), with concrete trigger phrases — a direct match to the anchor-5 example.	5 / 5
Trigger Term Quality	"forget this", "delete memory", "remove that note", and "scrub specific data for privacy" are natural user phrasings with multiple synonyms, comprehensively covering how a user would ask for this.	5 / 5
Distinctiveness Conflict Risk	The niche is clear (agentmemory deletion, confirmation-gated), but "delete memory" carries minor overlap risk with closely related sibling memory skills such as remember and recall; it is still mostly distinct.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rohitg00/agentmemory
Path: plugin/skills/forget/SKILL.md
Commit: c314c7b

Reviewed: 4 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.