CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

remember

Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is remember in mem0ai/mem0

SKILL.md
Quality
Evals
Security

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.

The body is exemplary: a short, single-purpose instruction skill that conveys exactly what to say and what not to say, with every token carrying non-obvious Mem0-specific information. It correctly leverages the fact that memory extraction reads the visible reply and warns against fabricating storage confirmations.

DimensionReasoningScore

Conciseness

The ~20-line body is lean with zero padding and no explanation of concepts Claude already knows; every sentence carries non-obvious, Mem0-specific facts like "there is no separate write command" and "Your visible reply is what memory extraction reads". This matches anchor 5 ("every token earns its place") and not 4, since there are no over-explanations to trim.

5 / 5

Actionability

The guidance is fully executable for an instruction-only skill: "Restate the fact clearly and completely in your reply, in one or two sentences, including any names, values, or paths it depends on" and a specific user-facing message including the concrete command "/mem0:search". Per the scoring notes, absence of code is not penalized when guidance is this actionable, matching anchor 5.

5 / 5

Workflow Clarity

A numbered two-step sequence (restate the fact, then tell the user how it will be saved) plus an explicit prohibition ("Do not invent a storage confirmation or a memory ID") makes the single task unambiguous. The simple-skill exception applies and no destructive/batch validation cap is triggered, so it matches anchor 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ exist) and no need for external references; the content is well-organized with a title, numbered steps, and a closing caution. Per the judging guideline, this earns anchor 5 ("well-organized sections" suffice for short self-contained skills).

5 / 5

Total

20

/

20

Passed

Description

70%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 solid: it has an explicit, well-phrased trigger clause with natural synonyms and a distinct niche. Its main weakness is the 'what' half — "make sure it is captured well" is abstract and doesn't enumerate the concrete actions the skill actually performs (restate the fact, tell the user how it will be saved).

Suggestions

Enumerate the concrete actions in the description, e.g. "Restate the fact precisely, explain how it will be saved with session memories, and check later with /mem0:search" instead of the abstract "make sure it is captured well".

Add one or two more natural trigger variations such as "keep this in mind" or "don't forget" to broaden keyword coverage.

Specify the mechanism in the 'what' clause (e.g. "Confirm memory-capture requests for Mem0-based session memory") so the capability is concrete rather than implied.

DimensionReasoningScore

Specificity

"Acknowledge a 'remember this' request" is concrete, but the companion action "make sure it is captured well" is abstract, leaving only 1-2 concrete actions with gaps in coverage (restating the fact, /mem0:search are not mentioned). This matches anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive") and not 4, which requires several specific listed actions.

3 / 5

Completeness

Both what ("Acknowledge a 'remember this' request and make sure it is captured well") and an explicit when with concrete trigger phrases are present. The 'what' clause is somewhat vague ("captured well" is undefined), placing it between anchors 4 and 5 rather than clearly matching 5's fully concrete what-and-when.

4 / 5

Trigger Term Quality

"asks to remember, note, or save something for future sessions" provides good natural-keyword coverage with synonyms users would actually say. It falls short of anchor 5 because common variations like "keep this in mind", "don't forget", or "note this down" are missing.

4 / 5

Distinctiveness Conflict Risk

"Use when the user explicitly asks to remember, note, or save something for future sessions" carves a clear niche tied to explicit memory requests, with only minor overlap risk against generic note-taking or session-summary skills. This matches anchor 4 ("Mostly distinct; minor overlap risk with closely related skills").

4 / 5

Total

15

/

20

Passed

Validation

100%

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-agent-plugin/skills/remember/SKILL.md

Reviewed

Table of Contents

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.