CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-dream

Memory consolidation protocol. Reviews all stored memories, merges duplicates, removes noise and credentials, rewrites unclear entries, and enforces TTL expiration. Use when the user asks to clean up, consolidate, or review their memories. Also triggers automatically after sufficient activity (configurable).

69

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 highly actionable, well-structured consolidation protocol with a clear phased workflow, held back by a missing pre-destruction validation gate and minor filler prose. No bundle files exist, and none are needed for this self-contained skill.

Suggestions

Trim filler such as 'Think of this as compressing raw observations into clean, durable knowledge.' so every line earns its place.

Add an explicit validation checkpoint before destructive/bulk deletes in Phase 3a — e.g., list deletion candidates with counts and confirm before executing memory_delete — to create a verify-then-act feedback loop.

Make the merge feedback loop explicit (update the base, verify the merged memory is self-contained and under 50 words, then delete the redundant entries) rather than leaving the verify step implied.

DimensionReasoningScore

Conciseness

Mostly efficient tool/phase documentation, but it includes unnecessary filler such as 'Think of this as compressing raw observations into clean, durable knowledge.' that could be trimmed; it is tighter than verbose but not fully lean.

2 / 3

Actionability

Provides executable, copy-ready tool calls with required/optional params, concrete thresholds (7 days, 90 days, 50-word cap) and specific category lists — fully concrete guidance rather than vague direction.

3 / 3

Workflow Clarity

Four phases are clearly sequenced with priority ordering, but the workflow performs destructive/bulk deletes without an explicit verify-before-act checkpoint; per the rubric, missing validation for batch/destructive operations caps this at 2.

2 / 3

Progressive Disclosure

A single self-contained, well-sectioned SKILL.md (Available Tools, Phase 1–4, Quality Targets) with no nested or external references; no bundle files are present or needed, so well-organized sections suffice.

3 / 3

Total

10

/

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 description: concrete actions, natural triggers, both what-and-when answered, third-person voice, and a distinct niche. No substantive weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Reviews all stored memories, merges duplicates, removes noise and credentials, rewrites unclear entries, and enforces TTL expiration' — matching the score-3 anchor of several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (consolidation protocol with the enumerated actions) and when ('Use when the user asks to clean up, consolidate, or review their memories'), plus an automatic-trigger note, so it is not capped at 2.

3 / 3

Trigger Term Quality

Natural trigger phrasing ('Use when the user asks to clean up, consolidate, or review their memories') covers the terms a user would actually say; not merely score-2 single-keyword because it lists multiple common variations.

3 / 3

Distinctiveness Conflict Risk

Memory consolidation is a clear niche with distinct triggers unlikely to fire for unrelated skills; uses third-person voice ('Reviews', 'Use when the user asks') with no first/second person.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
mem0ai/mem0
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.