CtrlK
BlogDocsLog inGet started
Tessl Logo

mem0-dream

Consolidates stored memories by merging duplicates, resolving contradictions, and pruning stale entries. Use when memory count is high, search results feel noisy or repetitive, or periodic cleanup is needed to maintain memory quality.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%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-engineered, highly actionable consolidation workflow with strong sequencing and validation checkpoints guarding destructive operations. Its only weakness is mild verbosity in a few sections that could be trimmed.

Suggestions

Tighten the 3a near-duplicate heuristic — the cosine-similarity/noun-overlap proxy explanation can be condensed to a one-line rule.

Consider moving the auto-mode reminder-storage logic (the search-then-add_memory block) into a short reference snippet to slim the main flow.

The Output formatting note repeats guidance already implied by the diff format; a one-line reminder would suffice.

DimensionReasoningScore

Conciseness

Mostly efficient and instructional with little concept-explanation fluff, but the ~237-line body includes sections (the elaborate similarity heuristic, the auto-mode reminder logic) that could be tightened further.

2 / 3

Actionability

Provides fully executable calls with concrete parameters — get_memories with filters, delete_memory, add_memory with full metadata, search_memories — plus an exact diff format.

3 / 3

Workflow Clarity

Six steps are explicitly sequenced with a strict-order warning, in-memory analysis before any mutation, a diff checkpoint, and a "Apply? [Y/n]" confirmation/feedback loop guarding destructive deletes.

3 / 3

Progressive Disclosure

No bundle files exist, so the single SKILL.md is scored on organization: clearly headed steps, a See-also section, and no nested/deep references — well-structured and easy to navigate.

3 / 3

Total

11

/

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, third-person description that concretely names three actions and gives explicit, natural trigger conditions. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "merging duplicates, resolving contradictions, and pruning stale entries" — rather than vague language.

3 / 3

Completeness

Explicitly states what it does (consolidation via merge/resolve/prune) and when to use it via a clear "Use when..." clause.

3 / 3

Trigger Term Quality

Natural trigger phrases like "memory count is high", "search results feel noisy or repetitive", and "periodic cleanup" match how a user would actually request this.

3 / 3

Distinctiveness Conflict Risk

The memory-consolidation niche with these triggers is distinct from sibling skills like /mem0-forget and /mem0-status, making misfires unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.