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.

73

Quality

90%

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

88%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.

A thorough, executable consolidation procedure with strong validation gates appropriate to its destructive/batch nature. Conciseness and the single-file structure leave small room for improvement.

Suggestions

Tighten the 3a/3c explanatory prose (e.g., drop or shorten the 'Use PostgreSQL for auth' style asides) to reduce token cost without losing clarity.

Consider moving the detailed Auto mode block into a reference file and summarizing it in SKILL.md to better match the progressive-disclosure overview pattern.

DimensionReasoningScore

Conciseness

Largely efficient with concrete code and formats, but explanatory prose in 3a/3c and restated ordering warnings add minor padding that could be trimmed.

4 / 5

Actionability

Fully executable guidance: complete get_memories/add_memory/delete_memory/search_memories calls with all arguments, an exact diff-report format, and concrete apply-order steps.

5 / 5

Workflow Clarity

Six clearly sequenced steps with explicit validation checkpoints — a diff report and Y/n approval before any mutation, per-conflict resolution, and an auto-mode lock guard with reminder dedup.

5 / 5

Progressive Disclosure

Well-organized into labeled sections (Steps 1–6, Auto mode, See also, Output formatting) with no nested references, though it is a long self-contained file rather than an overview pointing to one-level-deep references.

4 / 5

Total

18

/

20

Passed

Description

92%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, third-person description that pairs three concrete capabilities with explicit use-when triggers. Trigger-term coverage is the only minor gap, lacking a few lay synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'merging duplicates, resolving contradictions, and pruning stale entries' — giving comprehensive coverage of what consolidation does.

5 / 5

Completeness

Explicitly answers both 'what' (consolidates by merging/contradictions/pruning) and 'when' ('Use when memory count is high, search results feel noisy or repetitive, or periodic cleanup is needed').

5 / 5

Trigger Term Quality

Natural triggers like 'memory count is high', 'search results feel noisy or repetitive', and 'periodic cleanup' are present, but a few common synonyms (e.g., 'clean up memories', 'deduplicate') are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (memory consolidation/cleanup) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

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.