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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%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.

The content is highly actionable and the multi-step workflow is clearly sequenced with validation and approval checkpoints. Its main weaknesses are mild redundancy across the analyze, apply, and auto-mode sections and a referenced script that is not part of the bundle.

Suggestions

Consolidate the merge and prune definitions so they appear once (e.g., define candidates in Step 3 and reference them from Step 5 and Auto mode) to reduce repetition.

Either include the referenced scripts/parse_mem0_config.py in the bundle or replace the call with an inline fallback policy table so no path is dangling.

Trim the "IMPORTANT: Execute steps strictly in order" banner since the numbered 1→6 sequence already enforces ordering.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and free of concept padding, but merge/prune definitions recur across Step 3, Step 5, and the Auto mode section, and the ordering warning restates constraints already implied by the numbered sequence — it could be tightened.	2 / 3
Actionability	Fully executable guidance: exact get_memories/delete_memory/add_memory calls with metadata fields, a precise diff format, and a copy-paste bash command with platform PLUGIN_ROOT variables.	3 / 3
Workflow Clarity	Six clearly numbered steps with an explicit ordering directive, early-stop checks for empty/zero-proposal cases, a diff-then-confirm feedback loop before destructive batch deletions, and a lock-file concurrency guard for auto mode.	3 / 3
Progressive Disclosure	Sections are well organized and "See also" links sibling skills, but the body references a scripts/parse_mem0_config.py that does not exist in the bundle (no references/scripts/assets dirs present), so a referenced path is dangling rather than cleanly self-contained.	2 / 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.

The description is exemplary: concrete actions, natural trigger terms, and explicit what-and-when guidance in third person. It is concise, distinct, and would surface naturally when a user needs memory cleanup.

Dimension	Reasoning	Score
Specificity	Names three concrete actions — "merging duplicates, resolving contradictions, and pruning stale entries" — matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (consolidates by merging/resolving/pruning) and when (a "Use when..." clause with multiple concrete triggers), satisfying the highest completeness anchor.	3 / 3
Trigger Term Quality	Natural user phrasing like "memory count is high," "search results feel noisy or repetitive," and "periodic cleanup" covers the realistic ways a user would request this, not just jargon.	3 / 3
Distinctiveness Conflict Risk	It carves a clear memory-consolidation niche with distinct triggers (noisy/repetitive search, periodic cleanup) unlikely to fire for unrelated skills, even though sibling mem0 skills exist.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mem0ai/mem0
Path: integrations/mem0-plugin/skills/dream/SKILL.md
Commit: b357a5a

Reviewed: 7 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.