health

Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, add_memory errors occur, MCP connection drops, or to verify the plugin is working correctly.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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 highly actionable, well-sequenced diagnostic skill with executable bash and concrete MCP calls plus per-check validation. The main gap is that failure-recovery fix steps are delegated to Claude rather than specified inline.

Suggestions

Inline concrete remediation steps for each FAIL outcome (e.g., "No API key configured" → set MEM0_API_KEY / CLAUDE_PLUGIN_OPTION_MEM0_API_KEY) instead of instructing Claude to add a Troubleshooting section generically.

Tighten the Session-stats explanatory paragraph to the essential retry hint to lift conciseness toward a 5.

Consider splitting the Extended-mode memory-quality analysis into a referenced file (e.g., QUALITY.md) if the skill grows, to keep the base health check overview lean.

Dimension	Reasoning	Score
Conciseness	The body is lean with copy-paste bash and concrete MCP parameters, avoiding generic concept explanation; a few explanatory lines (session-stats origin note, v3 async note) could be trimmed but mostly earn their place, fitting the efficient-with-minor-trim anchor rather than the every-token-earns-its-place 5.	4 / 5
Actionability	Checks provide fully executable bash snippets and specific MCP call parameters (query, filters, top_k, text, user_id, app_id, metadata, infer), and Check 4 spells out the complete add_memory → get_event_status → extract ID → delete_memory flow, matching the copy-paste-ready top anchor.	5 / 5
Workflow Clarity	"Run ALL checks… Do not stop on the first failure" plus five numbered checks each with explicit PASS/WARN/FAIL checkpoints and a feedback loop in Check 4 give a clear sequence; the score stays at 4 because concrete troubleshooting fix steps are delegated ("add a Troubleshooting section with specific fix steps") rather than specified, a minor recovery-guidance gap.	4 / 5
Progressive Disclosure	No bundle files exist and the single-file body (~155 lines, above the 50-line simple-skill exception) is organized into well-labeled sections (Execution, Checks 1-5, Display, Extended mode), giving good structure with only minor organization gaps; the sizable --deep quality block is reasonably inline for a health skill.	4 / 5
	Total	17 / 20 Passed

Description

87%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, well-scoped description that clearly answers both what it does and when to use it with concrete, natural trigger phrases. Minor room for improvement only in trigger synonym coverage and enumerating additional diagnostic actions.

Dimension	Reasoning	Score
Specificity	"Diagnoses mem0 connectivity, API key validity, and memory read/write functionality" names three concrete diagnostic targets, matching the anchor for several specific actions with minor coverage gaps rather than the 1-2 actions of a 3 or the fully comprehensive multi-action list of a 5.	4 / 5
Completeness	It explicitly states both what ("Diagnoses mem0 connectivity, API key validity, and memory read/write functionality") and when ("Use when memory operations fail…") with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	"memory operations fail, searches return empty, add_memory errors occur, MCP connection drops, or to verify the plugin is working correctly" gives five natural trigger phrases with good coverage, but lacks some common synonyms (e.g., "mem0 not saving", "can't remember") that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	The niche is tightly scoped to mem0 plugin diagnostics with triggers tied to mem0-specific failure modes (MCP connection drops, add_memory errors), giving a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 20 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/health/SKILL.md
Commit: dae67f7

Reviewed: 10 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.