stats

Displays memory usage statistics for the current session and project including counts by category, age distribution, and API latency. Use when checking how many memories exist, reviewing session activity, or auditing memory distribution across categories.

Quality

96%

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

92%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 body is lean, highly actionable, and clearly sequenced with error and empty-state handling. Its main weakness is progressive disclosure: a 127-line single file with two modes and no external references could offload the weekly-digest material to a reference file.

Suggestions

Move the 'Weekly digest mode' (W1–W5) into a separate reference file (e.g. WEEKLY-DIGEST.md) and link to it from the main body, so the standard stats flow stays prominent and the file shrinks toward the concise overview the 3-anchor rewards.

Add a one-line validation/confirmation step before W4 overwrites ~/.mem0/weekly-digest.md and appends to digest-history.log (e.g. confirm the computed new-count is non-zero before writing), giving the digest write an explicit checkpoint.

Consider documenting the expected shape of the session_stats.py JSON output inline so the Step 1 'peek' result can be parsed without guessing, since no scripts/ bundle is present to inspect.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable — concrete commands, filters, and display rules — with no generic concept explanations Claude already knows; every line is task-relevant rather than padded.	3 / 3
Actionability	Provides executable bash, exact MCP tool calls with specific filters and parameters, and concrete display templates; placeholders like '<active_user_id>' are runtime substitutions, not pseudocode, so it stays copy-paste ready.	3 / 3
Workflow Clarity	Steps 1–3 and W1–W5 are clearly sequenced with an explicit error fallback ('If the script returns empty or errors, note No session data available and continue') and an empty-state branch (W5), meeting the validation/checkpoint anchor.	3 / 3
Progressive Disclosure	The 127-line file is well-sectioned but entirely inline with no reference files, and the weekly-digest mode could be split out; the over-50-line guidance favors splitting, so it sits at the 'content that should be separate is inline' anchor rather than 3.	2 / 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.

The description is third-person, concrete, and pairs a clear capability statement with an explicit 'Use when' trigger clause covering natural user phrasings. It is distinct to memory statistics and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete metrics/actions — 'counts by category, age distribution, and API latency' — matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers what ('Displays memory usage statistics...') and when ('Use when checking how many memories exist...'), satisfying the both-what-and-when anchor; not 2 because the 'Use when' trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	'checking how many memories exist, reviewing session activity, or auditing memory distribution' are natural phrases a user would say, giving good coverage rather than the partial-variation anchor at 2.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'memory usage statistics for the current session and project' with distinct triggers, giving a clear niche unlikely to fire for unrelated skills.	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/stats/SKILL.md
Commit: b357a5a

Reviewed: 6 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.