memory-triage

Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memory_add. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-mem0 plugin when skills mode is active.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./integrations/openclaw/skills/memory-triage/SKILL.md

Quality

Content

81%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.

The body is highly actionable and workflow-clear: a rigorous gate-based process with validation, safety checks, and concrete copy-paste memory operations. Its main weakness is conciseness — meaningful repetition across sections and duplicated examples inflate the token budget without adding capability.

Suggestions

Remove the duplicated Examples 11 and 12 (each appears twice) and consolidate the material-difference test, which is stated in both the Decision Gate and the Updating Existing Memories sections.

Consider splitting the long 'Worked Examples' and 'What NEVER to Store' blocks into a one-level reference file (e.g., EXAMPLES.md) so SKILL.md stays a lean overview.

Trim restated storage principles that merely rephrase the four gates to reduce token cost without losing guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-organized, but at ~380 lines it carries notable repetition — the material-difference test appears twice, storage principles restate the gate rules, and Examples 11 and 12 are duplicated — placing it at the 'mostly efficient but could be tightened' anchor rather than clearly lean.	3 / 5
Actionability	Fully executable guidance throughout: concrete memory_add calls with facts arrays, categories, and importance values, explicit search→update→delete procedures with IDs, and WRONG/CORRECT pairs covering the common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	A clearly sequenced four-gate decision process with explicit validation checkpoints ('All four gates must pass. If any fails → do nothing'), feedback loops for updates and consolidation, and safety gates (confirm: true, credential scanning) for batch/destructive operations, matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	5 / 5
Progressive Disclosure	Well-structured with clear section headers and all content appropriately inline (no bundle files exist, so no nesting problems), matching 'good structure; most content appropriately placed'. It is not a 5 because the long worked-examples and 'What NEVER to Store' blocks are monolithically inlined where a one-level reference split could aid navigation.	4 / 5
	Total	17 / 20 Passed

Description

58%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.

The description clearly communicates the skill's purpose and concrete actions but lacks an explicit 'Use when...' trigger and natural user-facing trigger phrases, which caps completeness and trigger-term quality. It is specific and reasonably distinct within its niche.

Suggestions

Add an explicit trigger clause such as 'Use when a conversation reveals durable facts worth persisting across sessions (identity, preferences, decisions, configurations, projects, relationships)'.

Include natural trigger synonyms users would actually say (e.g., 'remember', 'recall', 'save this', 'long-term memory') to improve trigger-term coverage.

Move the 'when' guidance from a plugin-load condition to a usage condition so Claude knows when to apply the skill, not just when it is loaded.

Dimension	Reasoning	Score
Specificity	Names the domain (memory protocol) and several concrete actions — 'Evaluate conversations for durable facts worth storing via memory_add', 'Handles identity, preferences, decisions, configurations, rules, projects, and relationships' — with only minor coverage gaps, matching the 'lists several specific actions' anchor.	4 / 5
Completeness	The 'what' is clear (persistent memory protocol that evaluates and stores durable facts), but 'when' is only weakly implied via 'Loaded by the openclaw-mem0 plugin when skills mode is active' rather than an explicit use trigger, so per the guideline a missing 'Use when...' clause caps this at 3.	3 / 5
Trigger Term Quality	Relevant keywords (memory, facts, durable, identity, preferences) are present, but it lacks the natural trigger phrases a user would say and their synonyms, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche (mem0-backed durable long-term memory with specific fact categories), mostly distinct from other skills with only minor overlap risk with general memory/note skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: mem0ai/mem0
Path: integrations/openclaw/skills/memory-triage/SKILL.md
Commit: 39bc023

Reviewed: 3 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.