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

67%

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

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 body is highly actionable and well-sequenced with strong decision gates and feedback loops, but it is over-long for a single file with notable internal repetition and no progressive disclosure of the worked-examples and API reference into bundle files.

Suggestions

De-duplicate Examples 11 and 12 (each appears twice) and consolidate the repeated material-difference/entity-grouping explanations into a single canonical statement.

Move the tool API reference and/or the 12 worked examples into references/ files (e.g., TOOLS.md, EXAMPLES.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Tighten the 'What to Extract' and 'Storage Principles' sections by merging overlapping guidance (e.g., the no-pronouns rule stated in both the CRITICAL and Storage Principles sections).

Dimension	Reasoning	Score
Conciseness	The body is largely useful protocol content without concept filler, but is padded by repetition: the material-difference test and entity-grouping rules are restated multiple times, and Examples 11 and 12 are literally duplicated.	2 / 3
Actionability	Provides concrete, executable tool-call invocations (memory_add, memory_search, memory_update) with WRONG/CORRECT contrasts and copy-paste-ready parameter usage across many worked examples.	3 / 3
Workflow Clarity	A four-gate decision gate gives an explicit sequenced pass/fail workflow, with a safety gate on bulk delete (confirm: true) and feedback loops (search -> update -> delete redundant memories).	3 / 3
Progressive Disclosure	The skill is a single monolithic file with ~60 lines of tool API reference and 12 worked examples all inline; no bundle files exist to offload this detail, so content that should be separate remains inline.	2 / 3
	Total	10 / 12 Passed

Description

57%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 conveys a clear, distinctive niche (durable memory via mem0) and a concrete core action, but it is jargon-heavy and lacks an explicit user-facing trigger clause, leaving 'when to use' only implied.

Suggestions

Add an explicit 'Use when ...' trigger clause naming natural user phrasings (e.g., 'Use when the user states durable facts to remember — identity, preferences, decisions, configurations, or project details').

Replace plugin/internal jargon ('memory_add', 'openclaw-mem0 plugin', 'skills mode') with user-facing terms, or relegate them to a secondary clause.

Surface additional concrete actions beyond 'evaluate and store' (e.g., search, update, and consolidate existing memories) to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the memory domain and one concrete action ('Evaluate conversations for durable facts worth storing via memory_add') plus an enumeration of entity categories, but does not list multiple distinct concrete actions to reach level 3.	2 / 3
Completeness	Clearly states what the skill does, but the only 'when' is a plugin-loading condition ('Loaded by the openclaw-mem0 plugin when skills mode is active') rather than an explicit user-facing trigger; missing 'Use when...' caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some relevant terms (memory, preferences, decisions, identity) but leans on jargon ('mem0', 'memory_add', 'openclaw-mem0 plugin', 'skills mode') and misses common user phrasings like 'remember' or 'recall'.	2 / 3
Distinctiveness Conflict Risk	'Persistent long-term memory protocol powered by mem0' is a clear, narrow niche scoped to durable-fact storage, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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: 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.