Name: memory-config
Rating: 67.2 (1 reviews)
Author: zilliztech

memory-config

Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.

Quality

82%

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

The canonical home for this skill is memory-config in zilliztech/memsearch

Quality

Content

86%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 high-quality configuration skill: fully executable commands and config blocks, real validation checkpoints, and an exemplary per-platform reference split that was verified against the actual bundle. The only notable costs are repetition of the host-agent disclaimer and 'see your platform file' phrasing, plus inline version-specific notes that could be consolidated.

Suggestions

Consolidate the repeated 'this is MemSearch, not the host agent's memory/config system' statements into the single top-of-file instruction and drop the second occurrence in 'Applying changes'.

Move version-bound behavior ('Since v0.4.11', 'v0.4.11+') into a dedicated 'Compatibility / old versions' section so time-sensitive details don't burden the main flow.

State the change workflow as an explicit numbered sequence (diagnose → choose scope → set → show resolved value → note restart need) so the post-change verification loop is unmistakable.

Dimension	Reasoning	Score
Conciseness	The body is dense and imperative with almost no conceptual padding — every section carries commands, keys, or decision rules. It falls short of lean because the 'this is MemSearch, not the host agent's memory system' disclaimer appears twice, 'see your platform reference file' is repeated roughly ten times, and time-sensitive version notes ('Since v0.4.11', 'v0.4.11+') sit inline rather than in a compatibility/deprecated section.	4 / 5
Actionability	Guidance is fully executable: copy-paste bash for diagnosis ('memsearch config list --resolved', 'memsearch stats', the PyPI version check), complete TOML blocks for all three providers, exact state-file paths ('.memsearch/.index-state.json', '.memsearch/.maintenance-state.json'), and explicit model-resolution and scope rules — the common cases are covered.	5 / 5
Workflow Clarity	The intent-routing → diagnose → apply → verify flow is clear and includes real checkpoints (version check before calling the setup healthy, resolved-config check before calling a field unset, showing the resolved value after changes, degraded/error status interpretation, maintenance last_error inspection). It stays at 4 because the end-to-end sequence is implied by section order rather than laid out as explicit steps, and post-change re-diagnosis is only implied.	4 / 5
Progressive Disclosure	The body is a genuine overview that splits all platform-specific detail (version-check commands, plugin keys, native defaults, restart guidance) into five clearly listed, verified one-level-deep reference files, instructs the agent to read only the one matching its environment, and provides environment markers to disambiguate — navigation is easy and nothing that belongs in a bundle file is inlined.	5 / 5
	Total	18 / 20 Passed

Description

78%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 description with an explicit 'Use when' clause and a rich list of concrete trigger phrases that clearly answers both what and when. Its main weakness is a thin 'what' clause — only two actions — and a few generic memory terms that create minor conflict risk with host-native memory skills.

Suggestions

Expand the 'what' clause with 2-3 more concrete actions (e.g., 'configure provider routing, tune summarization, troubleshoot index health') to lift specificity.

Add the failure-mode phrasings users actually say ('memory not capturing', 'search comes back empty') to the trigger list to reduce overlap ambiguity with host-built-in memory features.

Dimension	Reasoning	Score
Specificity	The 'what' clause names the domain ('MemSearch memory behavior') and exactly two actions ('Diagnose and configure'), matching the 1-2 concrete actions anchor; it does not enumerate the sub-capabilities (summarization, provider routing, maintenance) that the trigger list reveals, so it is not comprehensive enough for 4.	3 / 5
Completeness	It explicitly answers both questions: 'Diagnose and configure MemSearch memory behavior' (what) and 'Use when the user asks about...' followed by an enumerated list of concrete trigger phrases (when), matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural phrases like 'MemSearch configuration', 'plugin summarization', 'PROJECT.md/USER.md maintenance', 'index health', 'provider routing', and 'migration/compatibility questions' give good coverage, but common user variations such as 'memory not capturing', 'search returns nothing', or 'recall' are absent, keeping it below the comprehensive-synonyms anchor.	4 / 5
Distinctiveness Conflict Risk	The named MemSearch niche and specific artifacts (PROJECT.md/USER.md, plugin summarization) make it mostly distinct, but generic terms like 'memory directories' and 'memory behavior' could overlap with a host agent's built-in memory skill — an ambiguity the skill body itself acknowledges — so minor overlap risk remains.	4 / 5
	Total	16 / 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: zilliztech/memsearch
Path: plugins/openclaw/skills/memory-config/SKILL.md
Commit: 2a4652f

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.