CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 strong, highly actionable configuration skill: executable diagnostics, complete config examples, built-in error recovery, and excellent progressive disclosure across per-platform reference files. Remaining gains are small — tightening repeated phrases and adding one concrete `config set` example.

DimensionReasoningScore

Conciseness

The body is dense with MemSearch-specific operational detail and avoids explaining concepts Claude already knows; minor redundancy could be trimmed (the "not the host agent's memory/config system" disclaimer appears twice and "see your platform reference file" is repeated about six times).

4 / 5

Actionability

Diagnostics are copy-paste ready (`memsearch config list --resolved`, version-check pipeline, index-state inspection) and the TOML provider examples are complete, but the body never shows a concrete `memsearch config set <key> <value>` invocation, leaving a minor gap.

4 / 5

Workflow Clarity

The diagnose-first, route, apply, verify flow is clear with explicit checkpoints ("show the command, the resolved value, and whether a new session is needed"), error-recovery paths (`status: degraded`/`error`, `.maintenance-state.json` `last_error`), and user-confirmation gates before destructive operations; the sequence is distributed across thematic sections rather than stated as one explicit ordered workflow, keeping it just below the top anchor.

4 / 5

Progressive Disclosure

The body is a clear overview with six verified one-level-deep platform reference files, well-signaled paths, and explicit routing instructions ("Read ONLY the one file matching your current environment") plus environment markers for disambiguation — content is appropriately split and easy to navigate.

5 / 5

Total

17

/

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 well-constructed description with an explicit what/when structure and strong domain-specific trigger coverage. Its main weakness is that the capability statement rests on only two verbs ("diagnose" and "configure"), leaving the breadth of specific actions implied by the trigger list rather than stated.

Suggestions

Expand the capability clause from two verbs to several concrete actions, e.g. "Diagnose, read and change config values, route providers, troubleshoot capture and index health, and maintain PROJECT.md/USER.md".

Add the natural user phrasings for failure modes to the trigger list, such as "memory not being captured", "search/recall returns nothing", or "API key/provider setup".

Sharpen distinctiveness by scoping the generic terms, e.g. "MemSearch memory directories" instead of bare "memory directories", to reduce overlap with the host agent's built-in memory system.

DimensionReasoningScore

Specificity

"Diagnose and configure MemSearch memory behavior" names the domain with exactly two concrete verbs; the rest of the description enumerates trigger topics rather than actions, matching the anchor for 1-2 concrete actions rather than several specific actions.

3 / 5

Completeness

It clearly answers "what" ("Diagnose and configure MemSearch memory behavior") and "when" with an explicit "Use when the user asks about…" clause listing concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural terms are covered ("MemSearch configuration", "plugin summarization", "PROJECT.md/USER.md maintenance", "index health", "provider routing", "prompt files", "migration/compatibility"), but common user phrasings like "search/recall returns nothing", "memory not being captured", or "API key setup" are missing, so it falls just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Most triggers are anchored by the MemSearch brand name giving a clear niche, but generic phrases like "memory directories" and "maintenance" carry minor overlap risk with a host agent's built-in memory/config skill (a conflict the body itself acknowledges), so it is mostly distinct rather than minimally at risk.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.