CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-config

Diagnose and configure MemSearch memory behavior for the Claude Code plugin. 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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable, well-structured configuration skill with concrete commands and config examples throughout. Its main weaknesses are a long monolithic body that could offload some detail to reference files and the absence of an explicit validation feedback loop for changes.

Suggestions

Move the per-platform plugin update procedures (Codex/Claude Code/OpenClaw/OpenCode) into a references/ file and link to it, keeping only a short pointer inline to improve progressive disclosure.

Add an explicit validate-then-retry step after `memsearch config set` (e.g. re-run `memsearch config list --resolved` and confirm the changed key) to strengthen workflow_clarity for batch/config operations.

Trim the model-guidance and provider-example sections to the essential defaults, or relocate the full provider examples to a reference, to tighten conciseness.

DimensionReasoningScore

Conciseness

The body is dense and mostly earned — concrete CLI commands, config keys, and URLs rather than padded explanations — though the ~240-line length and some enumerative sections (platform update procedures, model guidance) could be trimmed slightly.

4 / 5

Actionability

It provides copy-paste-ready bash commands, resolved/global/project config inspection flows, concrete TOML blocks with specific keys and values, and exact version-check commands covering the common diagnostic and configuration cases.

5 / 5

Workflow Clarity

"Diagnose First" and Intent Routing give a clear sequence, and guardrails (ask before enabling paid providers/re-indexing; show resolved value and session-needed after changes) act as checkpoints, though there is no explicit validate->fix->retry loop for the config changes.

4 / 5

Progressive Disclosure

Content is well-organized into clearly headed sections (Intent Routing, Diagnose First, Background and Compatibility, Configuration Logic) with inline doc URLs and no nested references, though the large inline config detail could plausibly be split into reference files.

4 / 5

Total

17

/

20

Passed

Description

91%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, well-structured description that clearly states what the skill does and when to use it, with comprehensive natural trigger terms. The only soft spot is a slight overlap risk with Claude Code's native memory config, which the body addresses.

DimensionReasoningScore

Specificity

"Diagnose and configure MemSearch memory behavior" names the domain and core actions, and the Use-when clause enumerates several specific capability areas (summarization, maintenance, index health, provider routing, prompt files), with only minor action-verb gaps.

4 / 5

Completeness

It explicitly answers both what ("Diagnose and configure MemSearch memory behavior for the Claude Code plugin") and when ("Use when the user asks about...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

The Use-when clause lists comprehensive natural trigger phrases users would say, including synonyms and file references ("MemSearch configuration", "PROJECT.md/USER.md maintenance", "provider routing", "prompt files", "migration/compatibility questions").

5 / 5

Distinctiveness Conflict Risk

The MemSearch-specific niche and file references make it mostly distinct, with only minor overlap risk against Claude Code's own built-in memory configuration (which the body explicitly disambiguates).

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
zilliztech/memsearch
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.