memory-to-skill

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under .memsearch/skill-candidates/, not the host agent's own skills system.

Quality

84%

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

Quality

Content

85%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 well-structured, highly actionable skill body: clear intent routing, copy-paste CLI commands, explicit verification and confirmation checkpoints, and platform specifics correctly split into one-level-deep reference files that all exist. The only weaknesses are minor — an external reference dependency in flow C and a small amount of trimmable rationale plus one version-number note.

Suggestions

Inline the transcript-drill command (or a pointer to a file inside this skill's bundle) in flow C instead of referencing the memory-recall skill's platform reference, so the workflow is fully executable from this skill alone.

Trim rationale passages like the on-demand vs background-mining comparison in C to a single sentence, and move the "Since v0.4.11" config caveat into a clearly-labeled compatibility/notes line so the version reference reads as scoped guidance rather than dated prose.

Dimension	Reasoning	Score
Conciseness	The body is dense and imperative, and nearly all of it is MemSearch-specific operational detail Claude cannot already know. Not 5 because a few passages could be trimmed (e.g. the rationale for on-demand mining in C) and the bare version number "Since v0.4.11..." is time-sensitive content outside a deprecated/old-patterns section; not 3 because the padding is minor rather than a pattern.	4 / 5
Actionability	Concrete, copy-paste commands throughout: `memsearch skills add --name ... --body-file -`, `skills status`, `skills list`, `git -C .memsearch/skill-candidates log`, and exact `config get/set` invocations. Not 5 because flow C defers the transcript-drill command to "the memory-recall skill's platform reference" — an external dependency not in this bundle — leaving a gap in executability.	4 / 5
Workflow Clarity	Intent routing disambiguates requests up front; each flow is clearly sequenced with explicit validation checkpoints ("Be exact — do not guess", re-check candidates against source before install, confirm install destination, fallback chain "Only if that command fails... fall back to reading the raw file", "never fabricate"). The install step — the closest thing to a batch/destructive operation — is an interactive checkpoint with user confirmation, so the validation cap does not apply.	5 / 5
Progressive Disclosure	The body is a clear overview with an explicit platform-to-reference-file map; all five referenced files (claude-code.md, codex.md, openclaw.md, opencode.md, dsh.md) exist in references/, are one level deep, and contain exactly the platform-specific config/install-path detail kept out of the main body. No nesting, easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

83%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' trigger clause, natural trigger phrasing including a quoted user phrase, and a clear disambiguation against the host agent's skills system. The only gaps are minor: a few action types (history-mining, configuration) and trigger synonyms are unlisted.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Turn workflows from your MemSearch memory into reusable skills", "review skill candidates", "install a distilled skill" — plus the concrete store path ".memsearch/skill-candidates/". Not 5 because history-mining and configuration actions from the body are absent, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both: what ("Turn workflows from your MemSearch memory into reusable skills... Manages MemSearch procedural-memory candidates") and when ("Use when the user asks to make/create/extract/distill a skill... review skill candidates, install a distilled skill"). The 'when' clause is fully explicit with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Good natural-phrase coverage: "make/create/extract/distill a skill", "from what they just did", and the quoted "turn this into a skill". Not 5 because common variations like "save this workflow" or "what skills do I have" are missing; not 3 since multiple synonyms and a literal user quote are present.	4 / 5
Distinctiveness Conflict Risk	"not the host agent's own skills system" explicitly disambiguates and the MemSearch framing carves a niche. Not 5 because generic requests like "make a skill" could still be intended for the host agent's skill system, leaving minor overlap risk.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: zilliztech/memsearch
Path: plugins/claude-code/skills/memory-to-skill/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.