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

92%

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.

The body is well-structured, actionable, and uses progressive disclosure effectively with real reference files, strong workflow sequencing, and explicit validation checkpoints around the install step. Its main weakness is a subtle bug in the headline capture command plus some repeated accuracy guardrails that could be tightened.

Suggestions

Fix the section-A capture example: `printf '%s' "...\n..."` writes literal backslash-n; use `printf '## %s\n\n1. ...\n2. ...\n' "<title>"` or a heredoc so the candidate body gets real newlines.

Consolidate the repeated 'be exact / do not guess / never fabricate' guidance into one statement in section A and reference it from B and C, to trim tokens without losing the safeguard.

Consider moving the v0.4.11 `.memsearch.toml` allowlist note into the platform reference files, since it is version/time-sensitive and the rubric penalizes such details in the main body.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete commands and assumes Claude's competence, but the accuracy exhortations ("Be exact — do not guess", "never fabricate", "a wrong command is worse than a vague one") recur across sections A, B, and C and could be consolidated. Not a 5 because of that repeated hedging; not a 3 since most tokens earn their place.	4 / 5
Actionability	Provides copy-paste-ready bash throughout (memsearch skills add/status/list/install, config get/set, git log) covering capture, review, install, and configure. Capped below 5 because the marquee section-A example `printf '%s' "## <title>\n\n1. ..."` emits literal backslash-n rather than newlines (printf %s does not interpret escapes), so the headline command as written produces a malformed skill body.	4 / 5
Workflow Clarity	Clear staged sequence (0→1→2) with intent routing to A/B/C/D and explicit validation checkpoints: skim and re-check the candidate body before install ("last chance to catch a wrong step"), confirm the install destination with the user, and drill into the transcript when a step is uncertain. The semi-destructive install step has the review checkpoint the rubric requires, so the destructive cap does not apply.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview that splits platform-specific config-key prefixes and install paths into one-level-deep, clearly signaled reference files (references/claude-code.md, codex.md, dsh.md, openclaw.md, opencode.md — all present and verified), each referenced via a platform→file bulleted map for easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is comprehensive, concrete, and clearly signals both capability and trigger conditions, while explicitly disambiguating itself from the host agent's built-in skills system. It is a strong, low-conflict trigger description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full lifecycle — "Turn workflows... into reusable skills", "review skill candidates", "install a distilled skill", and manage candidates under .memsearch/skill-candidates/ — giving comprehensive coverage rather than vague domain naming.	5 / 5
Completeness	Explicitly answers both: what it does ("Turn workflows from your MemSearch memory into reusable skills... Manages MemSearch procedural-memory candidates") and when to use it ("Use when the user asks to make/create/extract/distill a skill...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes the natural phrases a user would actually type — "make/create/extract/distill a skill", "from what they just did", "from past work", "review skill candidates", "install a distilled skill", and the verbatim "turn this into a skill" — with synonyms well covered.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche (MemSearch procedural-memory distillation under .memsearch/skill-candidates/) and explicitly disambiguates from "the host agent's own skills system", giving distinct triggers and minimal overlap risk.	5 / 5
	Total	20 / 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: 3e98e4a

Reviewed: 3 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.