Name: memory-to-skill
Rating: 70.39999999999999 (1 reviews)
Author: zilliztech

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

86%

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

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

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 well-organized, actionable skill body that sequences a multi-stage workflow with explicit checkpoints and cleanly offloads platform specifics to reference files. The main improvement areas are tightening a few explanatory passages and reducing placeholder substitution in command examples.

Suggestions

Trim contextual prose such as the 'third layer beside the daily journals' framing and the 'Be exact — do not guess' paragraph to their essential guidance.

Add one fully concrete worked example for `memsearch skills add` (with a real slug and body) so the template block is copy-paste ready, not just parameterized.

Consider an automated validation checkpoint (e.g., a `memsearch skills status`/dry-run after install) to turn the human-gated review into a validate→fix→retry loop for the install stage.

Dimension	Reasoning	Score
Conciseness	Largely lean and imperative with concrete commands, but contains a few trimmable explanatory passages ('a third layer beside…', the 'Be exact — do not guess' prose) that nudge it below the fully-lean anchor.	4 / 5
Actionability	Provides concrete, mostly copy-paste-ready memsearch/git/config commands across all stages, but several blocks rely on placeholders (<platform>, <short-slug>, <configured-or-user-approved-path>) the reader must substitute.	4 / 5
Workflow Clarity	A clearly sequenced 0→1→2 pipeline with intent routing, hash-based status validation, and human-approval checkpoints plus a Guardrails checklist; validation is human-gated rather than an automated validate→fix→retry loop, leaving it just below the top anchor.	4 / 5
Progressive Disclosure	A well-sectioned overview that delegates all platform-specific config and install-path detail to five real, one-level-deep reference files (claude-code.md, codex.md, openclaw.md, opencode.md, dsh.md), each clearly signaled.	5 / 5
	Total	17 / 20 Passed

Description

95%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, specific description that pairs concrete capabilities with explicit, natural trigger phrases and proactively disambiguates itself from the host agent's skills system. The only minor gap is that the listed actions are closely related variants rather than a broad action set.

Dimension	Reasoning	Score
Specificity	Lists several concrete lifecycle actions (make/create/extract/distill, review candidates, install) but they are variants of one domain, so it sits just below the comprehensive-coverage anchor.	4 / 5
Completeness	Explicitly states what it does ('Turn workflows… into reusable skills') and gives a concrete 'Use when…' trigger clause, satisfying both halves.	5 / 5
Trigger Term Quality	Natural user phrasing is covered comprehensively with synonyms plus the colloquial 'turn this into a skill', matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	Clear MemSearch niche with the explicit disambiguation 'not the host agent's own skills system' minimizes conflict risk.	5 / 5
	Total	19 / 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-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.