CtrlK
BlogDocsLog inGet started
Tessl Logo

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 OpenClaw's own skills system.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 tight, highly actionable instruction skill with concrete commands and a well-sequenced multi-stage workflow. The only gap is that validation for the as-is install/copy step is advisory review rather than an explicit validate-and-retry loop, and the doc is flat rather than split into overview-plus-reference files.

DimensionReasoningScore

Conciseness

Lean and efficient: assumes Claude's competence, uses tight imperatives and concrete command blocks, and avoids explaining basic concepts (skills, journals, git). Every section earns its place with no padding to trim.

5 / 5

Actionability

Fully executable, copy-paste-ready bash commands throughout (memsearch skills add/install/status/list, config get/set, git -C log) with realistic flag combinations and placeholder examples, covering the common cases for each flow.

5 / 5

Workflow Clarity

Clear multi-stage sequence (0->1->2) with intent routing and an explicit install checkpoint (confirm destination, resolve paths from config). Validation is present as advisory review-before-install guidance rather than a hard validate->fix->retry loop, so it stops short of the explicit-feedback-loop anchor at 5.

4 / 5

Progressive Disclosure

Well-organized with clear section headers (A-D, Install paths, Guardrails), no nested references, and no bundle files needed for this self-contained instruction skill. It is a single flat well-structured doc rather than an overview pointing one level deep to detail files, so it does not reach the 5 anchor.

4 / 5

Total

18

/

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, concrete description with explicit trigger phrasing, natural user-language verbs, and clear disambiguation against a sibling system. Only minor specificity gaps prevent a perfect specificity score.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions ('make/create/extract/distill a skill', 'review skill candidates', 'install a distilled skill', "'turn this into a skill'"), but the actions are somewhat paraphrased rather than crisply distinct, leaving minor coverage gaps vs a comprehensive 5.

4 / 5

Completeness

Explicitly answers both 'what' (turn workflows from MemSearch memory into reusable skills) and 'when' via a concrete 'Use when the user asks to...' clause with multiple trigger phrases, plus a disambiguation clause.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrasing including verb variations users actually say ('make/create/extract/distill a skill') plus the literal quoted phrase "'turn this into a skill'" and 'review skill candidates' / 'install a distilled skill'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear named niche (MemSearch procedural-memory candidates under .memsearch/skill-candidates/) and explicitly disambiguates ('not OpenClaw's own skills system'), minimizing conflict with adjacent skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.