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 Claude Code's own skills system.

73

Quality

91%

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

88%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, actionable workflow skill with concrete memsearch commands, explicit install/review checkpoints, and clear intent routing. Minor conciseness trims and the absence of any bundle/reference structure keep conciseness and progressive_disclosure just below the top anchor.

Suggestions

Tighten the explanatory prose in sections A and C (e.g., the closing sentences about on-demand vs. background distillation) to push conciseness toward the lean 5 anchor.

If any reference material (e.g., a candidate SKILL.md template or transcript-format notes) would naturally live outside the body, add it as a one-level-deep reference file to strengthen progressive_disclosure.

Consider adding a brief validation/verification step after `skills install` (e.g., confirm the skill loads in a fresh session) to make the install feedback loop fully explicit.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence; the stage model and intent routing earn their tokens. A few prose sentences (e.g., "doing it here on demand lets you inspect the original transcripts more deliberately") could be trimmed without loss, so it sits below the fully-lean 5 anchor.

4 / 5

Actionability

Provides copy-paste-ready commands with specific flags throughout (memsearch skills add --name --body-file -, skills status/list/install, config get/set, transcript --turn), covering the common capture/review/install/configure cases concretely.

5 / 5

Workflow Clarity

Clear staged sequence (0→1→2) with intent routing, explicit interactive checkpoints ("install only if the user asked or explicitly approves", "Treat installation as an interactive checkpoint"), and review-before-install validation plus guardrails — satisfying the validation requirement for the install write operation.

5 / 5

Progressive Disclosure

Well-organized into clearly signaled sections (intent routing, A–D stages, install paths, guardrails) with easy navigation and no nested references; sits at 4 rather than 5 because all content is inline (no bundle files exist) and there is no one-level-deep reference pattern to evaluate.

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, specific description that names concrete actions, leads with the verbs users type, and gives explicit trigger guidance, while distinguishing itself from the built-in skills system. The only ding is the second-person phrasing ("your MemSearch memory"), which costs one specificity point per the rubric's voice rule.

DimensionReasoningScore

Specificity

Lists several concrete actions ("make/create/extract/distill a skill", "review skill candidates", "install a distilled skill", "Manages...candidates under .memsearch/skill-candidates/") with specific paths, near-comprehensive; reduced from 5 to 4 per the second-person penalty because the description says "your MemSearch memory".

4 / 5

Completeness

Explicitly answers both what ("Turn workflows from your MemSearch memory into reusable skills", "Manages...candidates") and when ("Use when the user asks to make/create/extract/distill a skill...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers the natural phrases a user actually types — "make a skill", "create", "turn this into a skill", "review candidates", "install" — including the literal quoted user phrase, matching the comprehensive-synonym anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (MemSearch procedural memory) and explicitly disambiguated from Claude Code's own skills system ("not Claude Code's own skills system"), giving minimal conflict risk.

5 / 5

Total

19

/

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.