CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

89%

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

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

SKILL.md
Quality
Evals
Security

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 instruction skill: concrete executable commands, an explicit staged workflow with interactive checkpoints and fallbacks, and correct use of one-level-deep platform reference files. The weakest spots are the deferred transcript-drill command and a version-number note that belongs in a clearer place, keeping actionability and conciseness at 4.

Suggestions

Inline the exact transcript-drill command (or a one-line example of it) in section C instead of deferring to the memory-recall skill's platform reference, so the core mining flow is fully executable from this file.

Move the 'Since v0.4.11' project-local config note into a short 'Version-specific notes' or deprecated-patterns section so time-sensitive version details don't sit in the main flow.

Trim rationale sentences (e.g. 'so the result can be more accurate' in section C) to tighten the body without losing the operational guidance.

DimensionReasoningScore

Conciseness

Imperative and command-dense with no re-teaching of known concepts, but a version-number reference ('Since v0.4.11, project-local .memsearch.toml...') sits in the main flow rather than a deprecated section, and a few rationale sentences ('so the result can be more accurate') could be trimmed.

4 / 5

Actionability

Mostly copy-paste-ready bash (skills add/status/list/install, exact config get/set keys, the printf --body-file pipeline), but the history-mining transcript drill defers the exact command to another skill's reference file, a minor gap.

4 / 5

Workflow Clarity

Clear intent routing and staged 0→1→2 flow with explicit validation checkpoints (hash-based 'skills status', 'Before recommending or installing, skim the candidate's body'), an error-recovery fallback ('Only if that command fails... fall back to reading the raw file directly'), and a guardrails checklist.

5 / 5

Progressive Disclosure

The body is a concise overview with clearly signaled one-level-deep platform references; all five referenced files (references/claude-code.md, codex.md, dsh.md, openclaw.md, opencode.md) exist in the bundle and match the body's pointers.

5 / 5

Total

18

/

20

Passed

Description

87%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: concrete actions, an explicit 'Use when' clause with quoted natural triggers, and active disambiguation from the host skills system. The only gaps are the unlisted configure/history-mining triggers and the missing configure capability, which keep specificity and trigger coverage at 4.

DimensionReasoningScore

Specificity

Lists several concrete actions (turn workflows into skills, review candidates, install a distilled skill) plus a concrete store path '.memsearch/skill-candidates/'; the configure stage covered by the body is absent, leaving a minor coverage gap short of a 5.

4 / 5

Completeness

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

5 / 5

Trigger Term Quality

Good natural coverage including the verbatim user phrase 'turn this into a skill' and 'make/create/extract/distill a skill', but phrases the body itself routes on ('mine my history', 'find recurring workflows', 'how eager') are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (MemSearch procedural-memory distillation) with a distinct trigger vocabulary, and it explicitly disambiguates from 'the host agent's own skills system', minimizing wrong-skill triggering.

5 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

zilliztech/memsearch

Path

plugins/_shared/skills/memory-to-skill/SKILL.md

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.