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 OpenCode's own skills system.

Quality

94%

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

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 high-quality operational skill: executable commands throughout, well-sequenced multi-route workflows with explicit verification and guardrails, and clean section organization. Minor tightening of rationale sentences and possibly extracting the per-agent install-path reference data would lift it further.

Suggestions

Trim non-actionable rationale tails such as 'doing it here on demand lets you inspect the original transcripts more deliberately, so the result can be more accurate' to improve token efficiency.

Consider condensing the per-agent install-path directory list (Claude Code .claude/skills/, Codex/OpenCode .agents/skills/, OpenClaw .openclaw/skills/) into a compact reference table, since it is reference data rather than workflow steps.

Dimension	Reasoning	Score
Conciseness	The body is dense and actionable with no padding of concepts Claude already knows, but a few rationale tails (e.g. 'so the result can be more accurate') and parentheticals could be trimmed, so it is efficient rather than perfectly lean.	4 / 5
Actionability	Provides concrete, executable memsearch/git/python3 commands with real flags covering the common cases (status, list, add, install, config get/set, parse-transcript); placeholders like __INSTALL_DIR__ and <title> are standard parameter substitutions, not pseudocode.	5 / 5
Workflow Clarity	The A/B/C/D routes are clearly sequenced with explicit validation checkpoints and feedback loops (skim-before-install, verify-or-keep-general, 'never fabricate') plus a Guardrails checklist; because validation is present, the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Well-organized into clear headers (Intent routing, A-D, Install paths, Guardrails) with nothing that needs splitting into separate files, but there are no external file references and the body exceeds 50 lines, so the simple-skill 5-exception does not apply.	4 / 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.

A strong description: imperative voice, explicit what-and-when, comprehensive natural trigger terms including the literal user phrase, and clear disambiguation from the host's built-in skills system. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'make/create/extract/distill a skill', 'review skill candidates', 'install a distilled skill', 'Manages ... candidates under .memsearch/skill-candidates/' — giving comprehensive coverage rather than just naming the domain.	5 / 5
Completeness	Explicitly states 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	Captures natural phrasings users actually say, including the literal quoted phrase "'turn this into a skill'" plus the synonym set make/create/extract/distill and review/install, matching the comprehensive-coverage-with-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear MemSearch procedural-memory niche and actively disambiguates ('not OpenCode's own skills system'), with triggers tied to skill distillation, so conflict risk with other skills is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zilliztech/memsearch
Path: plugins/opencode/skills/memory-to-skill/SKILL.md
Commit: f91f5d3

Reviewed: about 6 hours 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.