Memory to Skill

Memory to Skill is an AI Engineering skill for Claude Code, published by zilliztech in memsearch.

2.5K stars227 forkson zilliztech/memsearchAdded 2026/08/18+1% in starsRepository updated 2026/08/17

agentagent-memoryai-agentsclaude-codeclaude-code-plugincodexcodex-cliembeddingsharnesshybrid-searchlong-term-memorymemorymilvusopenclawopencodeprogressive-disclosureragrerankersemantic-searchskills

Install in seconds

Install Memory to Skill

Copy Memory to Skill into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/zilliztech/memsearch/tree/main/plugins/claude-code/skills/memory-to-skill ~/.claude/skills/memory-to-skill

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/zilliztech/memsearch.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/claude-code/skills/memory-to-skill/SKILL.md in zilliztech/memsearch
Installs to: ~/.claude/skills/memory-to-skill
Collection: One of 13 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Memory to Skill does

Memory to Skill turns workflows from MemSearch memory into reusable skills by managing procedural-memory candidates under .memsearch/skill-candidates/. Use it when asked to make, extract, distill, review, or install a skill from recent or past work.

Memory to Skill is cataloged under AI Engineering on DirSkills. Memory to Skill comes from a repository tagged agent, agent-memory, ai-agents, claude-code and claude-code-plugin.

Documentation

README

Excerpt

You manage MemSearch's procedural memory: skills distilled from the work you repeat — a third layer beside the daily journals (episodic) and PROJECT.md / USER.md (semantic). State once that this is MemSearch skill distillation, not Claude Code's built-in skills system.

Stages: 0 memory journals → 1 candidate (.memsearch/skill-candidates/, a git-tracked store that keeps evolving) → 2 installed (an agent skill dir). Candidates are never installed automatically; installing is always a human step. User requests may stop at candidate creation/review, or continue to installation in the same turn after explicit approval; match the requested stage.

Intent routing

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Memory to Skill

What else does zilliztech publish alongside Memory to Skill?
Memory to Skill is one of 13 skills that DirSkills catalogs from zilliztech/memsearch, the repository it ships in. Its siblings there include MemSearch Configuration, MemSearch Memory Config and Memory Config. Each one is a separate skill with its own page in this directory, installs the same way Memory to Skill does, and is maintained by zilliztech in that same repository. The rest of the collection is listed on the zilliztech/memsearch page.
How does Memory to Skill compare to other AI Engineering skills?
Memory to Skill ranks #800 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Memory to Skill against them. Open each page to compare what they document and how they install.