Is the Memory To Skill skill free?

Yes. The skill itself is free from zilliztech/memsearch. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Memory To Skill SkillProof Score?

7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Memory To Skill?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Memory To Skill with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Memory To Skill

Distills recurring workflows from MemSearch memory into installable agent skills — needs the memsearch CLI.

by zilliztech · zilliztech/memsearch

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 20, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · e698b2d

Fetched the repo tree (monorepo with 4 agent plugins each carrying identical skills/); picked plugins/claude-code/skills/memory-to-skill/SKILL.md, the best slug match. Read it plus the distiller prompt, marketplace.json and README fully: frontmatter parses (name+description, context:fork, allowed-tools:Bash), body is a clean, unusually careful prompt with explicit anti-fabrication and don't-install-without-approval guardrails. Security grep found no curl|sh, base64, tokens, or exfiltration — only its own "no secrets" rule. Every operative step invokes the external `memsearch` CLI (PyPI + plugin), so the skill is inert on a bare copy (dock 1 install point) and OUTPUT is NOT measured (not a measured loss) since I cannot install external CLIs.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Memory To Skill does

Turns workflows captured in MemSearch's memory journals into reusable, installable agent skills (a third "procedural memory" layer). Triggers when you ask to make/distill a skill from what you just did or past work, review skill candidates, or install a distilled one. It is an orchestration layer over the external `memsearch` CLI, not Claude Code's built-in skills system.

How to install Memory To Skill

/plugin marketplace add zilliztech/memsearch && /plugin install memsearch (also requires `pip install memsearch` for the CLI the skill drives), then restart Claude Code

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Memory To Skill

/memory-to-skill Distills recurring workflows from MemSearch memory into installable agent skills — needs the memsearch CLI.

It also activates on plain-language prompts like these:

Turn what I just did into a reusable skill
Review my skill candidates from past sessions
Extract a skill from this debugging workflow

Frequently asked questions

Is the Memory To Skill skill free?: Yes. The skill itself is free from zilliztech/memsearch. SkillProof publishes the install command and an independent test verdict at no cost.
Does Memory To Skill work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Works with setup. Fetched the repo tree (monorepo with 4 agent plugins each carrying identical skills/); picked plugins/claude-code/skills/memory-to-skill/SKILL.md, the best slug match. Read it plus the distiller prompt, marketplace.json and README fully: frontmatter parses (name+description, context:fork, allowed-tools:Bash), body is a clean, unusually careful prompt with explicit anti-fabrication and don't-install-without-approval guardrails. Security grep found no curl|sh, base64, tokens, or exfiltration — only its own "no secrets" rule. Every operative step invokes the external `memsearch` CLI (PyPI + plugin), so the skill is inert on a bare copy (dock 1 install point) and OUTPUT is NOT measured (not a measured loss) since I cannot install external CLIs.
What is the Memory To Skill SkillProof Score?: 7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Memory To Skill?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Memory To Skill with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.