Skills for Real Engineers. Straight from my .agents directory.
memory-to-skill
Agent skill fromzilliztech/memsearch
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.
How to install memory-to-skill
npx skills add zilliztech/memsearch# or add only this skill to Claude Code: copy the folder
plugins/_shared/skills/memory-to-skill/
# into
~/.claude/skills/memory-to-skill/ (all projects)
.claude/skills/memory-to-skill/ (one project)
1You manage MemSearch's **procedural memory**: skills distilled from the work you2repeat — a third layer beside the daily journals (episodic) and PROJECT.md /3USER.md (semantic). State once that this is MemSearch skill distillation, not4the host agent's built-in skills system.56Stages: **0** memory journals → **1** candidate (`.memsearch/skill-candidates/`,7a git-tracked store that keeps evolving) → **2** installed (an agent skill dir).8Candidates are never installed automatically; installing is always a human step.9User requests may stop at candidate creation/review, or continue to installation10in the same turn after explicit approval; match the requested stage.1112The `plugins.<platform>.memory_to_skill.*` config key prefix and the install-path13notes are platform-specific — see your platform reference file:1415- Claude Code → `references/claude-code.md`16- Codex → `references/codex.md`17- OpenClaw → `references/openclaw.md`18- OpenCode → `references/opencode.md`19- DeepSeek Harness → `references/dsh.md`2021## Intent routing2223- "make/turn this into a skill", "from what we just did" → **A. Capture now**.24- "what skills / review candidates / install X" → **B. Review & install**.25- "mine my history / find recurring workflows" → **C. Distill from history**.26- "enable / configure / how eager" → **D. Configure**.27- Unclear or empty → run **B**'s `list`; if empty, offer A or C.2829## A. Capture what you just did (0→1→2)30…
Excerpt shown under the repository's MIT license.
More skills in memsearch
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
