How do I install the Claude Memory Kit skill?

Run npx skillmds@latest add zuoguyoupan2023/claude-memory-kit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Claude Memory Kit safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Claude Memory Kit?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Claude Memory Kit free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Claude Memory Kit?

zuoguyoupan2023 (@zuoguyoupan2023) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Claude Memory Kit by zuoguyoupan2023

Name: Claude Memory Kit
Rating: 4.2 (5 reviews)
Author: zuoguyoupan2023

Claude Memory Kit

Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; agent captures, audits, proposes promotions, and writes. Four layers — daily logs, hot cache (MEMORY.md), role-based reference skills (Anthropic-native, user-invocable: false), canonical rules. /close-day runs the audit ritual at end of day. Multi-project isolation via projects/<name>/. Zero external dependencies.

File contents

Claude Memory Kit v4

Persistent memory for Claude Code agents. Four-layer architecture, agent-driven promotion, zero manual file editing.

Core invariant

User only talks. Agent captures, proposes, writes. Every architectural decision passes this test.

What's different from v3.2

Agent-driven promotion ritual via /close-day (was: background promote-patterns.py detection, killed as unreliable)
Role-based reference skills (.claude/skills/<role>-guidance/SKILL.md with user-invocable: false) alongside topic-based knowledge/concepts/ — two axes, no overlap. Uses Anthropic-native auto-invoke via description matching — no custom trigger tables.
Multi-project isolation via projects/<name>/ — shared layers load always, per-project scope on demand
/memory-audit operator for oversized-reference-skill detection + semantic split execution
Killed: experiences/ staging layer, promote-patterns.py background script, flush.py auto-flush, separate playbooks/ directory (merged into reference skills)

See CHANGELOG.md for full migration notes.

Quick start

git clone https://github.com/awrshift/claude-memory-kit.git my-project
cd my-project
claude

First session: agent greets you, asks 2-3 setup questions, loads you in. Type /tour for a guided walkthrough.

Daily workflow

Open a session — hooks auto-load NSP + MEMORY + knowledge index
Work normally — agent captures patterns in MEMORY.md as you speak
/close-day when done — agent synthesizes today, audits for promotions, proposes verbally, writes on your verbal "yes"

Tomorrow starts where today left off.

Included skills

Skill	Description
`/close-day`	End-of-day audit ritual: synthesis + promotion proposals
`/memory-audit`	Oversized-reference-skill structural check + split proposals
`/memory-lint`	Hygiene (broken links, sparse articles, orphans, oversized reference skills)
`/memory-compile`	Compile daily logs into `knowledge/concepts/` articles
`/memory-query`	Natural-language search across all memory layers
`/tour`	Interactive guided walkthrough

Architecture

Four layers, each with its own purpose:

Layer	Answers	Written by
`daily/YYYY-MM-DD.md`	«what happened today»	`/close-day`
`.claude/memory/MEMORY.md`	«what patterns repeat across sessions»	agent as you speak
`.claude/skills/<role>-guidance/SKILL.md`	«how should a think about X»	`/close-day` promotion
`.claude/rules/*.md`	«what must always / never happen»	`/close-day` after 6+ months stable

See ARCHITECTURE.md for full details and CLAUDE.md for the agent's session workflow.

Built from production use

Iteration on 700+ real sessions across 7+ projects. Every component earns its place; experiences/ and background-detection scripts didn't survive review.

---name: claude-memory-kitdescription: Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; agent captures, audits, proposes promotions, and writes. Four layers — daily logs, hot cache (MEMORY.md), role-based reference skills (Anthropic-native, user-invocable: false), canonical rules. /close-day runs the audit ritual at end of day. Multi-project isolation via projects/<name>/. Zero external dependencies.license: MIT---# Claude Memory Kit v4Persistent memory for Claude Code agents. Four-layer architecture, agent-driven promotion, zero manual file editing.## Core invariant**User only talks. Agent captures, proposes, writes.** Every architectural decision passes this test.## What's different from v3.2- **Agent-driven promotion ritual** via `/close-day` (was: background `promote-patterns.py` detection, killed as unreliable)- **Role-based reference skills** (`.claude/skills/<role>-guidance/SKILL.md` with `user-invocable: false`) alongside topic-based `knowledge/concepts/` — two axes, no overlap. Uses Anthropic-native auto-invoke via `description` matching — no custom trigger tables.- **Multi-project isolation** via `projects/<name>/` — shared layers load always, per-project scope on demand- **`/memory-audit`** operator for oversized-reference-skill detection + semantic split execution- **Killed:** `experiences/` staging layer, `promote-patterns.py` background script, `flush.py` auto-flush, separate `playbooks/` directory (merged into reference skills)See [CHANGELOG.md](CHANGELOG.md) for full migration notes.## Quick start```bashgit clone https://github.com/awrshift/claude-memory-kit.git my-projectcd my-projectclaude```First session: agent greets you, asks 2-3 setup questions, loads you in. Type `/tour` for a guided walkthrough.## Daily workflow1. Open a session — hooks auto-load NSP + MEMORY + knowledge index2. Work normally — agent captures patterns in MEMORY.md as you speak3. `/close-day` when done — agent synthesizes today, audits for promotions, proposes verbally, writes on your verbal "yes"Tomorrow starts where today left off.## Included skills| Skill | Description ||---|---|| `/close-day` | End-of-day audit ritual: synthesis + promotion proposals || `/memory-audit` | Oversized-reference-skill structural check + split proposals || `/memory-lint` | Hygiene (broken links, sparse articles, orphans, oversized reference skills) || `/memory-compile` | Compile daily logs into `knowledge/concepts/` articles || `/memory-query` | Natural-language search across all memory layers || `/tour` | Interactive guided walkthrough |## ArchitectureFour layers, each with its own purpose:| Layer | Answers | Written by ||---|---|---|| `daily/YYYY-MM-DD.md` | «what happened today» | `/close-day` || `.claude/memory/MEMORY.md` | «what patterns repeat across sessions» | agent as you speak || `.claude/skills/<role>-guidance/SKILL.md` | «how should a <role> think about X» | `/close-day` promotion || `.claude/rules/*.md` | «what must always / never happen» | `/close-day` after 6+ months stable |See [ARCHITECTURE.md](ARCHITECTURE.md) for full details and [CLAUDE.md](CLAUDE.md) for the agent's session workflow.## Built from production useIteration on 700+ real sessions across 7+ projects. Every component earns its place; `experiences/` and background-detection scripts didn't survive review.

Frequently asked questions