Distill verbose daily logs into compact, indexed digests. Use when managing agent memory files, compressing logs, creating summaries of past activity, or building index-first memory architectures.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install memory-curator或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install memory-curator⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/memory-curator/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: memory-curator description: Distill verbose daily logs into compact, indexed digests. Use when managing agent memory files, compressing logs, creating summaries of past activity, or building index-first memory architectures. ---
Transform raw daily logs (often 200-500+ lines) into ~50-80 line digests while preserving key information.
# Generate digest skeleton for today
./scripts/generate-digest.sh
# Generate for specific date
./scripts/generate-digest.sh 2026-01-30Then fill in the sections manually.
A good digest captures:
| Section | Purpose | Example | |---------|---------|---------| | Summary | 2-3 sentences, the day in a nutshell | "Day One. Named Milo. Built connections on Moltbook." | | Stats | Quick metrics | Lines, sections, karma, time span | | Key Events | What happened (not everything, just what matters) | Numbered list, 3-7 items | | Learnings | Insights worth remembering | Bullet points | | Connections | People interacted with | Names + one-line context | | Open Questions | What you're still thinking about | For continuity | | Tomorrow | What future-you should prioritize | Actionable items |
Digests work best with hierarchical indexes:
memory/
├── INDEX.md ← Master index (scan first ~50 lines)
├── digests/
│ ├── 2026-01-30-digest.md
│ └── 2026-01-31-digest.md
├── topics/ ← Deep dives
└── daily/ ← Raw logs (only read when needed)Workflow: Scan index → find relevant digest → drill into raw log only if needed.
Set up end-of-day cron to auto-generate skeletons:
Schedule: 55 23 * * * (23:55 UTC)
Task: Run generate-digest.sh, fill Summary/Learnings/Tomorrow, commit安装 Memory Curator 后，可以对 AI 说这些话来触发它
Help me get started with Memory Curator
Explains what Memory Curator does, walks through the setup, and runs a quick demo based on your current project
Use Memory Curator to distill verbose daily logs into compact, indexed digests
Invokes Memory Curator with the right parameters and returns the result directly in the conversation
What can I do with Memory Curator in my documents & notes workflow?
Lists the top use cases for Memory Curator, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/memory-curator/ 目录（个人级，所有项目可用），或 .claude/skills/memory-curator/（项目级）。重启 AI 客户端后，用 /memory-curator 主动调用，或让 AI 根据上下文自动发现并使用。
Memory Curator 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Memory Curator 可免费安装使用。请查阅仓库了解许可证信息。
Distill verbose daily logs into compact, indexed digests. Use when managing agent memory files, compressing logs, creating summaries of past activity, or building index-first memory architectures.
Memory Curator 属于「Documents & Notes」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my documents & notes tasks using Memory Curator
Identifies repetitive steps in your workflow and sets up Memory Curator to handle them automatically