Elite Longterm Memory → ExpertPack
Converts an Elite Longterm Memory (5-layer system with 32K ClawHub downloads) into a proper structured ExpertPack.
Supported layers:
- - Hot RAM —
SESSION-STATE.md (current task, context, decisions) - Warm Store — LanceDB vectors at
~/.openclaw/memory/lancedb/ (note: exported or skipped) - Cold Store — Git-Notes JSONL (decisions, learnings, preferences)
- Curated Archive —
MEMORY.md, memory/YYYY-MM-DD.md journals, INLINECODE4 - Cloud — SuperMemory/Mem0 (skipped, noted in overview)
Usage
CODEBLOCK0
Flags let you override auto-detected paths for each layer.
What It Produces
A complete ExpertPack conforming to schema 2.3:
- -
manifest.yaml (with context tiers, EK stub) - INLINECODE6 summarizing conversion (layer counts, warnings)
- Structured directories:
mind/, facts/, summaries/, operational/, relationships/, etc. - INLINECODE12 files, lead summaries,
glossary.md (if terms found) - INLINECODE14 (if relationships detected)
- Clean deduplication preferring curated > structured > raw sources
Secrets are automatically stripped (sk-, ghp_, tokens, passwords). Warnings emitted for any found.
Post-Conversion Steps
- 1. INLINECODE15
- Verify content files are 400–800 tokens each (Schema 2.5 — retrieval-ready by design)
- Measure EK ratio: INLINECODE16
- Review
overview.md and INLINECODE18 - Commit to git and publish to ClawHub
Learn more: https://expertpack.ai • ClawHub expertpack skill
See also: Elite Longterm Memory skill on ClawHub.
精英长期记忆 → 专家包
将精英长期记忆(包含32K ClawHub下载量的5层系统)转换为结构化的专家包。
支持的层级:
- - 热RAM — SESSION-STATE.md(当前任务、上下文、决策)
- 温存储 — 位于~/.openclaw/memory/lancedb/的LanceDB向量(注意:已导出或跳过)
- 冷存储 — Git-Notes JSONL(决策、学习、偏好)
- 精选归档 — MEMORY.md、memory/YYYY-MM-DD.md日志、memory/topics/*.md
- 云端 — SuperMemory/Mem0(已跳过,在概览中注明)
使用方法
bash
cd /root/.openclaw/workspace/ExpertPack/skills/elite-to-expertpack
python3 scripts/convert.py \
--workspace /path/to/your/workspace \
--output ~/expertpacks/my-agent-pack \
[--name 我的智能体知识库] \
[--type auto|person|agent]
标志参数允许您覆盖每层自动检测的路径。
输出内容
符合2.3模式的完整专家包:
- - manifest.yaml(包含上下文层级、EK存根)
- overview.md(汇总转换信息:层级计数、警告)
- 结构化目录:mind/、facts/、summaries/、operational/、relationships/等
- _index.md文件、引导摘要、glossary.md(如发现术语)
- relations.yaml(如检测到关系)
- 干净的去重处理,优先选择:精选 > 结构化 > 原始来源
自动剥离机密信息(sk-、ghp_、令牌、密码)。发现任何机密信息都会发出警告。
转换后步骤
- 1. cd ~/expertpacks/my-agent-pack
- 验证每个内容文件为400–800个令牌(模式2.5 — 设计为可直接检索)
- 测量EK比率:python3 /path/to/expertpack/tools/eval-ek.py .
- 审查overview.md和manifest.yaml
- 提交到git并发布到ClawHub
了解更多: https://expertpack.ai • ClawHub 专家包技能
另请参阅: ClawHub上的精英长期记忆技能。