OpenClaw

expertpack-export

Export an OpenClaw instance's accumulated knowledge into a structured ExpertPack composite. Use when backing up an agent's identity, exporting for migration, or creating a portable knowledge snapshot. Handles auto-discovery (scanning workspace state to identify constituent packs), distillation (compressing raw state into structured EP files), and packaging (writing EP-compliant packs + composite manifest). NOT for importing/hydrating from an existing EP.

brianhearn0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install brianhearn/expertpack-export

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

ExpertPack Export

Part of the ExpertPack framework — a structured, portable knowledge format for AI agents.

Export an OpenClaw instance into a composite ExpertPack — an agent pack (subtype: agent) as the voice, plus person/product/process packs as knowledge constituents.

Learn more: expertpack.ai · GitHub · Schema docs

Prerequisites

Read references/schemas-summary.md for the EP schema rules this export must follow.
The export writes to a target directory (default: {workspace}/export/). It does NOT modify the agent's live workspace files.

Export Flow

1. Scan

Run scripts/scan.py to inventory the workspace. It outputs a JSON manifest of discovered files, their categories, and proposed pack assignments.

python3 {skill_dir}/scripts/scan.py --workspace /root/.openclaw/workspace --output /tmp/ep-scan.json

Review the scan output. It proposes:

Which files map to which pack type (agent, person, product, process)
Which knowledge domains were detected
Confidence scores for ambiguous classifications

2. Propose

Present the proposed composite to the user:

List each proposed pack with type, slug, and key content sources
Flag ambiguous classifications for user decision
Note any gaps (e.g., "No process packs detected — skip or create stubs?")

Wait for user confirmation before proceeding.

3. Distill

Run scripts/distill.py for each proposed pack. It reads source files, extracts knowledge, deduplicates, and writes EP-compliant output.

python3 {skill_dir}/scripts/distill.py \
  --scan /tmp/ep-scan.json \
  --pack agent:easybot \
  --output /root/.openclaw/workspace/export/packs/easybot/

Repeat for each pack. The script:

Reads source files listed in the scan manifest
Extracts and classifies knowledge assertions
Deduplicates (prefers newest for conflicts)
Writes struct...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/brianhearn/expertpack-export
Version: —
Commit: 10a734764631044eda889d4e4d79615800e2fe94
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# ExpertPack Export

Part of the [ExpertPack](https://expertpack.ai) framework — a structured, portable knowledge format for AI agents.

Export an OpenClaw instance into a composite ExpertPack — an agent pack (subtype: agent) as the voice, plus person/product/process packs as knowledge constituents.

**Learn more:** [expertpack.ai](https://expertpack.ai) · [GitHub](https://github.com/brianhearn/ExpertPack) · [Schema docs](https://expertpack.ai/#schemas)

## Prerequisites

- Read `references/schemas-summary.md` for the EP schema rules this export must follow.
- The export writes to a target directory (default: `{workspace}/export/`). It does NOT modify the agent's live workspace files.

## Export Flow

### 1. Scan

Run `scripts/scan.py` to inventory the workspace. It outputs a JSON manifest of discovered files, their categories, and proposed pack assignments.

```bash
python3 {skill_dir}/scripts/scan.py --workspace /root/.openclaw/workspace --output /tmp/ep-scan.json
```

Review the scan output. It proposes:
- Which files map to which pack type (agent, person, product, process)
- Which knowledge domains were detected
- Confidence scores for ambiguous classifications

### 2. Propose

Present the proposed composite to the user:
- List each proposed pack with type, slug, and key content sources
- Flag ambiguous classifications for user decision
- Note any gaps (e.g., "No process packs detected — skip or create stubs?")

Wait for user confirmation before proceeding.

### 3. Distill

Run `scripts/distill.py` for each proposed pack. It reads source files, extracts knowledge, deduplicates, and writes EP-compliant output.

```bash
python3 {skill_dir}/scripts/distill.py \
  --scan /tmp/ep-scan.json \
  --pack agent:easybot \
  --output /root/.openclaw/workspace/export/packs/easybot/
```

Repeat for each pack. The script:
- Reads source files listed in the scan manifest
- Extracts and classifies knowledge assertions
- Deduplicates (prefers newest for conflicts)
- Writes struct...

搜索