AgentPearl Exporter
Use this skill to build a pure agent-core export from one or more supported repositories.
When To Use It
Use this skill when the user wants to:
- - extract only the files that define an agent
- package agent-core files into a clean zip
- detect which supported framework a repo uses
- prepare source material for AI-driven migration into another agent framework
- study the identity, instruction, runtime, capability, multi-agent, or composition layers of an agent repo
Supported Frameworks
The bundled exporter detects these framework signatures:
- - INLINECODE0
- INLINECODE1
- INLINECODE2
- INLINECODE3
- INLINECODE4
- INLINECODE5
Workflow
- 1. Confirm the target repositories exist under a common base directory.
- Run
scripts/export-agent-core-pack.sh. - Inspect the resulting zip,
README.txt, and MANIFEST.txt. - If the user needs migration guidance, read
references/AGENT_CORE.md to map the exported files into agent-core layers.
Commands
Export the default supported repositories under ~/Documents/GitHub:
CODEBLOCK0
Export a subset of repositories:
CODEBLOCK1
Choose a base directory, output directory, and archive name:
CODEBLOCK2
Rules
- - Keep the archive source-only.
- Include only files that directly define agent behavior.
- Exclude tests, build artifacts, dependency folders, unrelated app code, and target-framework metadata.
- If a repository does not match a supported signature, stop and report it instead of guessing.
References
- - Read
references/AGENT_CORE.md when you need the layer model for interpreting exported files.
AgentPearl 导出器
使用此技能从一个或多个受支持的仓库中构建纯 agent-core 导出文件。
使用场景
当用户希望实现以下目标时,可使用此技能:
- - 仅提取定义 agent 的文件
- 将 agent-core 文件打包成干净的 zip 文件
- 检测仓库使用的受支持框架
- 为 AI 驱动的迁移到其他 agent 框架准备源材料
- 研究 agent 仓库的身份、指令、运行时、能力、多 agent 或组合层
受支持的框架
内置的导出器可检测以下框架特征:
- - nanoclaw-ts-bootstrap
- nanobot-py-templates
- nullclaw-zig-bootstrap
- zeroclaw-rs-config-prompt
- openfang-rs-manifests
- codex-rs-builtins
工作流程
- 1. 确认目标仓库存在于同一个基础目录下。
- 运行 scripts/export-agent-core-pack.sh。
- 检查生成的 zip 文件、README.txt 和 MANIFEST.txt。
- 如果用户需要迁移指导,请阅读 references/AGENT_CORE.md,将导出的文件映射到 agent-core 层。
命令
导出 ~/Documents/GitHub 下的默认受支持仓库:
bash
./scripts/export-agent-core-pack.sh
导出部分仓库:
bash
./scripts/export-agent-core-pack.sh --repos nanobot,openfang
选择基础目录、输出目录和归档名称:
bash
./scripts/export-agent-core-pack.sh \
--base-dir ~/Documents/GitHub \
--output-dir ./out \
--name agent-core-snapshot \
--repos codex,nullclaw
规则
- - 归档仅包含源代码。
- 仅包含直接定义 agent 行为的文件。
- 排除测试文件、构建产物、依赖文件夹、无关的应用代码以及目标框架元数据。
- 如果仓库不匹配任何受支持的特征,则停止并报告,而不是进行猜测。
参考资料
- - 当需要解释导出文件的层模型时,请阅读 references/AGENT_CORE.md。