Self-Improving Agent → ExpertPack
Converts a Self-Improving Agent skill's .learnings/ directory (3.8K ClawHub installs) into a properly structured ExpertPack.
Supported sources:
- - LEARNINGS.md — corrections, knowledge gaps, best practices, simplify-and-harden patterns
- ERRORS.md — command failures, exceptions, integration issues
- FEATURE_REQUESTS.md — user-requested capabilities and implementation notes
- Promoted content — entries already promoted to CLAUDE.md, AGENTS.md, SOUL.md, TOOLS.md (detected and cross-referenced)
Usage
CODEBLOCK0
Override .learnings/ location with --learnings /path/to/.learnings.
What It Produces
A complete ExpertPack conforming to schema 2.3:
- -
manifest.yaml (with context tiers, EK stub) - INLINECODE4 summarizing conversion (entry counts, categories, priority breakdown)
- Structured directories mapped from learning types:
-
mind/ — best practices, conventions, behavioral patterns, promoted rules
-
facts/ — knowledge gaps filled, project-specific facts
-
operational/ — error resolutions, tool gotchas, integration fixes
-
summaries/ — pattern analyses, recurring issue summaries
-
relationships/ — cross-references between related entries
- -
_index.md files, lead summaries, glossary.md (if terms/tags found) - INLINECODE12 (from See Also links and shared tags)
- Clean deduplication preferring promoted > resolved > pending entries
Secrets are automatically stripped (sk-, ghp_, tokens, passwords). Warnings emitted for any found.
Post-Conversion Steps
- 1. INLINECODE13
- Verify content files are 400–800 tokens each (Schema 2.5 — retrieval-ready by design)
- Measure EK ratio: INLINECODE14
- Review
overview.md and INLINECODE16 - Commit to git and publish to ClawHub
Learn more: https://expertpack.ai • ClawHub expertpack skill
See also: Self-Improving Agent skill on ClawHub.
自我改进代理 → ExpertPack
将自我改进代理技能的.learnings/目录（3.8K ClawHub安装量）转换为结构化的ExpertPack。
支持的来源：
- - LEARNINGS.md — 修正、知识缺口、最佳实践、简化与强化模式
- ERRORS.md — 命令失败、异常、集成问题
- FEATURE_REQUESTS.md — 用户请求的功能和实现说明
- 已提升内容 — 已提升至CLAUDE.md、AGENTS.md、SOUL.md、TOOLS.md的条目（检测并交叉引用）
使用方法
bash
cd /root/.openclaw/workspace/ExpertPack/skills/self-improving-to-expertpack
python3 scripts/convert.py \
--workspace /path/to/your/workspace \
--output ~/expertpacks/my-learnings-pack \
[--name My Agents Learnings] \
[--type auto|person|agent|process]
使用--learnings /path/to/.learnings覆盖.learnings/位置。
生成内容
符合schema 2.3的完整ExpertPack：
- - manifest.yaml（包含上下文层级、EK存根）
- overview.md，汇总转换信息（条目数量、类别、优先级分布）
- 从学习类型映射的结构化目录：
- mind/ — 最佳实践、约定、行为模式、提升规则
- facts/ — 填补的知识缺口、项目特定事实
- operational/ — 错误解决方案、工具陷阱、集成修复
- summaries/ — 模式分析、重复问题总结
- relationships/ — 相关条目之间的交叉引用
- - _index.md文件、主要摘要、glossary.md（如果找到术语/标签）
- relations.yaml（来自另请参阅链接和共享标签）
- 干净的去重，优先级：已提升 > 已解决 > 待处理
自动剥离机密信息（sk-、ghp_、令牌、密码）。发现任何机密信息时发出警告。
转换后步骤
- 1. cd ~/expertpacks/my-learnings-pack
- 验证每个内容文件为400–800个令牌（Schema 2.5 — 设计为可检索）
- 测量EK比率：python3 /path/to/expertpack/tools/eval-ek.py .
- 检查overview.md和manifest.yaml
- 提交到git并发布到ClawHub
了解更多： https://expertpack.ai • ClawHub expertpack技能
另请参阅： ClawHub上的自我改进代理技能。
