Claude Skill
Sibo-Zhao/OpenPraxis
OpenPraxis 是一个原生 OpenClaw 的知识保留技能,能将原始输入转化为结构化练习,帮助你真正运用所学知识,而不仅仅是存储。
概览
仓库信息
安装这个 Skill
pip install openpraxisRegistry 信息
pip install openpraxisgit clone https://github.com/Sibo-Zhao/OpenPraxis.gitpip install -e ".[dev]"
项目简介
OpenPraxis 是一个原生 OpenClaw 的知识保留技能,能将原始输入转化为结构化练习,让你真正运用所学知识,而不仅仅是存储它们。
An OpenClaw-native knowledge retention skill that turns raw inputs into structured practice so you can use what you know, not just store it.
要点
- 与 OpenClaw 原生集成,实现无缝知识保留
- 将原始输入转化为结构化、可操作的练习
- 注重主动运用而非被动存储
- 使用 Python 构建,易于扩展和定制
使用场景
- 从文章或研究论文中保留关键见解
- 将会议笔记转化为可操作的练习项
- 强化在线课程或教程的学习效果
- 通过主动回忆构建个人知识库
README 摘要
# OpenPraxis An OpenClaw-native knowledge retention skill that turns raw inputs into structured practice so you can use what you know, not just store it. **OpenClaw users**: zero extra API key configuration — the host agent's model is reused automatically. **Standalone CLI users**: configure your own provider with `praxis llm setup`. ## Requirements - Python 3.11+ ## OpenClaw Users: Zero-Config Path When running as an OpenClaw skill, OpenPraxis delegates all LLM calls to the host agent. No local API key is needed. ```bash pip install openpraxis export OPENPRAXIS_MODE=openclaw ``` Then use the skill directly from your OpenClaw agent — import knowledge, generate practice, evaluate answers, and produce insight cards. See `openclaw-knowledge-coach/SKILL.md` for the full skill workflow. ## Standalone CLI Users: Manual Setup For use outside of OpenClaw, configure your own provider and API key: ```bash pip install openpraxis praxis llm setup praxis llm show ``` Or install from source (for development): ```bash git clone https://github.com/Sibo-Zhao/OpenPraxis.git cd OpenPraxis pip install -e ".[dev]" ``` Supported providers: - `openai` (default): native structured output parse - `doubao`: native structured output parse - `kimi` / `deepseek`: JSON mode + Pydantic validation API key env vars (higher priority than config file): - `OPENAI_API_KEY` for `openai` - `ARK_API_KEY` for `doubao` - `MOONSHOT_API_KEY` for `kimi` - `DEEPSEEK_API_KEY` for `deepseek` ## Usage ```bash praxis add <file> [--type report|interview|reflection|idea] praxis practice <input_id> praxis answer <scene_id> [--editor] [--file <path>] praxis insight [<input_id>] [--type <insight_type>] [--min-intensity <n>] praxis show <id> praxis export [--format md|json] [--output <path>] praxis list [
话题
暂无话题