hm-framework-skill
Skill0 starsChanged 4 months agoNo licenceView on GitHub
OpenHarmony (鸿蒙) 服务层/框架层代码仓库架构与命名规范领域知识。 适用于识别、导航、分析和创建符合 OpenHarmony 分层架构标准的代码仓库。 当用户需要以下任一场景时使用此 Skill： (1) 分析 OpenHarmony 服务层或框架层代码仓库的目录结构与命名约定， (2) 判断一个仓库是否符合 OpenHarmony foundation 分层架构规范（subsystem/component 路径模式）， (3) 理解 bundle.json 组件描述符与 GN 构建系统的路径映射关系， (4) 在 OpenHarmony 项目内新增组件、服务或接口时遵循正确的命名格式, (5) 理解 frameworks/ vs services/ vs interfaces/ vs common/ 的分层职责边界。
In this repository89 other files it gives its agents.
- vercel-react-best-practices/AGENTS.mdAGENTS.md
- 3d-cad-skillSkill
- agent-browserSkill
- arkts-skillSkill
- autoresearchSkill
- baoyu-post-to-wechatSkill
- blogwatcherSkill
- canvasSkill
- chrome-cdpSkill
- cii-skillSkill
- claudeceptionSkill
- clawdhubSkill
- coding-agentSkill
- c-skillSkill
- discordSkill
- distributed-systemsSkill
- docxSkill
- ebookSkill
- elf-patcherSkill
- embodied-intelligence-skillSkill
- excalidraw-diagramSkill
- fanqie-publishSkill
- fetch-skill-and-then-write-skillSkill
- fetch-skillSkill
- frontend-slidesSkill
- geminiSkill
- gifgrepSkill
- githubSkill
- git-wtSkill
- harmonyos-code-reviewSkill
- harmonyos-linux-cli-devSkill
- hm-fetch-skillSkill
- hm-napi-skillSkill
- hm-sa-skillSkill
- humanizerSkill
- ian-gemini-webSkill
- kernel-dev-skillSkill
- docxSkill
- macos2linuxappSkill
- macos-menubar-tuist-appSkill
- matecodeSkill
- medialibrary-ut-generatorSkill
- mermaid-validatorSkill
- mobai-reverseSkill
- model-usageSkill
- modern-bashSkill
- modern-c-devSkill
- modern-c-makefileSkill
- moonbitSkill
- nano-pdfSkill
- notebooklmSkill
- notionSkill
- obsidian-plugin-devSkill
- obsidianSkill
- openai-image-genSkill
- openai-whisperSkill
- pack-skillSkill
- paddleocr-doc-parsingSkill
- paper2codeSkill
- pdfSkill
- The first 60 shown.
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.