create-skill
The create-skill resource provides a standardized framework for developing new Agent Skills, including required directory structure, frontmatter metadata, and content organization guidelines. Use this when building custom skills for the aiskillstore marketplace to ensure consistency, maintainability, and proper documentation across all skill implementations.
git clone --depth 1 https://github.com/aiskillstore/marketplace /tmp/create-skill && cp -r /tmp/create-skill/skills/0xmsc/create-skill ~/.claude/skills/create-skillSKILL.md
# Create Skill ## Skill Structure ``` skill-name/ ├── SKILL.md # instructions + metadata ├── scripts/ # executable code (optional) ├── references/ # documentation (optional) └── assets/ # templates/resources (optional) ``` ## Requirements - **Frontmatter**: Must include `name` (lowercase-alphanumeric) and `description`. - **Description**: Must include **what** it does and **when** to use it. - **Body**: Keep under 500 lines. Use imperative language. - **Resources**: Move detailed docs to `references/` and code to `scripts/`. ## Process 1. **Directory**: `mkdir <name>`. Create `scripts/`, `references/`, or `assets/` only if you actually have content for them. 2. **Metadata**: Write the `SKILL.md` frontmatter first. 3. **Resources**: Implement scripts and test them. 4. **Instructions**: Write concise steps in `SKILL.md` body. 5. **Verify**: Ensure frontmatter name matches directory name. ## References - [Full Specification](references/specification.md) - [Design Patterns](references/what-are-skills.md)
Let Codex use Google Antigravity CLI (agy) for repository exploration, bounded feature work, and project-scale implementation. Use when a Codex task benefits from delegated repository work while Codex retains diff review, verification, repair, and delivery assurance.
Use when replying. Refresh current date and time.
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid.
Design systems, plan implementations, review architecture decisions - Use when you need to plan a complex feature, design system architecture, or make high-level technical decisions.
Use when automating iOS Simulator interactions, capturing screenshots/video, or inspecting accessibility via AXe CLI.
Use when working with Canton Network participants, DAML smart contracts, Splice applications, or debugging LF version and package ID issues.
>
HSK4級レベルから流暢さを目指す学習者向け。中国語表現の使用場面・自然さを分析し、作文を「ネイティブらしい流暢な表現」に改善。bilibili等のコンテンツ理解とネイティブとの会話をサポート。実際の用例をWeb検索で提示