build-and-compile
Building, compiling, and resolving dependency issues across languages
Best practices for creating research diagrams with Excalidraw MCP tools
$ npx -y skills add vstorm-co/pydantic-deepagents --skill diagram-design --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/diagram-designContext preview
The summary Claude sees to decide when to auto-load this skill.
Best practices for creating research diagrams with Excalidraw MCP tools
name: diagram-design description: Best practices for creating research diagrams with Excalidraw MCP tools
Create a diagram when your research findings involve:
1. **Plan the diagram** — decide type, elements, and layout before creating 2. **Create elements** — use `create_element` or `batch_create_elements` 3. **Arrange** — use `align_elements` and `distribute_elements` for clean layout 4. **Inspect** — use `describe_scene` to verify the diagram looks right 5. **Adjust** — use `update_element` to fix positioning or text 6. **Group** — use `group_elements` to lock related items together
> **Note:** Do NOT export or share links — the user sees a live embedded canvas that auto-syncs.
Use consistent colors across diagrams:
| Purpose | Color | Hex | |---------|-------|-----| | Primary concepts | Blue | #1971c2 | | Positive / supported | Green | #2f9e44 | | Negative / limitations | Red | #e03131 | | Warning / caveats | Orange | #e8590c | | Neutral / context | Gray | #868e96 | | Highlight / focus | Yellow | #f08c00 |
[Option A] [Option B] [Option C] | | | [Pros] [Pros] [Pros] [Cons] [Cons] [Cons] | | | └──── [Verdict] ─────────┘
┌─────────────────────────────┐ │ [System Name] │ │ ┌──────┐ ┌──────┐ │ │ │Comp A│──│Comp B│ │ │ └──────┘ └──┬───┘ │ │ │ │ │ ┌────▼────┐ │ │ │ Comp C │ │ │ └─────────┘ │ └─────────────────────────────┘
[2020]──[2021]──[2022]──[2023]──[2024]──[2025] │ │ │ │ │ │ Event Event Event Event Event Event
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
Repo: vstorm-co/pydantic-deepagents
Building, compiling, and resolving dependency issues across languages
Working with diverse data formats: binary, text, structured, and custom
Systematic exploration of unknown environments before starting work
Writing efficient code that handles large data and tight constraints