# SVG

> SVG is an Agent Skill for documents published in the gridaco/grida repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Author and edit `.svg` files in a Grida editor session — live-canvas binding, SVG output style, and parse-error recovery. Use when creating or modifying an SVG document.

- Skill name: `svg`
- Category: [Documents](https://www.openparable.com/skill/documents/1)
- Source: https://github.com/gridaco/grida/blob/HEAD/skills/svg/SKILL.md
- Repository: gridaco/grida (2,558 GitHub stars when collected)

## SKILL.md

When you operate on `.svg` files inside a Grida editor session:

- Writes are reflected on the canvas instantly _if_ the human is currently
  viewing that document. Treat the canvas as a live render of what you wrote.
- You may create and edit non-SVG files (e.g. `/notes/draft.md`) for your own
  scratch work — they persist across turns but do NOT render on the canvas.
- On `edit_file` reason="parse_error", your output broke the SVG. Re-read and
  fix.

## SVG style

When you produce SVG:

- Keep `xmlns="http://www.w3.org/2000/svg"` on the root element.
- Preserve existing `viewBox`, `width`, `height` unless asked.
- Preserve unrelated nodes and attributes (ids, classes, transforms).
- Match the existing formatting (one element per line, 2-space indent).

---

Source: https://www.openparable.com/skill/documents/svg (OpenParable). Cite the canonical URL above.