# Canvas Ops

> Operational guidance for Cursor's Canvas artifacts. Activates when producing data-heavy, structured, or analytical outputs that benefit from rich formatting.

- Skill: `mike-diff/canvas-ops` (Agent Skill)
- Install (CLI): `npx skillmds@latest add mike-diff/canvas-ops`
- Raw SKILL.md: https://api.skillmd.com/api/skills/mike-diff/canvas-ops/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: mike-diff (https://skillmd.com/u/mike-diff)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/mike-diff/canvas-ops

---


# Canvas — Structured Output Artifacts

Guidance for using Cursor's Canvas for rich, structured deliverables.

## When to use

- Architecture reviews and decision records
- Audit reports with tables and cross-references
- Timelines, roadmaps, and milestone tracking
- Data analysis with charts or structured findings
- Any output that benefits from rich formatting beyond markdown chat

## How it works

1. Canvas artifacts are rendered as dedicated documents in Cursor
2. They support rich formatting, tables, and structured layouts
3. Canvas outputs are saved and can be referenced later

## Best practices

- Prefer canvas over chat for any deliverable exceeding ~200 words
- Use canvas for outputs stakeholders might review
- Structure canvas content with clear sections and summaries
- Keep chat for iteration; use canvas for the final product