docs-canvas

An agent skill by cursor, from cursor/plugins. Tags: architecture, documentation, documents, presentation, ui.

What it does

Render a documentation-style Cursor Canvas that organizes architecture notes, API references, walkthroughs, and how-tos into a navigable layout with sections, tables of contents, and cross-references. Use when the user asks for a docs canvas, documentation overview, architecture walkthrough, API reference page, or wants to render structured documentation as an interactive canvas.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cursor/plugins --skill docs-canvas

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/docs-canvas/skills/docs-canvas ~/.claude/skills/docs-canvas

Safety box score

Grade B, low risk: 14 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a documentation-canvas formatter: it reads docs, code references, and optionally a doc URL, then lays them out as an interactive canvas. The main security-relevant reach is read access outside the workspace to `~/.cursor/...` guidance/type files and possible network access when the source is a URL; it does not itself show execution, secret handling, or destructive actions.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No shell commands, scripts, or code evaluation are defined in `SKILL.md`; it only describes how to structure documentation.
Network access	1 (low)	It explicitly accepts "a single doc URL," so using the skill can involve fetching remote content, but the file does not describe any data exfiltration.
Filesystem reach	2 (moderate)	The skill directs the agent to read files outside the project in the home directory, including `~/.cursor/skills-cursor/canvas/SKILL.md` and sibling `.d.ts` files.
Secrets & credentials	0 (none)	There is no instruction to read tokens, keys, passwords, `.env` files, browser sessions, or other credential stores.
Privilege & persistence	0 (none)	The skill does not request sudo, global installs, service registration, shell startup edits, or other privilege changes.
Instruction hijack surface	0 (none)	The text contains normal guidance for building a docs canvas and does not tell the agent to ignore rules, hide actions, or follow remote instructions.
Irreversible actions	0 (none)	It is a rendering/organization skill only; it does not instruct the agent to publish, send, deploy, pay, or delete anything.
Transparency	1 (low)	The file is a "placeholder" and defers key behavior to external files under `~/.cursor/...`, so some of the effective behavior is not visible in the package here.

Before installing

Inspect `~/.cursor/skills-cursor/canvas/SKILL.md` and the referenced `.d.ts` files before enabling it.
Test it first on a local markdown folder, not a URL, so you can see whether it makes any network requests.
Confirm you are comfortable granting read access to `~/.cursor/` dot-directories from the agent.

Rated 2026-10-16 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: docs-canvas/skills/docs-canvas/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

google-docs — Author and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers.
how — Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live".
design-md — Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files
diagramming-code — Generates Mermaid diagrams from Trailmark code graphs.
guidelines-advisor — Smart contract development advisor based on Trail of Bits' best practices.
sales-enablement — When the user wants to create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts.