canvas

Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, safety-conscious skill body with strong workflow sequencing and validation for destructive canvas mutations, plus well-signaled external references. Minor trimming of discursive passages and showing the transaction-bundle construction as code would lift it to the top anchor.

Suggestions

Tighten the link-node egress paragraph and 'Choose the syntax source' section to the essential rule, removing explanatory framing.

Show the claude-obsidian.transaction.v1 bundle construction as a concrete example instead of only describing it.

Consider moving the inline JSON Canvas node-type/field spec detail into references/canvas-spec.md to sharpen the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's knowledge of JSON Canvas, but the link-node egress paragraph and 'Choose the syntax source' section are mildly discursive and could be tightened, landing just below the top anchor.	4 / 5
Actionability	Concrete bash commands, a real JSON example, a validation checklist, and a specific ID format give mostly executable guidance; minor gaps remain because bundle construction is described rather than shown and commands use placeholders (BUNDLE/VAULT/APPROVAL_SHA256).	4 / 5
Workflow Clarity	Numbered draft steps, an explicit pre-apply validation checklist, an inspect→apply flow gated on an approval SHA-256, and explicit consent for destructive changes provide clear sequencing with validation checkpoints and a fix-and-retry loop, so the destructive-operation 3-cap does not apply.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references (references/canvas-spec.md is a real bundled file, plus the upstream json-canvas skill and operation-transactions.md) and clean sectioning, but only one bundled reference and some spec detail inlined in the body keep it just below the top anchor.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: third-person voice, concrete actions, comprehensive node coverage, explicit 'Use for' triggers with natural phrasing and file extension, and a clearly distinct niche. It hits the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Create, inspect, and update') plus comprehensive node-type coverage ('text, file, link, group, and edge nodes'), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (create/inspect/update Obsidian JSON Canvas boards with node types) and 'when' ('Use for …' with concrete request phrases like 'create canvas, add to canvas, or put this on the canvas').	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms ('canvas status', 'canvas lists', 'visual maps', 'zones', 'spatial layouts') and the '.canvas' file extension, matching the synonyms-and-extensions anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Obsidian JSON Canvas, .canvas files) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: AgriciDaniel/claude-obsidian
Path: skills/canvas/SKILL.md
Commit: 32ac5a0

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.