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

88%

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

88%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 tight, highly operational skill body with a well-sequenced, validation-gated mutation workflow and real bundle references. Slight improvements available in making the PRODUCT_ROOT resolution fully copy-paste and pushing more spec detail into the reference file.

Suggestions

Make the PRODUCT_ROOT resolution actionable: provide a concrete command to detect the installed claude-obsidian root instead of the /absolute/path/to/installed placeholder.

Move the inline JSON Canvas node-positioning spec (20px padding, 40px gaps, z-order) into references/canvas-spec.md and keep SKILL.md focused on workflow and transaction safety.

Add a brief validation feedback loop example showing a failed `transaction inspect` output and the re-draft/re-inspect recovery path.

Dimension	Reasoning	Score
Conciseness	Lean, dense body that assumes Claude's competence — no padding about what JSON/canvas/Obsidian are; every line is operational (scope rules, validation checks, transaction commands). Below a 5 only on padding, and there is essentially none.	5 / 5
Actionability	Concrete executable bash (transaction inspect/apply), a real minimal JSON node example, and exact validation rules; the PRODUCT_ROOT path remains a placeholder users must resolve, leaving a minor gap versus copy-paste-ready.	4 / 5
Workflow Clarity	Destructive mutation workflow is explicitly sequenced (read+record SHA-256 → draft → validate → inspect bundle → apply with approved sha) with validation checkpoints and a consent gate for destructive changes, satisfying the destructive-ops requirement rather than being capped at 3.	5 / 5
Progressive Disclosure	Well-organized sections with one-level-deep references (references/canvas-spec.md, which exists) and a clear deference to an upstream json-canvas skill for format details; the body still inlines a fair amount of spec detail (node rules, positioning) rather than fully pushing it to the reference, keeping it just short of a 5.	4 / 5
	Total	18 / 20 Passed

Description

88%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.

A strong, specific description covering what the skill does across all node types and when to use it with natural trigger phrases. Minor keyword expansion (e.g., .canvas extension) could push trigger quality to a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Create, inspect, and update... boards') across all node types (text, file, link, group, edge), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (create/inspect/update JSON Canvas boards with named node types) and 'when' ('Use for canvas status, canvas lists... and requests such as create canvas, add to canvas...').	5 / 5
Trigger Term Quality	Strong natural triggers ('canvas status', 'canvas lists', 'visual maps', 'create canvas', 'add to canvas', 'put this on the canvas'); missing the .canvas file extension and a few synonyms, so just short of a 5.	4 / 5
Distinctiveness Conflict Risk	Narrow niche (Obsidian JSON Canvas / .canvas files) with distinctive triggers unlikely to collide with other skills; minimal conflict risk.	5 / 5
	Total	19 / 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: ad67087

Reviewed: 10 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.