json-canvas

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

1.12x

Quality

88%

Does it follow best practices?

Impact

96%

1.12x

Average score across 3 eval scenarios

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 highly actionable, well-structured format reference with complete examples and an explicit validation checklist, though it runs long: the When-to-Use section duplicates the description and the example section could be halved or split out. Token efficiency is the main drag on an otherwise strong body.

Suggestions

Remove the "When to Use This Skill" section — it duplicates the frontmatter description that already governs triggering, and trim the Overview to one line.

Cut the four complete examples down to two (one node/edge showcase and one group-based board) and move the rest to a references/EXAMPLES.md, keeping SKILL.md to the spec tables and validation rules.

Drop the "ID Generation" prose and fold the 16-char hex format into the Validation Rules section to avoid restating spec details across sections.

Dimension	Reasoning	Score
Conciseness	The attribute tables and enum references are tight, but the "When to Use This Skill" section duplicates the frontmatter description, the Overview restates known context ("JSON Canvas is an open file format for infinite canvas data"), and four complete JSON examples (~250 lines) pad the budget where two would cover the cases. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than anchor 4's 'minor instances'.	3 / 5
Actionability	Complete, copy-paste-ready JSON examples for every node type and edge, required/optional attribute tables, valid enum values, and numeric layout guidance (sizes, spacing) fully cover the common cases. Nothing is pseudocode or abstract, so anchor 5 fits rather than anchor 4's 'minor gaps'.	5 / 5
Workflow Clarity	This is a single-purpose format skill where the single action — construct a valid .canvas file — is unambiguous, and the 8-rule "Validation Rules" section plus the ID-uniqueness guidance serve as an explicit checklist, so the simple-skill exception applies. It is not a 4 because no validation checkpoint is missing; the validation rules are explicit and numbered.	5 / 5
Progressive Disclosure	Sections are well-organized with clear headers, tables, and an in-file References section linking the external spec, and the core reference content is appropriately placed inline. It is not a 5 because ~560 lines are fully inlined with no bundle files — the four complete examples are a clear candidate for a separate EXAMPLES.md — though structure and navigation are good, matching anchor 4's 'minor organization gaps'.	4 / 5
	Total	17 / 20 Passed

Description

95%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 description: it states concrete capabilities in third person, includes the file extension, synonyms, and host application as triggers, and explicitly separates what the skill does from when to use it. The only weakness is modest breadth in the action list (create/edit only).

Dimension	Reasoning	Score
Specificity	"Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections" lists several concrete actions with the object types they apply to, matching the 'several specific actions; minor gaps' anchor. It falls short of anchor 5 only because more advanced operations (e.g., parsing, validating, or editing existing canvas structure) are not enumerated.	4 / 5
Completeness	It explicitly answers both what ("Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections") and when ("Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian") with concrete trigger phrases, exactly matching the anchor 5 example pattern. Anchor 4 is ruled out because the 'when' clause is fully explicit, not merely present.	5 / 5
Trigger Term Quality	The description covers ".canvas files", "visual canvases", "mind maps", "flowcharts", and "Canvas files in Obsidian" — natural synonyms, the file extension, and the host application — matching the comprehensive-coverage anchor. It is not a 4 because no natural phrasing a user would plausibly say is missing.	5 / 5
Distinctiveness Conflict Risk	"JSON Canvas files (.canvas)" plus Obsidian-specific triggers establish a clear niche with minimal conflict risk against generic document or diagram skills. It is not a 4 because the .canvas extension and Obsidian mention make cross-triggering with other skills very unlikely.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (570 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/json-canvas/SKILL.md
Commit: b90e2de

Reviewed: 6 hours 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.