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.
92
88%
Does it follow best practices?
Impact
100%
1.08xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the key criteria. It provides specific capabilities (create/edit with nodes, edges, groups, connections), includes natural trigger terms (mind maps, flowcharts, Obsidian, .canvas), and has an explicit 'Use when' clause covering multiple realistic user scenarios. The Obsidian context and .canvas file extension make it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections.' This names the format, file extension, and specific structural elements. | 3 / 3 |
Completeness | Clearly answers both what ('Create and edit JSON Canvas files 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'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: '.canvas files', 'visual canvases', 'mind maps', 'flowcharts', 'Canvas files', 'Obsidian', 'JSON Canvas'. Good coverage of both technical and natural terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: JSON Canvas / .canvas files in Obsidian. The specific file format, extension, and application context (Obsidian) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides clear workflows with validation checkpoints and concrete, executable JSON examples for all canvas element types. Its main weakness is moderate verbosity — some tables and explanations could be tightened — and the referenced EXAMPLES.md file is not present in the bundle. Overall it serves as an effective reference for creating and editing JSON Canvas files.
Suggestions
Trim the layout guidelines section — suggested dimensions table and basic coordinate system explanation could be condensed since Claude can infer reasonable defaults
Provide the referenced references/EXAMPLES.md file in the bundle, or inline one compact complete example instead of deferring all examples to a missing file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and well-structured with tables and code examples, but includes some information Claude would already know (like JSON basics, what Markdown is) and the layout guidelines section with suggested dimensions adds bulk that could be more compact. The tables are a good format choice but the overall length (~180 lines) could be tightened. | 2 / 3 |
Actionability | Provides fully executable JSON examples for every node type and edges, concrete attribute tables with types and defaults, specific ID generation format (16-char hex), exact spacing values, and a complete validation checklist. All examples are copy-paste ready JSON. | 3 / 3 |
Workflow Clarity | All four workflows (create, add node, connect nodes, edit) have clear numbered sequences with explicit validation steps at the end of each workflow. The validation checklist provides a comprehensive feedback loop for error detection and recovery, including specific things to check when validation fails. | 3 / 3 |
Progressive Disclosure | The skill references 'references/EXAMPLES.md' for complete canvas examples, which is good progressive disclosure, but no bundle files were provided so this reference is unverifiable. The main content is fairly long and some reference material (like the full attribute tables for every node type) could potentially be split out, though the inline tables are reasonably organized. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- kepano/obsidian-skills
- Commit
ac93987
- Reviewed
Table of Contents
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.