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.
Install with Tessl CLI
npx tessl i github:davepoon/buildwithclaude --skill json-canvas86
Quality
82%
Does it follow best practices?
Impact
96%
1.12xAverage score across 3 eval scenarios
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 a well-crafted skill description that excels across all dimensions. It provides specific capabilities (nodes, edges, groups, connections), includes natural trigger terms users would actually say (mind maps, flowcharts, Obsidian), and has an explicit 'Use when...' clause. The mention of Obsidian and the .canvas file extension makes 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' - clearly describes the file format and structural elements involved. | 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 | Excellent coverage of natural terms users would say: '.canvas files', 'visual canvases', 'mind maps', 'flowcharts', 'Canvas files in Obsidian' - includes file extension, use cases, and the specific application context. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with distinct triggers - the combination of '.canvas' file extension, 'JSON Canvas', and 'Obsidian' creates a very specific domain that is unlikely to conflict with general diagramming or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid reference skill with excellent actionability - the JSON examples are complete, executable, and cover diverse use cases. However, it's overly long for a SKILL.md file, lacking workflow guidance for validation/error handling, and would benefit from splitting detailed examples and reference tables into separate files.
Suggestions
Add a validation workflow section: how to verify JSON is valid, common errors to check for, and what to do if the canvas doesn't render correctly in Obsidian
Move the 4 complete example canvases to a separate EXAMPLES.md file and reference it from the main skill
Consider moving detailed attribute tables to a REFERENCE.md file, keeping only essential quick-reference info in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy - the extensive examples section could be trimmed, and some tables repeat information that could be consolidated. The overview section adds minimal value beyond what the title conveys. | 2 / 3 |
Actionability | Excellent actionability with fully executable JSON examples for every node type, edge configuration, and complete canvas structures. All examples are copy-paste ready and cover diverse use cases (mind maps, project boards, flowcharts). | 3 / 3 |
Workflow Clarity | While the format specification is clear, there's no explicit workflow for creating/editing canvas files - no validation steps, no guidance on how to verify the JSON is valid before saving, and no error recovery guidance for malformed canvases. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is in one monolithic file. The extensive examples section (4 complete canvases) could be split into a separate EXAMPLES.md file, and the detailed attribute tables could be in a REFERENCE.md. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- 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.