CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/json-canvas/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A thorough, highly actionable JSON Canvas reference with complete examples and validation rules, but it is verbose and monolithic. Consolidating redundant examples and splitting the spec into reference files would improve token efficiency and navigation.

Suggestions

Reduce the four full canvas examples to one canonical example plus brief inline snippets, cutting redundant demonstrations of the same node/edge concepts to improve conciseness.

Add a short sequenced workflow (e.g. 1. lay out nodes with coordinates, 2. connect with edges, 3. run the validation checklist, 4. fix and re-check) with an explicit validation checkpoint/feedback loop.

Move the detailed attribute tables and full example library into a references file (e.g. references/canvas-spec.md) and keep SKILL.md as a concise overview that links to it, improving progressive disclosure.

DimensionReasoningScore

Conciseness

The JSON Canvas schema reference is genuinely useful domain knowledge Claude lacks, but four large complete examples (simple canvas, project board, research canvas, flowchart) are largely redundant demonstrations of the same concepts and the overall length could be tightened.

2 / 3

Actionability

Provides complete, valid, copy-paste-ready JSON examples plus attribute tables with required/optional/type and eight explicit validation rules, so a reader can produce correct .canvas files directly.

3 / 3

Workflow Clarity

A Validation Rules section exists as a checklist, but there is no sequenced create→connect→validate workflow with explicit checkpoints or a validate→fix→retry feedback loop for the creation task.

2 / 3

Progressive Disclosure

Internal sectioning is clean (nodes, edges, colors, examples, validation), but it is a single ~640-line monolithic file with no bundle files; the spec reference and example library are content that could be split into separate reference files.

2 / 3

Total

9

/

12

Passed

Description

90%

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, well-formed description with explicit what/when triggers, natural trigger terms, and a clear niche. Its only gap is that the action verbs are limited to generic create/edit rather than a richer set of specific capabilities.

DimensionReasoningScore

Specificity

Names concrete domain objects ("nodes, edges, groups, and connections") but only offers two generic verbs ("Create and edit"), so it lists the domain and some actions rather than the multiple distinct concrete actions the top anchor requires.

2 / 3

Completeness

Explicitly answers what ("Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections") and when ("Use when working with .canvas files..."), matching the top anchor's what+trigger structure.

3 / 3

Trigger Term Quality

".canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian" gives good natural coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to .canvas/Obsidian JSON Canvas with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (643 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
heyitsnoah/claudesidian
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.