Name: json-canvas
Rating: 75.2 (1 reviews)
Author: administrakt0r

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.

Quality

93%

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

The canonical home for this skill is json-canvas in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

92%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.

The body is a well-organized, actionable reference: executable JSON examples for every construct, four workflows each with explicit validation, a validation checklist with recovery hints, and a single one-level-deep reference to EXAMPLES.md. It is only slightly verbose in a few introductory sentences that restate what Claude already knows.

Suggestions

Trim definitional asides like "Nodes are objects placed on the canvas" and "Groups are visual containers for organizing other nodes" — the tables that follow already convey this.

Consider moving the full Colors and Layout Guidelines tables into a reference file to further slim the core SKILL.md, keeping only the essentials inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — attribute tables, compact JSON snippets, and targeted pitfall notes like the newline warning — with only minor over-explanation such as "Groups are visual containers for organizing other nodes" that assume knowledge Claude already has.	4 / 5
Actionability	Each node type and edges have copy-paste-ready JSON examples with concrete IDs, coordinates, and field values, plus a colors preset table, ID-generation samples, and a pixel-based layout table — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Four numbered workflows (create, add node, connect, edit) each close with an explicit "Validate" step, and a final 8-point Validation Checklist with error-recovery guidance provides the feedback loop this file-editing skill requires.	5 / 5
Progressive Disclosure	The SKILL.md body is a well-sectioned overview that offloads full canvas examples to a clearly signaled one-level reference (references/EXAMPLES.md, verified to exist) and links the external spec, keeping navigation shallow and easy.	5 / 5
	Total	19 / 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.

The description is strong: third-person voice, concrete object types, explicit "Use when" triggers with synonyms and file extensions, and a clearly distinct niche around .canvas/Obsidian Canvas files. The only minor gap is the narrowness of action verbs (create/edit) versus a broader action inventory.

Dimension	Reasoning	Score
Specificity	"Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections" names the domain and several concrete object types the actions operate on, but the action verbs are limited to create/edit, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	It explicitly states what the skill does ("Create and edit JSON Canvas files...") and gives a concrete "Use when..." trigger clause listing multiple scenarios, satisfying both what and when.	5 / 5
Trigger Term Quality	"Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian" covers natural synonyms, the file extension, and concrete use-case terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The niche is sharply defined by the .canvas extension and Obsidian Canvas context, with distinct triggers that minimize overlap with other skills.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/json-canvas/SKILL.md
Commit: debb2ec

Reviewed: 1 day 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.