json-canvas

产品经理与内容创作者在构建Obsidian知识库或梳理复杂逻辑时，当需要创建思维导图、流程图等可视化画布，使用此技能可自动生成标准.canvas文件，精准配置节点、连线与层级，一键生成完美排版，彻底告别手写JSON的繁琐与报错。

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/obsidian-skills-integrated/json-canvas/SKILL.md

The canonical home for this skill is json-canvas in kepano/obsidian-skills

Quality

Content

71%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 thorough, highly actionable JSON Canvas reference with executable examples for every construct and a solid validation checklist, but it is over-long for a SKILL.md: four full canvas examples inflate token cost and everything is inlined with no progressive disclosure into bundle files.

Suggestions

Move three of the four complete-canvas examples into a separate `references/examples.md` and keep only one inline quick-start example in SKILL.md.

Add an explicit validation workflow step (generate → check the 8 validation rules → fix and re-check) to convert the rules into a feedback loop.

Consider extracting the full attribute tables and enum value lists into a `references/spec.md`, leaving SKILL.md as a concise overview pointing to it.

Dimension	Reasoning	Score
Conciseness	The body is a dense ~650-line spec reference; while it avoids explaining concepts Claude already knows, it includes four large complete-canvas examples (Simple, Project Board, Research, Flowchart) where one or two would suffice, so it could be tightened noticeably.	3 / 5
Actionability	Provides complete, copy-paste-ready JSON for every node type, edges, colors, plus four full executable canvases and attribute tables with required/optional/type — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	The single generation action is unambiguous and a "Validation Rules" section lists 8 explicit checks (unique ids, valid fromNode/toNode references, allowed type/color/style enums), but there is no explicit generate→validate→fix feedback-loop sequence.	4 / 5
Progressive Disclosure	Sections are clearly headed and the external References section points one level to the authoritative spec, but there are no bundle files and the four full multi-example canvases are inlined monolithically where they could live in a separate examples file.	3 / 5
	Total	15 / 20 Passed

Description

78%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 specific, well-targeted to a distinct niche, and covers both what and when, but is padded with marketing fluff and over-claims ("一键生成完美排版", "彻底告别手写JSON的繁琐与报错") that the rubric penalizes. Third-person voice ("使用此技能") is correctly used.

Suggestions

Trim marketing language such as "一键生成完美排版" and "彻底告别手写JSON的繁琐与报错"; keep factual capability statements.

Reframe the "when" guidance as an explicit "Use when..." clause listing concrete triggers (e.g., "Use when creating mind maps, flowcharts, or other visual canvases in Obsidian, or when the user asks for a .canvas file").

Add common synonyms/file extensions ("canvas file", ".canvas", "Obsidian canvas") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "自动生成标准.canvas文件", "精准配置节点、连线与层级", "一键生成完美排版" — but marketing over-claims ("一键生成完美排版", "彻底告别...繁琐与报错") dilute precision, keeping it just below a 5.	4 / 5
Completeness	Explicitly answers both what (generate/configure .canvas files with nodes, edges, hierarchy) and when ("当需要创建思维导图、流程图等可视化画布" / "在构建Obsidian知识库或梳理复杂逻辑时"), but the trigger guidance is embedded in marketing prose rather than crisp "Use when..." phrasing.	4 / 5
Trigger Term Quality	Includes natural user terms like "思维导图", "流程图", "可视化画布", "Obsidian知识库", and ".canvas文件", giving good keyword coverage with only minor variations missing, but the framing is scenario-based rather than a clean trigger phrase list.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche — Obsidian `.canvas` files — with distinct, format-specific triggers and minimal risk of colliding with other skills.	5 / 5
	Total	17 / 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
skill_md_line_count	SKILL.md is long (657 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: anbeime/skill
Path: skills/obsidian-skills-integrated/json-canvas/SKILL.md
Commit: d9e888d

Reviewed: 3 days 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.