excalidraw-diagram-generator

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./app/skills/excalidraw-diagram-generator/SKILL.md

Quality

Content

63%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 delivers genuinely actionable, well-sequenced guidance with concrete commands, layout values, and a validation checklist, and its external references are mostly real and one level deep. It is held back by a padded, partially duplicated icon-library section, three referenced template files missing from the bundle, and the absence of a single fully-populated element JSON example on the main generation path.

Suggestions

Deduplicate the Icon Libraries section: remove the repeated request line and 'Recommended Workflow' header in the AWS example, collapse the manual-integration warnings into a single caution, and move the ~280-line library setup instructions into a separate reference file (e.g. references/icon-libraries.md) with a short pointer from SKILL.md.

Fix the broken references: either add the three missing template files (templates/flowchart-template.json, templates/relationship-template.json, templates/mindmap-template.json) or remove them from the References section.

Add one complete worked example to the main workflow — a small fully-populated .excalidraw element (e.g. a rectangle with x/y/width/height/strokeColor/fontFamily 5 and an arrow with points) — so the primary generation path is executable without opening the reference files, and make script paths consistent ('scripts/...' vs 'skills/excalidraw-diagram-generator/scripts/...').

Dimension	Reasoning	Score
Conciseness	Mostly operational content Claude would not already know (element properties, fontFamily 5, spacing/color values, script commands), but the ~280-line Icon Libraries section is padded: the "Example: Creating AWS Diagram with Icons" section repeats its request line and "Recommended Workflow (using Python scripts)" header verbatim twice, the manual-integration path restates the token-consumption warning four times, and emoji benefit/challenge lists restate what the commands already demonstrate.	3 / 5
Actionability	Guidance is mostly copy-paste ready: exact script invocations with arguments ("python scripts/add-icon-to-diagram.py my-diagram.excalidraw VPC 250 250"), concrete spacing ("Horizontal gap: 200-300px"), hex colors, the complete output JSON skeleton, and troubleshooting rows. Minor gap: the primary manual-generation path never shows one fully-populated element JSON — the skeleton's elements array is just a comment placeholder and the detailed specs are deferred to the (existing) reference files.	4 / 5
Workflow Clarity	The six-step workflow (understand → choose type → extract info → generate JSON → format → save) is clearly sequenced with a decision table, per-type extraction checklists, and a pre-delivery validation checklist covering overlaps, fonts, connections, and JSON validity. Checkpoints are present but mostly static — the troubleshooting table lists fixes without an explicit validate→fix→retry loop in the workflow itself, which keeps it just below the top anchor.	4 / 5
Progressive Disclosure	A dedicated References section clearly signals one-level-deep pointers and the referenced files (references/excalidraw-schema.md, references/element-types.md, scripts/*) do exist in the bundle, but three of the eight listed references (templates/flowchart-template.json, templates/relationship-template.json, templates/mindmap-template.json) do not exist, and the long optional icon-library setup guide is inlined in SKILL.md rather than split into a separate reference, so structure could be appreciably better organized.	3 / 5
	Total	14 / 20 Passed

Description

87%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.

A strong description that explicitly answers both what the skill does and when to use it, with natural quoted trigger phrases and a distinct Excalidraw-specific identity. The only weakness is that it undersells coverage by naming just 4 diagram types while the body supports 9, missing trigger terms for DFD, swimlane, class, sequence, and ER diagram requests.

Dimension	Reasoning	Score
Specificity	Concrete actions are stated ("Generate Excalidraw diagrams from natural language descriptions", "Outputs .excalidraw JSON files") and capabilities are enumerated ("Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams"), but the description covers only 4 of the 9 diagram types the skill actually supports (no DFD, swimlane, class, sequence, or ER mention), leaving minor gaps in coverage.	4 / 5
Completeness	Both questions are explicitly answered with concrete trigger phrases: what ("Generate Excalidraw diagrams from natural language descriptions... Outputs .excalidraw JSON files that can be opened directly in Excalidraw") and when ("Use when asked to 'create a diagram', 'make a flowchart', ..."), matching the anchor for a complete what+when answer.	5 / 5
Trigger Term Quality	Six natural quoted trigger phrases ("create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", "generate an Excalidraw file") plus the ".excalidraw" file extension give good coverage, but common variations users would say for the other supported diagram types (e.g. "sequence diagram", "ER diagram", "class diagram", "swimlane") are missing.	4 / 5
Distinctiveness Conflict Risk	The Excalidraw-specific niche and file format ("Outputs .excalidraw JSON files", "generate an Excalidraw file") give it a clear trigger vocabulary with minimal overlap risk against generic diagramming or visualization skills.	5 / 5
	Total	18 / 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 (614 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ZHangZHengEric/Sage
Path: app/skills/excalidraw-diagram-generator/SKILL.md
Commit: 81bddde

Reviewed: 7 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.