CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

excalidraw

Generate architecture diagrams as .excalidraw files from codebase analysis. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, or generate excalidraw files.

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 highly actionable, well-structured skill body: concrete JSON patterns, exact geometry, and a validated six-step workflow with a real one-level-deep reference bundle. The main improvement areas are trimming the duplicated quick-reference blocks and making the validate-fix-retry loop explicit in the workflow.

DimensionReasoningScore

Conciseness

The body is dense, table-driven, and assumes competence — no explanations of what Excalidraw is or how JSON works. However, the Quick Arrow Reference, Default Color Palette, and Quick Validation Checklist sections each duplicate content already delegated to references/arrows.md, colors.md, and validation.md, which is trimmable redundancy. Fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean-every-token-earns-its-place level.

4 / 5

Actionability

Copy-paste-ready JSON fragments for label binding, elbow arrows, and straight/L/U-turn routes with exact coordinates; edge-point formulas; a concrete layout grid (rows y:100-680, columns, element sizes); Glob/Grep patterns; and a 10-row color table. The common cases (labels, arrow routing, colors, layout, validation) are all covered with executable specifics, matching the top anchor.

5 / 5

Workflow Clarity

The six-step workflow is clearly sequenced with an explicit validation step ('Run validation before writing') plus an inline checklist and a Common Issues fix table. It falls short of the top anchor because the validate → fix → re-validate feedback loop is not explicit in the body — error-recovery detail is only pointed at references/validation.md.

4 / 5

Progressive Disclosure

All five referenced files exist, are one level deep, well-signaled at point of need, and summarized in a Reference Files table — close to top-anchor structure. Held at 4 because the inline 'quick reference' sections (colors, arrows, validation) partially duplicate their counterpart reference files, a minor organization gap versus the 'content appropriately split' anchor.

4 / 5

Total

17

/

20

Passed

Description

82%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 with an explicit 'Use when...' trigger clause, distinct niche keywords, and a concrete what/when pairing. Its only weakness is thin capability enumeration — it states a single overall action rather than the several specific things it does.

Suggestions

Enumerate 1-2 more concrete capabilities in the first sentence (e.g., '...mapping services, databases, and data flows into styled, labeled elements') to lift specificity beyond a single action.

Add a common synonym or the file extension (e.g., '.excalidraw' or 'system design diagram') to the trigger list to broaden natural-term coverage.

DimensionReasoningScore

Specificity

The description names the domain and essentially one concrete action — "Generate architecture diagrams as .excalidraw files from codebase analysis" — with a concrete output format and input source, but does not list several specific actions (e.g., mapping services/databases, routing arrows, applying cloud palettes). It matches the 'names domain and 1-2 concrete actions' anchor, not the 'several specific actions' level above.

3 / 5

Completeness

It clearly answers what ("Generate architecture diagrams as .excalidraw files from codebase analysis") and when via an explicit "Use when the user asks to..." clause with four concrete trigger phrases. Explicitly matches the top anchor; the level below would require a weaker or implicit 'when'.

5 / 5

Trigger Term Quality

"create architecture diagrams, system diagrams, visualize codebase structure, or generate excalidraw files" gives good natural-phrase coverage including the tool name, but misses common variations like "system design", "diagram" alone, or the .excalidraw extension. Solidly at 'good keyword coverage; a few natural terms missing' rather than the comprehensive-synonym level.

4 / 5

Distinctiveness Conflict Risk

"excalidraw" is a clear niche trigger with a distinct output format, and the codebase-analysis source further differentiates it from generic diagramming or viz skills. Minimal conflict risk; fits 'clear niche with distinct triggers'.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

eigent-ai/agent-skills

Path

skills/web-and-frontend-development/excalidraw/SKILL.md

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.