excalidraw

Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams/flowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)

1.59x

Quality

68%

Does it follow best practices?

Impact

97%

1.59x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/excalidraw/SKILL.md

Quality

Content

53%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 skill delivers actionable, well-structured delegation templates that clearly guide the main agent. Its main weaknesses are heavy repetition of the same anti-direct-read principle and a lack of validation checkpoints in the file-writing workflows.

Suggestions

Collapse the redundant anti-rationalization sections (Common Rationalizations, Red Flags, 'Why Straightforward JSON', Iron Law) into one concise section to cut token cost substantially without losing the rule.

Add a validation/verification step to the Modify and Create templates (e.g., have the subagent confirm the written file is valid JSON and renders the expected elements before returning).

Show the concrete Task-tool invocation form (or a minimal example) so the templates are fully copy-paste ready rather than relying on placeholders.

Dimension	Reasoning	Score
Conciseness	The body restates the single principle ('never read directly, always delegate') across Overview, Common Rationalizations, Red Flags, 'Why Straightforward JSON Doesn't Matter', and The Iron Law, which is noticeably verbose padding of one idea; not a 3 because the repetition is substantial rather than incidental.	2 / 5
Actionability	Provides copy-paste-ready subagent task templates (Read/Modify/Create/Compare) with numbered steps and explicit return specs, giving mostly executable guidance; minor gaps (placeholder syntax, no concrete Task-tool invocation form) keep it just below 5.	4 / 5
Workflow Clarity	Subagent workflows are clearly sequenced with numbered steps, but the Modify and Create operations write files with no validation/verification step; per the rubric, destructive/batch operations without validation cap workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the content is self-contained, with well-organized headers, tables, and templates providing good structure and easy navigation; not a 5 because at ~220 lines the monolithic single-file form could be trimmed without loss.	4 / 5
	Total	13 / 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.

The description clearly states what the skill does and when to use it, with strong natural trigger terms and a distinct niche. Its only weakness is specificity: it describes delegation as a single action rather than enumerating the concrete operations it supports.

Suggestions

Enumerate the concrete operations the skill covers (e.g., read, modify, create, and compare Excalidraw diagrams) instead of the generic 'all Excalidraw operations' to raise specificity.

Add a few more natural trigger synonyms users might say ('diagram', 'draw', 'architecture diagram') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the Excalidraw domain and a concrete action ('delegates all Excalidraw operations to subagents') but does not enumerate the distinct operations (read/modify/create/compare), so coverage is not comprehensive; not a 4 because only one generic action is named.	3 / 5
Completeness	Explicitly answers both 'what' ('delegates all Excalidraw operations to subagents to prevent context exhaustion') and 'when' ('Use when working with *.excalidraw... files, user mentions diagrams/flowcharts, or requests architecture visualization') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage including file extensions ('.excalidraw', '.excalidraw.json') and user phrases ('diagrams/flowcharts', 'architecture visualization'); a few common variants (e.g., 'diagram', 'draw') are missing, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Excalidraw files) with file-extension triggers and domain-specific keywords, giving minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: softaworks/agent-toolkit
Path: skills/excalidraw/SKILL.md
Commit: 3027f20

Reviewed: 4 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.