eraser-diagrams

Generates architecture diagrams from code, infrastructure, or descriptions. Use when user asks to visualize, diagram, or document system architecture.

1.88x

Quality

80%

Does it follow best practices?

Impact

100%

1.88x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/eraser-diagrams/SKILL.md

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with excellent workflow clarity and good progressive disclosure through reference files for each diagram type. However, it is significantly too verbose - repeating the X-Skill-Source header instructions multiple times, explaining diagram types in ways Claude doesn't need (what a sequence diagram is), and including a 'When to Use' section and 'How It Works' overview that add little value. The content could be reduced by 40-50% without losing any actionable information.

Suggestions

Remove the 'When to Use' and 'How It Works' overview sections - these describe rather than instruct and Claude can infer activation triggers from the skill description.

Consolidate the diagram type descriptions to just a table mapping diagramType values to their reference files, removing the verbose descriptions of what each diagram type visualizes (Claude already knows what sequence diagrams and ERDs are).

Mention the X-Skill-Source header requirement once in the curl command with a brief comment, rather than repeating it 4 times across different sections.

Merge the 'Best Practices' section into the relevant instruction steps to avoid repeating guidance (e.g., single-line labels is already stated as CRITICAL in step 2).

Dimension	Reasoning	Score
Conciseness	Extremely verbose for what it does. Extensive explanation of when to use it, how it works overview, repeated instructions about X-Skill-Source header (mentioned 4+ times), lengthy descriptions of each diagram type that Claude doesn't need (e.g., 'Visualize system flows using sequence diagrams. Each vertical column represents an entity...'). The 'Best Practices' section largely repeats instructions already given. Much of this could be cut in half.	1 / 3
Actionability	Provides fully executable curl commands, concrete API endpoint, specific request/response JSON formats, exact header values, and clear error handling table. The instructions are copy-paste ready with specific field names and values.	3 / 3
Workflow Clarity	Clear numbered sequence from analysis through DSL generation, API call, and response handling. Includes explicit validation guidance (verify DSL syntax before calling), error handling steps with specific error codes and solutions, and a feedback loop for regenerating DSL on failure. The output format is precisely specified with 5 required elements.	3 / 3
Progressive Disclosure	Excellent use of progressive disclosure - each diagram type links to a dedicated reference file (e.g., references/flowchart-syntax.md, references/erd-syntax.md) for detailed DSL syntax, keeping the main skill file as an overview. References are one level deep and clearly signaled.	3 / 3
	Total	10 / 12 Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid skill description that clearly communicates its purpose and includes an explicit 'Use when' clause with natural trigger terms. Its main weakness is that the capability description could be more specific about the types of diagrams or outputs it produces. Overall it performs well across all dimensions.

Suggestions

Add more specific concrete actions/outputs, e.g., 'Generates architecture diagrams including component diagrams, sequence diagrams, and cloud infrastructure maps from code, infrastructure configs, or descriptions.'

Dimension	Reasoning	Score
Specificity	Names the domain (architecture diagrams) and mentions inputs (code, infrastructure, descriptions), but doesn't list multiple specific concrete actions beyond 'generates'. Could specify outputs like sequence diagrams, component diagrams, cloud architecture diagrams, etc.	2 / 3
Completeness	Clearly answers both 'what' (generates architecture diagrams from code, infrastructure, or descriptions) and 'when' (explicit 'Use when' clause with trigger scenarios: visualize, diagram, or document system architecture).	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'visualize', 'diagram', 'document', 'system architecture', 'code', 'infrastructure'. These are terms users would naturally use when requesting this kind of work.	3 / 3
Distinctiveness Conflict Risk	The combination of 'architecture diagrams' with specific inputs (code, infrastructure) and trigger terms (visualize, diagram, system architecture) creates a clear niche that is unlikely to conflict with general documentation or code generation skills.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: eraserlabs/eraser-io
Commit: 30d6f36

Reviewed: 3 months 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.