eraser-diagrams
Generates architecture diagrams from code, infrastructure, or descriptions. Use when user asks to visualize, diagram, or document system architecture.
Install with Tessl CLI
npx tessl i github:eraserlabs/eraser-io --skill eraser-diagrams90
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
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 when to use it. The explicit 'Use when...' clause with natural trigger terms is a strength. The main weakness is that the capabilities could be more specific about what types of diagrams or outputs are supported.
Suggestions
Add more specific concrete actions like 'create component diagrams, generate infrastructure maps, produce sequence diagrams' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (architecture diagrams) and mentions inputs (code, infrastructure, descriptions), but doesn't list multiple specific concrete actions like 'create flowcharts, generate component diagrams, export to PNG'. | 2 / 3 |
Completeness | Clearly answers both what ('Generates architecture diagrams from code, infrastructure, or descriptions') and when ('Use when user asks to visualize, diagram, or document system architecture') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'visualize', 'diagram', 'document', 'system architecture'. These are terms users naturally use when requesting this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on architecture diagrams with distinct triggers. Unlikely to conflict with general diagramming or documentation skills due to the specific 'system architecture' focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with clear workflows and appropriate progressive disclosure to reference files. The main weakness is moderate verbosity - the 'When to Use' triggers and diagram type descriptions explain things Claude already knows, and some content is repeated across sections. Overall, it's a strong skill that could benefit from trimming explanatory content.
Suggestions
Remove or significantly condense the 'When to Use' section - Claude can infer when to generate diagrams without explicit trigger words listed
Trim the 'Use for' descriptions under each diagram type - Claude already knows what flowcharts and ERDs are used for; just keep the diagramType and reference link
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., describing what each diagram type is 'for' when Claude already knows this) and could be tightened. The 'When to Use' section lists obvious triggers, and some best practices repeat information already covered. | 2 / 3 |
Actionability | Provides fully executable curl commands, complete JSON request/response formats, and specific DSL references. The step-by-step instructions are concrete with copy-paste ready code examples. | 3 / 3 |
Workflow Clarity | Clear 7-step numbered workflow with explicit validation checkpoints (error handling section), specific output format requirements, and error recovery guidance. The sequence from analysis to API call to response handling is unambiguous. | 3 / 3 |
Progressive Disclosure | Excellent structure with overview in main file and detailed DSL syntax appropriately delegated to separate reference files (flowchart-syntax.md, erd-syntax.md, etc.). References are one level deep and clearly signaled with links. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.