design-patterns
Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.
54
63%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skills/design-patterns/SKILL.mdQuality
Discovery
100%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 an excellent skill description that clearly communicates specific capabilities (detect, suggest, evaluate design patterns), uses natural trigger terms across multiple relevant domains (pattern names, frameworks, languages), and includes an explicit 'Use when' clause with concrete scenarios. The description is concise yet comprehensive, making it easy for Claude to distinguish this skill from general code review or framework-specific skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Detect, suggest, and evaluate GoF design patterns' along with specific pattern names (singleton/factory/observer/strategy) and specific frameworks (React, Angular, NestJS, Vue). Also mentions 'reviewing pattern quality' and 'finding stack-native alternatives'. | 3 / 3 |
Completeness | Clearly answers both 'what' (detect, suggest, and evaluate GoF design patterns in TS/JS codebases) and 'when' (explicit 'Use when' clause covering refactoring, applying specific patterns, reviewing pattern quality, or finding stack-native alternatives). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'design patterns', 'refactoring', 'singleton', 'factory', 'observer', 'strategy', 'TypeScript', 'JavaScript', 'React', 'Angular', 'NestJS', 'Vue', 'GoF'. These cover a wide range of terms a developer would naturally use when seeking pattern guidance. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: GoF design patterns specifically in TypeScript/JavaScript with named frameworks. Unlikely to conflict with general code review, refactoring, or framework-specific skills due to the specific focus on design pattern detection, suggestion, and evaluation. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely verbose and poorly structured for token efficiency. It inlines hundreds of lines of output format examples, detection heuristics, and adaptation tables that should live in the referenced files it claims to have. The referenced bundle files don't exist, creating a disconnect between the claimed progressive disclosure structure and reality. While the domain coverage is thorough, the skill explains too many concepts Claude already knows and provides descriptive rather than truly executable guidance.
Suggestions
Move the large JSON/Markdown output examples, detection heuristics, code smell mappings, and stack adaptation tables into the referenced files (signatures/*.yaml, reference/*.md) and actually provide them in the bundle.
Condense the SKILL.md to a lean overview (~80-100 lines) covering: operating modes, key workflow steps, constraints, and pointers to reference files—remove all inline examples longer than 10 lines.
Add validation/feedback steps to workflows: what to do when confidence is low, how to handle files that don't parse, and how to verify detection accuracy before presenting results.
Remove explanations of well-known concepts (what GoF patterns are, what code smells are, what a switch statement looks like) and focus only on the skill-specific decision logic and configuration.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensively explains concepts Claude already knows (GoF patterns, code smells, what a switch statement is). The massive inline JSON/Markdown output examples consume enormous token budget and could be in reference files. Detection heuristics, scoring guidelines, and adaptation tables all add bulk that could be drastically condensed. | 1 / 3 |
Actionability | Provides concrete output format examples and CLI invocations, but the actual detection/analysis logic relies on YAML files and scripts that don't exist in the bundle. The workflow steps are described in pseudocode-like numbered lists rather than executable commands. The skill describes what to do conceptually but lacks truly executable, copy-paste-ready implementation details. | 2 / 3 |
Workflow Clarity | Each mode has a numbered workflow sequence, but there are no validation checkpoints or feedback loops. For a read-only analysis skill the risk is lower, but there's no guidance on what to do when detection fails, when confidence is low, or how to handle ambiguous results. The adaptation logic uses pseudocode IF/ELSE rather than clear decision procedures. | 2 / 3 |
Progressive Disclosure | References 8+ external files (signatures/*.yaml, checklists/*.md, reference/*.md) but none are provided in the bundle, making them dead references. Meanwhile, the SKILL.md itself is a monolithic wall of text with massive inline JSON examples, full markdown report templates, and detailed tables that should be in those referenced files. The content organization is inverted—everything is inline despite having a reference structure defined. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (567 lines); consider splitting into references/ and linking | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Commit
60a4372
- 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.