CtrlK
BlogDocsLog inGet started
Tessl Logo

function-class-generator

Generate complete, production-ready functions and classes from formal specifications, design descriptions, type signatures, or natural language requirements. Use this skill when implementing APIs from specifications, creating data structures from schemas, building classes from UML diagrams, generating code from contracts, or translating design documents into code. Supports multiple programming languages and follows language-specific best practices.

75

1.16x
Quality

71%

Does it follow best practices?

Impact

94%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/function-class-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 content is highly actionable with concrete, executable examples across multiple languages, and the generation workflow is reasonably clear. Its major weakness is poor conciseness and progressive disclosure: ~890 lines of fully-worked code and test suites plus general design-pattern primers are inlined into SKILL.md rather than split into reference files.

Suggestions

Move the four full worked patterns (BankAccount class + tests, FastAPI example, Product schema, etc.) into separate reference files under references/ and keep only a concise skeleton plus a pointer in SKILL.md to cut hundreds of lines.

Delete or compress the 'Best Practices' (10 items) and 'Common Patterns' (design-pattern glossary) sections, which restate general SOLID and GoF knowledge Claude already has.

Add an explicit validate->fix->retry checkpoint in the workflow (e.g. run the generated tests, fix failing cases, re-run) to push workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

The file is ~890 lines dominated by fully worked code listings (e.g. the complete BankAccount class plus a ~100-line test suite) that pad the context with implementations Claude already knows how to write, and the 'Best Practices'/'Common Patterns' sections restate general SOLID/design-pattern knowledge.

2 / 5

Actionability

Provides concrete, executable Python/TypeScript code and test suites across several patterns, but much of the guidance is illustrative output rather than concise instructions for how to actually run the generation process on a new specification.

4 / 5

Workflow Clarity

The 5-step Code Generation Workflow (Parse -> Design -> Generate -> Document -> Test) is clearly sequenced and includes a validation/test step, but there is no explicit validate-then-fix feedback loop checkpoint (tests are generated rather than run-and-iterate) and no failure-recovery guidance.

4 / 5

Progressive Disclosure

The body is a monolithic wall of text with no references to separate files; the four large worked patterns (functions, classes, interfaces, data structures) with full implementations are inlined when they clearly belong in reference files, and there are no bundle files present at all.

2 / 5

Total

12

/

20

Passed

Description

81%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 is strong: it explicitly states both what the skill does and when to use it, with good coverage of concrete capability types and natural trigger terms. The main weakness is slight genericness in the action verbs and broad overlap risk from the 'natural language requirements' trigger.

Suggestions

Tighten trigger terms with concrete file extensions or formats a user would name (e.g. '.proto', 'OpenAPI/Swagger', '.json schema') to push trigger_term_quality toward 5.

Sharpen action verbs beyond repeated 'Generate/build/create' to make capabilities feel more distinct (e.g. 'transpile', 'scaffold', 'derive').

Narrow or qualify the 'translating design documents into code' trigger to reduce overlap with general-purpose coding skills.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Generate complete, production-ready functions and classes', 'implementing APIs from specifications', 'creating data structures from schemas', 'building classes from UML diagrams', 'generating code from contracts', 'translating design documents into code') with broad coverage, though the action vocabulary is somewhat generic across each item.

4 / 5

Completeness

Clearly answers both 'what' ('Generate complete, production-ready functions and classes from formal specifications, design descriptions, type signatures, or natural language requirements') and 'when' ('Use this skill when implementing APIs from specifications, creating data structures from schemas, building classes from UML diagrams, generating code from contracts, or translating design documents into code').

5 / 5

Trigger Term Quality

Good natural keyword coverage ('specifications', 'APIs', 'schemas', 'UML diagrams', 'contracts', 'design documents', 'requirements'); missing a few common synonyms or concrete file extensions a user might say, keeping it just below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The specification-driven generation niche is fairly distinct with concrete triggers (UML, OpenAPI, contracts), but 'translate design documents into code' and 'natural language requirements' are broad enough to risk minor overlap with general coding skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (897 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
ArabelaTso/Skills-4-SE
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.