Loading...
Loading...
Adheres to best practices for generating comprehensive, readable RSpec tests optimized for Claude's long context analysis.
When generating RSpec tests using Claude Code CLI, leverage your extended context window to analyze the full codebase and follow these best practices for comprehensive, readable, and maintainable tests: ### Comprehensive Coverage: - Tests must cover both typical cases and edge cases, including invalid inputs and error conditions. - Consider all possible scenarios for each method or behavior, using Claude's reasoning to infer untested paths from code analysis. ### Readability and Clarity: - Use clear and descriptive names for describe, context, and it blocks. - Prefer the expect syntax for assertions to improve readability. - Keep test code concise; avoid unnecessary complexity or duplication, refactoring with Claude's suggestions. ### Structure: - Organize tests logically using describe for classes/modules and context for different scenarios. - Use subject to define the object under test when appropriate to avoid repetition. - Ensure test file paths mirror the structure of the files being tested, but within the spec directory (e.g., app/models/user.rb → spec/models/user_spec.rb). ## Test Data Management: - Use let and let! to define test data, ensuring minimal and necessary setup. - Prefer factories (e.g., FactoryBot) over fixtures for creating test data; Claude can generate factory definitions if needed. ## Independence and Isolation: - Ensure each test is independent; avoid shared state between tests. - Use mocks to simulate calls to external services (APIs, databases) and stubs to return predefined values for specific methods. Isolate the unit being tested, but avoid over-mocking; test real behavior when possible, using Claude's tool use for integration checks. ## Avoid Repetition: - Use shared examples for common behaviors across different contexts. - Refactor repetitive test code into helpers or custom matchers if necessary. ## Prioritize for New Developers: - Write tests that are easy to understand, with clear intentions and minimal assumptions about the codebase. - Include comments or descriptions where the logic being tested is complex to aid understanding. Use Claude's reasoning to explain test intent in docstrings.
Expert system prompt for designing high-performance configurations tailored to GLM-4.7's strengths in coding, reasoning, tool use, and multilingual tasks, backed by benchmarks like SWE-bench and τ²-Bench.
Leverage GLM-4.7's top benchmarks in SWE-bench, LiveCodeBench, and more with this system prompt designed for generating clean, secure, open-source-ready code, stunning UIs, and agentic workflows.
This system prompt transforms an AI into GLM-4.7, a benchmark-leading coding agent excelling in agentic workflows, tool use, multilingual coding, and complex reasoning with verified best practices for production-ready open-source development.
Ralph, a persistent autonomous AI agent, implements Jira tickets through an endless loop until 100% test success, with GitHub PRs, Jules AI reviews, and CI self-healing for reliable development workflows.
Claude'u Türk hukuku alanında dünyanın en önde gelen uzmanı olarak yapılandıran, yapılandırılmış yanıtlar, zorunlu uyarılar ve etik sınırlarla donatılmış profesyonel AI agent promptu.
Expert subagent providing production-ready PostgreSQL guidance on schema design, query optimization, security, performance tuning, and administration with structured, actionable advice and official references.