test-sentinelWrites and runs tests (unit, integration, E2E), performs linting, and auto-fixes failures
Install via ClawdBot CLI:
clawdbot install guifav/test-sentinelGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
http://localhost:3000/api/entitiesAudited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Ensures checkout flows, payment processing, and inventory management work correctly. The agent writes unit tests for pricing calculations, integration tests for order APIs with mocked payment gateways, and E2E tests for user purchase journeys using Playwright to simulate real user interactions.
Maintains reliability for a subscription-based software with frequent updates. The agent plans tests for new features, runs full test suites to catch regressions, and auto-fixes linting issues in code changes, ensuring high code quality and preventing bugs in production deployments.
Validates patient data processing and compliance with regulations in a health app. The agent writes unit tests for data transformation functions, integration tests for secure API endpoints with mocked external services, and E2E tests for user authentication flows to protect sensitive information.
Tests financial transactions and fraud detection algorithms in a banking app. The agent creates unit tests for currency formatting and error handling, integration tests for transaction APIs with mocked databases, and E2E tests for user account management to ensure security and accuracy.
Offers testing services as part of a subscription package for businesses developing web applications. Revenue is generated through monthly or annual fees based on usage tiers, with additional charges for premium support or custom test automation features.
Provides tailored testing solutions and code fixes for clients on a project basis. Revenue comes from hourly rates or fixed-price contracts, focusing on integrating the agent into existing development workflows to improve testing coverage and reduce manual QA efforts.
Distributes the core testing agent as open-source software to build a community, while monetizing advanced features like AI-driven test generation or detailed analytics. Revenue is earned through licensing for enterprise features or donations from users who benefit from the tool.
💬 Integration Tip
Integrate the agent into CI/CD pipelines by adding its test commands to build scripts, ensuring it runs automatically on code commits to catch issues early and maintain consistent code quality across deployments.
Scored Apr 18, 2026
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode.
Ship production code with AI agents through acceptance contracts, micro diffs, red green loops, and deterministic handoff checkpoints.
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Provides a 7-step debugging protocol plus language-specific commands to systematically identify, verify, and fix software bugs across multiple environments.