run-test-planExecute YAML test plan, stop on first failure, output rich debug prompt
Install via ClawdBot CLI:
clawdbot install anderskev/run-test-planGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
${DATABASE_URL}AI Analysis
The skill is designed to execute a local test plan and does not contain instructions to send data to external servers. The credential access signal is a false positive, as the `${DATABASE_URL}` pattern is used for environment variable resolution within a controlled test environment, not for harvesting credentials. The skill's behavior is transparent and focused on automation testing.
Audited Apr 17, 2026 · audit v1.0
Generated Apr 19, 2026
This scenario involves using the Run Test Plan skill to automate end-to-end testing in a CI/CD pipeline for a web application. Developers can define YAML test plans that include setup commands (like building Docker images), health checks (polling service endpoints), and sequential test execution (including browser automation via agent-browser). It ensures that new code changes don't break existing functionality by running tests on every commit, stopping on the first failure to provide immediate feedback with rich debug output.
In this scenario, the skill is used to validate APIs and microservices in a distributed system. The test plan includes prerequisites checks (e.g., verifying database connectivity), setting environment variables, starting services with health checks, and executing tests that involve curl actions to verify endpoints. It helps teams ensure that APIs return expected responses and that services are correctly integrated, with the ability to stop on failures and generate debug reports for quick troubleshooting.
This scenario applies the skill to regression testing for an e-commerce platform. Test plans include setup steps like deploying a staging environment, running health checks on payment gateways, and executing tests that combine shell commands (e.g., database queries) and browser automation (e.g., simulating user purchases). It ensures that critical workflows, such as checkout and inventory management, remain functional after updates, with screenshots saved as evidence and cleanup of background services after execution.
Here, the skill is used for quality assurance in educational software, such as learning management systems. Test plans involve setup commands to seed test data, health checks on user authentication services, and sequential tests that include agent-browser steps for UI interactions (e.g., navigating courses, submitting assignments). It helps educators and developers verify that features work as intended across different user roles, with failure handling that provides context on recent code changes for debugging.
This scenario involves using the skill to test firmware for IoT devices. The test plan includes prerequisites checks for hardware dependencies, setup commands to flash firmware, health checks on device connectivity, and tests that run shell commands to validate sensor readings or network configurations. It enables engineers to automate validation of device functionality in lab environments, stopping on failures to analyze logs and generate debug prompts for hardware-software integration issues.
This business model leverages the Run Test Plan skill to offer automated testing as a service for clients. Companies can provide a platform where users upload YAML test plans, and the service executes them in cloud environments, handling setup, health checks, and test execution with browser automation. Revenue is generated through subscription tiers based on test frequency, complexity, and support levels, targeting startups and enterprises needing reliable CI/CD pipelines.
In this model, businesses use the skill to offer consulting services for integrating automated testing into client workflows. Experts help clients design YAML test plans, set up prerequisites, and optimize test execution for specific industries like e-commerce or IoT. Revenue comes from project-based fees for implementation, training, and ongoing maintenance, focusing on clients with complex systems that require tailored testing solutions.
This model involves distributing the Run Test Plan skill as open-source software to build a community, while offering premium features for advanced users. Free versions include basic test execution, while paid upgrades provide enhanced debug prompts, integration with third-party tools, and priority support. Revenue is generated through licensing fees for enterprise features, targeting developers and teams who need scalable testing capabilities beyond the core functionality.
💬 Integration Tip
Integrate this skill into existing CI/CD pipelines by calling it with the --plan argument in build scripts, and use the --skip-setup flag for faster re-runs after initial setup to optimize testing cycles.
Scored Jul 11, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.