Codacy Skills is a feature that allows coding agents to automatically set up test coverage for projects. It uses LLMs to analyze code and generate tests, helping developers improve code quality and reduce manual testing effort.
Visit project ↗Argus is an agentic QA tool that helps teams whose coding agents produce code faster than QA can review. It uses LLMs to automate testing and quality assurance tasks, addressing the bottleneck of manual QA in high-velocity development environments.
Argus is an agentic QA tool that helps teams whose coding agents produce code faster than QA can review. It uses LLMs to automate testing and quality assurance tasks, addressing the bottleneck of manual QA in high-velocity development environments.
Bugbout lets developers test coding agents on real bugs that their own repository previously fixed. It turns historical bug fixes into evaluation tasks, so teams can measure which LLM coding agent actually resolves their codebase's issues.
Bugbout lets developers test coding agents on real bugs that their own repository previously fixed. It turns historical bug fixes into evaluation tasks, so teams can measure which LLM coding agent actually resolves their codebase's issues.
Agent Monitor is a tool that provides live monitoring for coding agents, allowing developers to observe their agent's actions in real time. It uses LLMs to power coding agents and helps developers debug and optimize agent behavior by providing visibility into the agent's decision-making process.
Agent Monitor is a tool that provides live monitoring for coding agents, allowing developers to observe their agent's actions in real time. It uses LLMs to power coding agents and helps developers debug and optimize agent behavior by providing visibility into the agent's decision-making process.
AgentSnap is a tool for snapshot testing of AI agents, allowing developers to capture and compare agent outputs across runs. It uses LLMs to generate deterministic snapshots of agent behavior, helping debug regressions and ensure consistency. The tool targets developers building complex agentic systems who need reliable testing.
AgentSnap is a tool for snapshot testing of AI agents, allowing developers to capture and compare agent outputs across runs. It uses LLMs to generate deterministic snapshots of agent behavior, helping debug regressions and ensure consistency. The tool targets developers building complex agentic systems who need reliable testing.
A skill for Claude Code that enhances analysis coverage in tests, likely by generating or refining test cases. It aims to help developers improve test quality and find edge cases. The creator is seeking community validation to break the results.
A skill for Claude Code that enhances analysis coverage in tests, likely by generating or refining test cases. It aims to help developers improve test quality and find edge cases. The creator is seeking community validation to break the results.