Testing agents

madebyaris/advance-minimax-m3-cursor-rules

Agent Cursor

Validates completed work. Use after tasks are marked done to confirm implementations are functional. Invoke with /verifier when you need to verify code actually works.

cesarferreira/stax

Agent Claude Code

Verifies stax code changes by running cargo check, clippy, and targeted nextest runs. Reports exact errors with file:line references and actionable fix suggestions.

go-to-k/cdkd

Agent Claude Code

Review test adequacy for a PR — find coverage gaps, mock anti-patterns, fixture realism issues. Read-only — never writes or edits.

lucifer1004/claude-skill-typst

Agent

Run full QA suite on a Typst package before publishing. Use when preparing a package for Typst Universe submission.

lucifer1004/claude-skill-typst

Agent

Verify Typst document output against requirements. Use after compilation when you need to confirm content, structure, or visual layout correctness.

AI-Unified-Process/marketplace

Agent

Part of aiup-vaadin-jooq

Read-only auditor that checks whether a use case (UC-XXX) or test case (TC-XXX) is completely implemented and completely tested against its specification. Use it during or after implementation and during or after writing tests: it maps every main success scenario step, alternative flow, business rule, precondition…

vinilana/invokta

Agent

Use for reproducing failures, isolating root causes, and implementing evidence-backed regression fixes.

UiPath/coder_eval

Agent

Run OpenAI Codex as the agent under evaluation in Coder Eval — installation, authentication, task configuration, and how Codex telemetry maps to sandboxed, weighted scoring.

Houseofmvps/ultraship

Agent

Part of ultraship

Runs the static accessibility (WCAG 2.2) audit using the a11y-scanner tool. Dispatched by /ship for scorecard generation.

avibebuilder/claude-prime

Agent Claude Code

Decide whether the skill improvement loop should continue or stop. You are independent from the agent that wrote the improvements — your only job is to look at the evidence and make an honest call.

anam-org/metaxy

Agent Claude Code

Part of metaxy

Use this agent when you need to create new tests, fix failing tests, refactor test code, or improve test organization and maintainability. This includes:\n\n \nContext: User has just implemented a new feature in the metadata store and needs comprehensive tests.\nuser: "I've added a new fallback store chain feature.…

anam-org/metaxy

Agent Claude Code

Part of metaxy

Use this agent when:\n\n1. A logical unit of work has been completed (feature implementation, bug fix, refactoring)\n2. Code changes are ready for review before committing or creating a pull request\n3. You need to verify that acceptance criteria and definition of done are met\n4. After making changes to test files to…

revfactory/claude-code-harness

Agent Claude Code

A test and usage layer for a small programming language, with four suites covering the lexer, parser, interpreter, and integration. It also includes example programs and a REPL, an interactive prompt for entering code and seeing results.

revfactory/claude-code-harness

Agent Claude Code

An end-to-end integration test suite for five order scenarios: success, insufficient stock, payment failure, simultaneous orders, and timeout. End-to-end tests check the complete flow across connected parts of a system.

jellydn/my-ai-tools

Agent

Generates comprehensive, meaningful tests for code changes. Focuses on testing behavior and edge cases rather than implementation details.

espennilsen/pi

Agent

QA specialist that tests running web applications against acceptance criteria.

ammarion/waf-detector

Agent Claude Code

Use this agent when you need to perform comprehensive end-to-end testing of a system with multiple components (CLI, web interface, APIs). This includes testing functionality, integration points, error handling, and accuracy validation. The agent should be invoked after significant code changes, before releases, or…

Changan-Su/Forsion

Agent

Evaluate expectations against an execution transcript and outputs.

openshift-eng/ai-helpers

Agent

Part of ci

Automated Ginkgo e2e test porting agent. Ports tests from openshift-tests-private to openshift/origin, creates PRs, monitors CI, responds to review feedback, pushes fixes, and escalates to humans when needed. Use this agent for any task related to porting tests between these repos.

ChrisRoyse/610ClaudeSubagents

Agent

Expert in AI-enhanced testing, machine learning for test optimization, intelligent test generation, predictive test analytics, and autonomous testing systems.

ChrisRoyse/610ClaudeSubagents

Agent

Expert in API and microservice integration testing, contract validation, and service mesh testing. Orchestrates comprehensive API testing strategies including REST, GraphQL, gRPC, and event-driven architectures with advanced contract testing and service virtualization.

bladeofgod/flutter-ai-harness

Agent Claude Code

A runtime UI verification agent for apps using Marionette, a tool for connecting to and controlling an app during development. It follows an already approved behavior specification and writes a run report.

zhangdszq/teamclaw

Agent

Evaluate expectations against an execution transcript and outputs.

jaktestowac/awesome-copilot-for-testers

Agent

Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Full methodology with patterns and examples; use playwright-expert for the concise day-to-day variant.