Testing plugins

A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.

4 skills

Unit and integration test automation for Python and JavaScript with debugging support

1 command · 2 agents

Author, automate, and reconcile behavior specifications in Gherkin, turning system behavior into executable specs.

3 skills

Adversarial E2E test layer that hunts for unguarded destructive paths in web applications.

1 command · 1 agent

See inside your running iOS app: network calls, WebSocket frames, logs, UserDefaults, screen layout, and API mocking.

1 skill · 1 MCP server

Shared CLI/MCP control for mobile, browser and desktop sessions, with observations, durable tasks, human handoff and evidence export.

1 skill · 1 command

Testing for Claude Code plugins before release: installs a copy the way your users receive it in a throwaway config, checks it loads, runs your plugin eval suite against that copy, and reviews your evals so they measure what the plugin adds. Quality you can prove.

2 skills

Skills for evaluating AI agents with @agent-evals/core: suites, graders, pass@k and pass^k, reports, and eval tasks from failures.

2 skills

Pinned mobile-mcp MCP server so the designer and the manual tester can drive local iOS simulators and Android emulators (list, tap, type, read the screen).

1 skill · 1 MCP server

Control real iOS and Android devices, simulators and emulators: read the screen, tap, type, swipe, launch apps, and mirror one action across a whole fleet.

1 skill · 1 MCP server

Skills for writing stormbreaker smoke and load runs (axx scenarios) and the dispatchers that prepare and clean up for them.

2 skills

Generates interactive HTML dashboards using real Supabase data to debug app issues. Testers interact with the dashboard, flag problems, and copy structured feedback back to Claude for action.

1 skill

Critical-path QA for web apps in plain words. Your agent writes a qc-use test, runs it in a private Chrome, and explains the verdict and evidence for each step.

1 skill

Origin-style Demo Check for GitHub and everywhere else: a recorded visual-QA walkthrough + expected-vs-actual on the PR. Triggers when you finish tested UI work, or on "QA this and leave receipts".

1 skill

Run the probe loop to verify whether software actually works against the real runtime. Catches silent no-ops, environment mismatches, swallowed errors, hardcoded parameters, cross-layer trust violations, and destructive edge cases.

1 skill

White-box testing skill: path coverage, cyclomatic complexity, decision-path analysis, and language-specific test generation for Python/JS/Java/C.

1 skill

Guide Go development with tests: smallest test first, start from public behavior, keep IO out of decision packages

1 skill

Uncover test coverage gaps by applying semantic mutations to production TypeScript, Go, or Python code

1 skill

Generate adversarial, negative, and chaos tests for TypeScript code — boundary conditions, fuzzing, injection scenarios

1 skill

Helps you decide what to test instead of generating a test suite for you. Maps the code's risk surface and asks what behavior you would protect and what input breaks it. You name the cases, then write them yourself or approve specific ones for Claude to implement.

1 skill

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.

1 MCP server

It told you the tests passed. What is that based on? Reports what the transcript can and cannot show about each claim in the agent's final message, and checks a scoped test claim against an opt-in pytest receipt. Report-only.

hooks

Quarantine an intermittently failing test as tracked debt - owner, cause, expiry - instead of deleting it or leaving it to rot. Use before muting or skipping any test, and on a schedule to review the register.

1 skill

KPI Simulation - measure a project's KPIs locally, simulate user behavior with UAT-style Characters, and predict real-world targets from web benchmarks, writing a result.json the Personas app ingests into its KPI module (env-tagged simulated series + proposal-gated adjustments). Engine doctrine mirrors src/features/teams/sub_kpis/kpiSimPrompt.ts - the app dispatches the same contract into managed…

1 skill

Prove a change works before it is committed by writing or extending a test that fails first and then passes. Use whenever you change behaviour, fix a bug, or accept AI-generated code.

1 skill

Makes Claude an expert in Claude Code plugin evals: designs eval suites and benchmarks that prove what a plugin or its skills add, writes cases, graders and mocks, runs and gates them in CI, and reads the results, always checked against the CLI and docs you have today. Testing and quality for plugins.

1 skill

Claude runs rook against the agent it is building: live verdict pane, re-test prompts after agent edits, failures fed back as fix context, status line score, /rook commands and a production-target guard.

NCT/NACT/NSCT methodology guidance for Ivy protocol testing via ivy-tools MCP server. Provides agents, skills, and commands for formal protocol specification, attack modeling, and simulation-based testing using the 14-layer template architecture.

30 skills · 3 commands · 9 agents · 2 MCP servers · hooks · LSP

Agentic QA — skip the manual grind. AgenTeX plans and runs your tests for you (human-in-the-loop or fully autonomous) with structured evidence, a consolidated defect report, and an interactive HTML dashboard, driving a real browser via playwright-cli. Test steps can call your APIs and query your database from a user-defined integration catalog, and ask your project's knowledge base a question mid-run. On your work tracker — Azure DevOps or Jira Cloud — it designs test cases from story ACs and links them to stories, estimates QA effort and creates [Testing] tasks, and files run defects as bugs, all behind one consolidated approval; on Azure it also reaches Azure resources mid-run via the az CLI.

17 skills · 11 commands · 3 agents