Testing

xiaozhi86/qamaster

Cursor rule Cursor

A test-case design workflow that turns requirements or prototypes into test cases in Markdown or Excel, with coverage analysis.

jyotiraditya-chauhan/test-kit

Skill Claude Code

Writes unit, widget, golden, and integration tests for Flutter projects, detecting whether BLoC, Riverpod, Provider, or GetX is in use from pubspec.yaml before writing any business-logic test. Use when the user asks to write Flutter tests, add test coverage to a widget/bloc/provider/repository, test a .dart file, or…

hoainho/podium-mcp

Plugin Claude Code

Lists 1 plugin

Podium — the mobile + canvas automation MCP for AI agents: iOS & Android control, native UI automation, Maestro E2E, React Native debugging, and a no-vision canvas/WebGL brain that taps game UIs like DOM elements — for Claude Code.

RightNow-AI/autoevolve

Skill Claude CodeCodex

Use this skill whenever asked to join an autoevolve run, evolve code toward a measured target, work an evolution population, mutate a candidate under EVOLVE-BLOCK rules, or report measured autoevolve progress and artifacts.

liatrio-labs/ai-prompts

Skill Codex

Use when you need lightweight browser QA for a web page, local HTML file, or app: inspect console errors, broken assets, keyboard/focus behavior, viewport readability, and publish evidence-backed findings JSON through a local HTML report viewer.

hronaut/hronaut

Skill Claude CodeCodex

Use the Hronaut desktop Browser MCP for visible, persistent web workflows in isolated agent workspaces. Use for authenticated browser QA with human handoff, localhost or responsive testing, accessibility and performance diagnosis, or tasks that should survive one agent session while the user watches or takes over.

0ryant/engineering-doctrine

Skill Claude CodeCodex

Primes an artefact-producing agent to separate what it intended, what it materialised, what it re-checked, and what remains unverified before it reports completion. Load for build-class tasks (code generation, evidence-pack emission, tool-wrapper generation, implementation work whose claims can be re-tested against…

automators-com/flowproof

Skill Claude CodeCodex

Configure flowproof's SAP GUI, Fiori, and AI authoring credentials by walking the user through flowproof config sap / flowproof config fiori / flowproof config ai. Use when the user wants to set up, change, or check their SAP/Fiori login or model authoring key, or when a flow run fails because SAPUSER, FIORIPASSWORD…

yeongseon/kpubdata

Skill Claude CodeCodex

A set of instructions for adding and repairing datasets in kpubdata, a project that describes public data APIs with specification files. It covers recording real API responses, replaying examples, validating schemas, and updating documentation.

logandoo/vibeweaver

Skill Claude CodeCodex

A generic senior-engineer operating playbook. MANDATORY for every coding task — plan before you type, test before you claim, debug from evidence, review your own diff.

skyzhao1223/wheel-hub

MCP server Claude CodeCodexCursor +2

MCP server exposing wheelhub open-source evaluation to AI coding agents. Runs locally from the @wheel-hub/mcp npm package.

MontoyaAndres/ganju

Skill Claude CodeCodex

Write, test, deploy and debug Ganju custom tools (Functions) with the ganju CLI and the @ganju/sdk handler API. Use this whenever the user works in a folder with a ganju.json, imports @ganju/sdk or defineTool, mentions @ganju/cli or any ganju command (init, link, build, test, deploy, logs, versions, rollback, secret…

agent-ecosystem/agent-skill-implementation

Skill Claude Code

Re-run this repository's automated skill-loading checks against the installed harnesses (Antigravity CLI, Claude Code, Codex CLI, Copilot CLI), compare the verdicts with the previous run, and publish the changes. Use when asked to run or re-run the checks, test the harnesses on new releases, see whether skill behavior…

yotambraun/Toolscore

Plugin Claude Code

Bundles 4 skills · 450 tokens together

Test MCP servers and the tool calls your agents make, with the Toolscore CLI: lint and grade a server, check with effect probes that its tools really did what they reported, turn traces into tool-call tests, check that an agent told the truth about its tool results, and pin servers against drift. Deterministic, local.

metago-ai/metagolifeform

Skill Claude CodeCodex

A delivery-check procedure for visible work such as websites, software interfaces, documents, images, and videos. It requires rendering the result, looking at the rendered output, recording problems, fixing them, and checking again.

HereditaryDog/gaster-code-releases

Skill Claude CodeCodex

Verify a code change does what it should by running the app.

jun0-ds/sonmat

Plugin Claude Code

Bundles 6 skills, 3 agents, 1 hook · 378 tokens together

sonmat — External verification system. Six verification axes (guard/inspect/witness/punch/devil/scribe) + autoloop orchestration. Discovery-led depth, protocol-isolated intent/baseline-artifact comparator (witness), post-work persistence layer (scribe).

NazarKalytiuk/tarn

Plugin Claude Code

Bundles 1 MCP server, 1 plugin

CLI-first API testing tool for .tarn.yaml files with structured JSON output and a bundled MCP server for AI-assisted write/run/debug workflows. A companion tarn-lsp language server plugin ships from the same marketplace under the tarn-lsp name.

corralimited/snapdiff-mcp

MCP server Claude CodeCodexCursor +2

Visual-diff & change-detection tools that catch agentic UI drift for coding agents. Runs locally from the @corralimited/snapdiff-mcp npm package. Needs 2 environment variables to run.

ironclawdevs27/Argus

MCP server Claude CodeCodexCursor +2

Argus — the QA layer for AI-assisted development. Claude-native (MCP) Chrome audits across 67 categories — errors, visual regressions, a11y, security, performance — no test files, secrets redacted by default (Aegis). Runs locally from the argusqa-os npm package.

mockzilla/mockzilla-mcp

MCP server Claude CodeCodexCursor +2

Mockzilla MCP server. Mock any OpenAPI spec locally with Claude, Cursor, or Gemini CLI. Runs locally from the @mockzilla/mcp npm package. Needs 3 environment variables to run.

piyushpathakqa/Vigilis

MCP server Claude CodeCodexCursor +2

Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt. Runs locally from the vigilis-mcp npm package. Needs 1 environment variable to run.

christopherlouet/claude-base

Agent Claude Code

Autonomous audit-fix loop aligned with the Anthropic 2026 pattern (code-review plugin). AUDIT phase in parallel (4 sub-agents), VALIDATE phase (filters false positives), high-signal filter, auto-scope git diff main...HEAD. Flags --audit-only and --comment for read-only and inline PR post modes.

GxFn/Wakeflow

Skill Claude CodeCodex

Use in a window that has received a Wakeflow delivery for a test target - read the frozen test contract in the task package, run its approved steps in the real environment against the landing the implementation produced, record what each step actually observed with its evidence, then import the per-step report and…