AgenTeX

Plugin agentex from marketplace elgazzar-plugins in MhmdElGazzar/elgazzar-plugins. Commands read from the repo's manifest — 17 days ago.

Skills (17)

• api-integration

  Execute user-defined API calls during test runs, from the project's integration/ catalog. Use whenever a test step needs an HTTP call: verify via API that a UI action persisted, check an endpoint's response, or seed test data through a service. Triggers on spec steps starting with "api:", or request

• ask-kb

  Ask a project's knowledge base a natural-language question during a test run, via the KB Ask API, and read the answer as advisory context. Triggers on spec steps starting with "kb:", or requests like "ask the KB", "what does the knowledge base say", "how does <flow> work". Explicit only — the agent

• azure-integration

  Interact with Azure resources from a QA/test run via the Azure CLI (`az`) — login/auth, discovery, and reading App Service, Storage, Key Vault, and AKS resources. Use whenever a task needs to reach Azure (verify a deployment, tail app logs, read a blob/secret, get AKS credentials) or when `az` is no

• browser-driver

  The browser driver for test-execution runs. It drives a real browser through playwright-cli for unprefixed (prose) spec steps and covers isolated sessions, screenshot and console evidence, login modes, and the failure signatures that decide retry versus defect. Use when a test-execution run's driver

• bug-report-azure

  After a completed test/regression run where one or more defects were found, file them as tracker Bugs on the configured tracker — Azure DevOps or Jira Cloud (\"file these as Jira bugs\" works the same) — following a configurable bug template, through bundled Node scripts that talk to the tracker RES

• db-integration

  Execute user-defined database queries during test runs, from the project's integration/ catalog (SQL Server via sqlcmd). Use whenever a test step needs a DB check: verify a row was created/updated by a UI action, check column values, or seed test data. Triggers on spec steps starting with "db:", or

• define-flow

  Define a test flow by doing it: an agent-led session that builds a spec step by step in a live browser — the agent proposes each step, executes it immediately, and the user asserts the real outcome before the next step is defined. Use when a user wants to create a spec for a long or complex flow wit

• endpoint-testing

  Run a standalone API test pass over the project's cataloged endpoints ("api-tests"), independent of any browser test spec. Use for /test-endpoints, or requests like "run the API tests", "test all endpoints". Also opens the local API suite editor (/test-endpoints --edit) to review, fix and re-run cas

• extent-report

  Produce a standalone, self-contained extent-report.html — a dark-themed interactive dashboard (verdict banner, donut chart, per-status stat cards, expandable test-case cards with step-by-step detail). Use at the end of any playwright-cli test execution (one test case or a full parallel/sequential ba

• mobile-testing

  Test a native mobile app (Android/iOS) by driving it through Appium. Use whenever the user wants to test a mobile app for defects — happy paths, edge cases, and negative cases — either sequentially (human-in-the-loop, the default) or in parallel (autonomous, one session per available device/emulator

• optimize-login

  Pay a web application's login cost once per session instead of once per test — drive the login live, reduce it to the smallest script that works, save the browser session, and reload that session into a fresh browser to continue. Use when login is the slow part of a run, when several scenarios each

• swagger-import

  Generate an API catalog + suite of test cases (integration/api_test_suites/<service>/) from a Swagger 2.0 or OpenAPI 3.x JSON document. Use for /import-swagger, or requests like "import this swagger doc", "generate endpoint tests from this OpenAPI spec", or the guided wizard (/import-swagger --wizar

• task-estimation

  Creates QA testing tasks with estimation on the configured tracker's User Stories — Azure DevOps or Jira Cloud. Reads the sprint, analyzes each story, then creates all [Testing] tasks (ADO Tasks or Jira sub-tasks) behind ONE consolidated approval, through bundled REST scripts (no Azure CLI, no acli)

• test-design

  Designs test cases for User Stories on the configured tracker — Azure DevOps or Jira Cloud: analyze a story's acceptance criteria into test conditions, map them to test case titles, create the test artifacts (ADO Test Cases with structured steps, or the Jira issue type the user chooses — Jira has no

• test-execution

  Run test specs against an application and report defects, routing each step to its driver (browser via playwright-cli, API calls, database checks, knowledge-base questions, UI design checks). Use whenever the user wants to test a website, web app, or API for defects (happy paths, edge cases, negativ

• tracker-ops

  Ad-hoc work-item operations on the configured tracker — Azure DevOps or Jira Cloud — behind one approval per write batch. Use this skill whenever the user asks for a one-off board operation outside the shipped flows: "move PROJ-12 to In Progress", "transition this issue to Done", "comment on bug 471

• ui-check

  Execute ui-check: steps in test specs — compare the live page currently open in the browser under test against a declared design baseline: a Figma frame (identifier only; file + token configured once per project) or a screenshot image, in exact mode (every visible detail) or reference mode (only enu

Slash commands (11)

• /agentex:ask-kb

  Ask the project's Knowledge Base a natural-language question via the KB Ask API and show the answer with its sources. Usage: /ask-kb <question>, or /ask-kb <project>: <question> to target a specific project.

• /agentex:define-flow

  Define a test flow by doing it: an agent-led session that executes each step live as you define it, then saves a runnable spec. Usage: /define-flow [url] [on <env>] [existing-spec-path]. Pass an existing spec path to walk it through step by step and clarify it.

• /agentex:design-test

  Design test cases for User Stories on the configured tracker — Azure DevOps or Jira — analyze ACs into test conditions, create titled test artifacts with structured steps (ADO Test Cases linked Tested By; on Jira the issue type the user chooses, linked back to the story), all behind ONE consolidated

• /agentex:estimate-sprint

  Estimate QA effort for every User Story in the current sprint on the configured tracker (Azure DevOps or Jira) and create their `[Testing]` tasks from the project's `config/estimation.json` (proposed from your team's last closed sprints on the first run), behind ONE consolidated approval.

• /agentex:estimate-story

  Estimate QA effort for named User Stories (Azure DevOps IDs or Jira keys) and create the `[Testing]` tasks your project's `config/estimation.json` defines, proposed from your team's last closed sprints on the first run, behind ONE consolidated approval. No IDs → the current sprint (same as `/estimat

• /agentex:execute-mobile-test

  Execute tests against a native mobile app (Android/iOS), optionally from a named suite folder (e.g. suite2/). Sequential (human-in-the-loop) by default; say "parallel" for an autonomous run.

• /agentex:execute-test

  Execute tests against a target, optionally from a named suite folder (e.g. suite3/). Sequential (human-in-the-loop) by default; say "parallel" for an autonomous run.

• /agentex:import-swagger

  Generate an API catalog + suite of test cases from a Swagger 2.0 / OpenAPI 3.x JSON document (local file or URL). --wizard opens the guided page that collects real test data first.

• /agentex:init-test

  Initialize AgenTeX in the current project — scaffold a sample test suite, config/project.json, environments/qc.json, the executions output folder, a keys-only .env file, and CLAUDE.md guidance.

• /agentex:test-endpoints

  Run the standalone API test pass ("api-tests") over every cataloged case, independent of any browser test spec. --edit opens the local suite editor.

• /agentex:update-agentex

  Checks for a newer plugin version first (one confirmation before any pull; after a pull, stop and reload), then migrates the current project to the installed AgenTeX version's conventions — folder structure, config file schemas, the secrets-only .env split, catalog format, CLAUDE.md and .gitignore e

Subagents (3)

• api-executor

  Executes a standalone API endpoint test run ("api-tests") by running every cataloged case and returns a consolidated report. Dispatched by the endpoint-testing skill (one call per invocation — this is not per-browser-session, there's no browser involved). Never modifies application code or the catal

• mobile-qa-executor

  Executes a single QA test specification against a native mobile app in an isolated Appium session (one device/emulator) and returns a defect report. Dispatched by the mobile-testing orchestrator (one subagent per test file / device session). Never modifies application code.

• qa-executor

  Executes a single QA test specification (browser, API, and database steps) in its own isolated session and returns a defect report. Dispatched by the test-execution orchestrator (one subagent per test file / session). Never modifies application code.

Similar plugins