Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/PramodDutta/AITesterBlueprint4x.Loading the repository README…
Showing 40 of 145 collected skills.
Turn a vague user story into testable Given/When/Then acceptance criteria. Use when a tester or BA says "write acceptance criteria for this story", "make these ACs testable", "convert this to Given When Then", or pastes a one-line user story. Produces…
Build a requirements traceability matrix (RTM) that links requirements and acceptance criteria to scenarios, test cases and defects. Use when a QA lead says "build an RTM for this release", "which requirements have no tests", "find orphan test cases", or…
Score features by likelihood x impact into a risk matrix and turn it into test depth and execution order. Use when a QA lead says "prioritize testing by risk", "build a risk matrix for this release", "we only have 3 days, what do we test first", or pastes a…
Plan test environments and test data needs: environment matrix, browsers and devices, integrations, stubs, data refresh, access and a booking schedule. Use when a QA lead says "plan our test environments", "what environments and data do we need", "set up the…
Estimate test effort with a work breakdown structure (WBS) and three-point PERT estimates, with explicit assumptions and buffer. Use when a QA lead says "estimate the testing effort", "how many days do we need to test this", "give me a PERT estimate", or…
Turn a JIRA ticket into a review-ready test plan. Use when a tester or QA lead says "write a test plan for JIRA-1234", "plan testing for this story", "what should we test here", or pastes an acceptance-criteria / user-story ticket. Fetches the ticket,…
Write a product or release level test strategy covering test levels, test types, environments, tooling, automation approach, risk, entry/exit criteria and roles. Use when a QA lead says "write a test strategy for this product", "define our testing approach…
Design API-level test coverage from an endpoint or contract. Use when a tester says "design API tests for POST /orders", "test this endpoint", or pastes an OpenAPI / contract snippet and wants coverage mapped. Produces a coverage matrix across happy path,…
Write Gherkin feature files (Feature, Background, Scenario Outline with Examples, tags) from acceptance criteria, using declarative business-language steps. Use when a tester or SDET says "write BDD scenarios for this story", "convert these ACs to Gherkin",…
Design session-based exploratory testing charters with a mission, target areas, heuristics (SFDPOT, FEW HICCUPPS) and a timebox, plus a session report template. Use when a tester says "write exploratory charters for this feature", "plan an exploratory…
Design mobile app test coverage: device and OS matrix, gestures, interruptions, network conditions, permissions, background/foreground behavior and install/upgrade paths. Use when a tester says "design mobile tests for this app", "which devices should we test…
Apply black-box test design techniques (equivalence partitioning, boundary value analysis, decision tables, state transition, pairwise) to a field or business rule and show the derived cases. Use when a tester says "apply BVA to this field", "build a decision…
Convert test cases between formats (spreadsheet or CSV rows, Jira Xray or Zephyr import CSV, Gherkin, Markdown) without losing steps or expected results. Use when a tester says "convert these test cases to Xray CSV", "turn this spreadsheet into Gherkin",…
Review a set of test cases for clarity, atomicity, missing expected results, duplicates, weak test data and traceability, and return findings with fixes. Use when a QA lead says "review these test cases", "are my test cases good enough", "peer review this…
Turn an approved test case into a runnable automation script skeleton. Use when an engineer says "automate TC-5", "write a Playwright test for this", or "generate a Selenium script from this case". Produces a Playwright (TypeScript) or Selenium draft using…
Reads CI test results and classifies every failure as product bug, test bug, flaky, or environment, with the evidence behind each call. Use when an SDET says "why did the pipeline fail", "triage these CI failures", "is this a real bug or flaky", or pastes a…
Writes a daily or weekly QA status update for an active test cycle from real execution data. Use when a QA lead says "write today's QA status", "send the weekly test report", "summarize where testing stands", or pastes a test run export and defect list.…
Log and summarize the execution of a test cycle. Use when a tester says "log this run", "track execution for the sprint", or reports results case by case and wants them recorded. Captures pass / fail / blocked / not-run per case with evidence links and…
Turn a failure into a clean, reproducible bug report. Use when a tester says "file a bug for this", "write up this defect", or describes something broken and wants it documented properly. Produces a structured report — title, environment, steps to reproduce,…
Reduces a long or intermittent bug reproduction to the minimal reliable steps and conditions by bisecting steps, data, environment, and timing. Use when a tester says "shrink this repro", "find the minimal steps", "this bug only happens sometimes", or pastes…
Analyzes defect data for trends such as density per module, leakage to production, reopen rate, aging, and severity mix, then recommends actions. Use when a QA lead says "analyze our bug trends", "which module has the most defects", "what is our defect…
Runs a QA retrospective for a release or sprint: what went well, what escaped and why, and process changes with owners. Use when a QA lead says "run a QA retro", "why did these bugs escape", "prepare the release retrospective", or pastes escaped defects and…
Checks a release against a go-live checklist (exit criteria, open defects by severity, performance and security sign-offs, rollback plan, monitoring) and presents the evidence. Use when a release manager or QA lead says "are we ready to release", "prepare the…
Find the gaps between what was required and what was actually tested. Use when a lead says "where are our coverage gaps", "what isn't tested", or wants requirements and code areas checked against the executed and available tests. Builds a traceability view —…
Tests an AI agent's guardrails with explicit pass/fail criteria. Use when an SDET says "test the agent's guardrails", "make sure it never leaks PII", "check it can't call admin tools", or describes topic limits, tool permissions, or approval policies.…
Designs test scenarios for tool-using AI agents, from task success to cost limits. Use when an SDET says "how do we test this agent", "write test scenarios for our AI agent", "check it picks the right tools", or pastes an agent's tool definitions and system…
Evaluates an agent's trajectory (its sequence of tool calls) against expected paths using exact, in-order, and any-order matching. Use when an SDET says "check the agent's tool calls", "score these agent traces", "did it take the right path", or pastes agent…
Tests multi-agent workflows (CrewAI or LangGraph style) for correct handoffs, shared state, role adherence, termination, and single-agent failure. Use when an SDET says "test our multi-agent workflow", "check the agents hand off correctly", "make sure the…
Tests LLM apps and agents you are authorized to test against direct and indirect prompt injection, data exfiltration, and jailbreak-style instructions. Use when a security tester or SDET says "test our chatbot for prompt injection", "can a document hijack the…
Designs consumer-driven contract tests (Pact) and OpenAPI schema conformance checks between services. Use when an SDET says "add contract tests between these services", "set up Pact for our consumer", "check the API matches the OpenAPI spec", or describes a…
Designs API mocks and stubs (WireMock or similar) for dependencies, covering success, error, latency, and stateful scenarios. Use when an SDET says "mock the payment service", "stub this third-party API", "simulate timeouts and 500s from a dependency", or…
Tests GraphQL APIs: queries, mutations, variables, the errors array, auth, depth and complexity limits, and introspection settings. Use when an SDET says "write tests for our GraphQL API", "test this mutation", "check GraphQL error handling", or pastes a…
Builds a Postman collection with environments, pre-request scripts, and pm.test assertions that runs with Newman in CI. Use when a tester says "build a Postman collection for this API", "add tests to my Postman requests", "run our collection in CI with…
Generates Python API tests with pytest and requests: fixtures for base URL and auth, parametrize for negative cases, and schema validation with jsonschema or pydantic. Use when an SDET says "write pytest API tests for this endpoint", "add negative cases with…
Generates REST Assured API tests in Java (given/when/then) with status, JSON schema, and auth checks. Use when an SDET says "write REST Assured tests for this endpoint", "add JSON schema validation in Java", "cover auth and negative cases with RestAssured",…
Generates Appium mobile test drafts (WebdriverIO or Java) with accessibility-id locators, Android and iOS capabilities, and explicit waits. Use when an SDET says "write an Appium test for this screen", "automate this mobile flow", "set up Appium capabilities…
Designs a test automation framework structure (layers, page objects or screenplay, config, test data, reporting, CI) for a given stack. Use when an SDET says "design our automation framework", "how should we structure our Playwright/Selenium project", "set up…
Detects flaky tests from run history (pass/fail flips on the same code), quarantines them with tags or annotations, and tracks owners and exit criteria. Use when an SDET says "find our flaky tests", "quarantine this flaky test", "our pipeline fails randomly",…
Writes API tests in Cypress with cy.request and combines API setup with UI checks. Use when an SDET says "write API tests in Cypress", "test this endpoint with cy.request", "create the data through the API and check it in the UI", or pastes an endpoint spec…
Configures Cypress to run reliably in CI, with GitHub Actions as the default. Use when an SDET says "run Cypress in GitHub Actions", "parallelize our Cypress suite", "save screenshots and videos from CI", or pastes a slow or failing pipeline. Produces a…
The README is too large to preview here. The Skill directory remains available below.