PramodDutta

Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.

Teach agents to use AI browser agents for exploratory and smoke QA with step budgets, evidence-based assertions, guardrails, and Playwright conversion.

Teach agents to build synthetic monitoring as code with Checkly, including Playwright browser checks, API checks, alerting, and CI deploy workflows.

Teach agents to use the Chrome DevTools MCP server for performance testing with traces, Core Web Vitals, throttling, and evidence-based analysis.

Teach agents to shard and parallelize Playwright, Jest, and pytest suites in CI to reduce wall-clock time while merging reports reliably.

Teach agents to run Nuclei DAST and API security scans in CI, write templates, and gate builds on actionable findings.

Teach agents to automate accessibility testing in CI with pa11y and pa11y-ci, including thresholds, sitemap crawling, GitHub Actions gating, and WCAG rule tuning.

Teach AI coding agents to use the Playwright CLI and debug loop efficiently with last-failed runs, locator probing, trace evidence, and safe healing.

Score, ATS-check, and tailor a resume against a specific job description, then produce a clean updated Word (.docx) resume. Use this skill whenever the user provides (or mentions) a resume plus a job description and wants any of: a resume score/review, an ATS keyword gap analysis, a resume rewritten or tailored to a JD, missing keywords added, or a polished .docx resume produced. Trigger on phrases like 'score my resume', 'review my resume', 'tailor my resume to this JD', 'ATS check', 'which keywords am I missing', 'update my resume', 'make my resume match this job', or whenever a resume file and a job description appear together. Also trigger if the user pastes Joblytics/Jobscan-style keyword lists and asks to incorporate them.

Full content production engine for Pramod Dutta / The Testing Academy. Give it ONE topic and it produces a complete publish-ready pack in Pramod's brand voice: LinkedIn post, Medium article, YouTube script, Instagram carousel script, Instagram carousel image prompt, Medium cover image prompt, and LinkedIn cover image prompt. Use whenever a topic about QA, SDET, testing, Playwright, AI testing, automation, or QA careers is provided.

Build a structured, high-quality AI prompt using the RICE-POT framework (Role, Instructions, Context, Example, Parameters, Output, Tone). Use this whenever the user wants to create, write, fix, structure, or improve a prompt — especially for generating test cases, code, documents, or any repeatable AI task — or mentions "RICE-POT", "prompt template", "build me a prompt", "structure this prompt", "help me write a prompt", or hands over a rough/messy prompt to clean up. Trigger this even when the user only describes what they want the AI to do without naming RICE-POT at all.

Set up a DeepEval LLM-as-judge evaluation framework from scratch for any chatbot, RAG pipeline, AI agent, or LLM-backed app under test — the same architecture used in Chapter 19 (ShopSphere chatbot, RAG Explorer, and the live BrowserBash bot). Use this skill WHENEVER the user wants to "evaluate", "test", "score", "benchmark", "add metrics to", "measure quality of", or "QA" a chatbot / RAG / agent / LLM app, or asks to "set up DeepEval", "build an eval harness", "judge an LLM", "add a new eval target", "add a metric", or replicate the Chapter 19 framework for a new application — even if they don't say the word "DeepEval". Covers the judge factory (OpenAI/Groq/Ollama), HTTP target clients, the metric registry, golden datasets, the FastAPI dashboard, the pytest suites, version pins, and the known gotchas.

Run large or multi-phase tasks as a tiered workflow - the top model (Fable/Opus) orchestrates while subagents on cheaper models (Sonnet, Haiku) do the bulk of the work, stretching usage limits without sacrificing quality. Use this skill whenever the user mentions hitting rate limits or usage limits, wants to "save tokens", asks to orchestrate or delegate work across models, says "use subagents", or gives any big task (multi-file refactor, full feature build, large research sweep, repo-wide analysis) that would burn significant tokens if done in a single session. Also use proactively when a task clearly decomposes into independent phases, even if the user never mentions limits or models.

Teach and implement Playwright AI agent workflows (Planner, Generator, Healer) with MCP and repository guardrails. Use when preparing workshops, generating Playwright tests with architecture constraints, or enforcing deterministic code generation through a rule engine.

Automate browser interactions using Playwright CLI tools. Covers both standard CLI (npx playwright) for test execution, codegen, debugging, reporting, and the new @playwright/cli for AI-agent-friendly persistent browser sessions.

Generate a Playwright Page Object (POM) class for the TTACart demo app (app.thetestingacademy.com/playwright/ttacart) by driving the live page and reading its real selectors. Use this whenever the user gives a TTACart page URL plus a flow to reach it and asks to "create a page object", "build the POM", "scaffold a page class", "POM this page", "generate the page object for the checkout/inventory/cart page", or pastes a TTACart URL and wants a typed page class — even if they don't say the word "POM". The generated class extends BasePage and matches the existing LoginPage / CartPage / InventoryPage conventions exactly (data-test locators, .js ESM imports, the `el` wrapper, `open()` + `assertLoaded()`), then is wired into the pages barrel and verified with typecheck + lint.

Use after every CI Playwright run to triage failures end-to-end. Runs RCA, hands locator failures to heal, runs the flaky detector over recent runs, files Jira bugs for product defects, returns a one-line summary.