Skill Masterclass for QA
Build reusable AI Skills that turn Claude into a testing specialist for your whole team.
36
agent skills
7
STLC phases
22
framework skills
46
sections of notes
∞
lifetime access
Build a Copilot skill that turns a Jira story into a PDF + XLSX test plan, then install the full 36-skill QA Skill Suite. Taught by Pramod Dutta · The Testing Academy.
✓ Instant access✓ Lifetime access✓ 30-day money back✓ MIT-licensed skill files
Highly Recommended Course. Easy to Understand, Informative, Very Well Organized.Thank you!!
John Smith
This is an amazing course!. Very well thought out Course offering lots of value. Thanks!
Emma Wells
What happens next
In the next sixty seconds
No waiting for a drip schedule, no “your access will be activated within 24 hours”. You complete the form, you are in.
What is included
Everything that unlocks with this purchase
Included
5 class recordings
The full masterclass: building custom AI skills with GitHub Copilot and Claude Code, agent skills for QA engineers, custom automation skills, and the 250+ skill walkthrough.
Included
Basics & Install notes
A written, diagrammed lesson: what a skill is, the ladder from prompt to agent, install commands for macOS / Linux / Windows, the full build, and the top five skills to install first.
Included
46-section Full Notes
The searchable reference: complete SKILL.md, both scripts explained line by line, all 36 skills, troubleshooting tables, security checklist, glossary, interview questions, and self-check quizzes.
Included
The 36-skill suite
14 STLC skills across all seven phases, an 11-skill Playwright pack, and an 11-skill Selenium pack. MIT licensed, yours to fork and edit.
Included
The working build
test-plan-from-jira — SKILL.md plus fetch_jira.py and export.py, complete and copy-paste ready.Included
Lifetime access
Watch it as many times as you want. Updates to the notes are included, and there is no renewal.
The syllabus
Twelve modules, end to end
| # | Module | What you leave with |
|---|---|---|
| 01 | What an LLM actually is | Next-token prediction and the six limitations — so nothing later feels like magic |
| 02 | LLM vs AI Agent | The formula: LLM + memory + tools + a stopping loop. Where MCP fits. |
| 03 | Prompt → Skill → Agent | The ladder, the comparison table, and when to stop climbing |
| 04 | What an agent skill is | SKILL.md front-matter, description matching, the instruction body |
| 05 | Writing a description that fires | The single reason skills do not get picked up, fixed |
| 06 | Install & setup | Folder scopes, three packages, three env vars, all three operating systems |
| 07 | Secrets done properly | Env vars, the .gitignore you write first, the security conversation |
| 08 | Build: test-plan-from-jira | Full SKILL.md, the fetch script line by line, ADF flattening, custom field ids |
| 09 | Export to PDF + XLSX | reportlab and openpyxl, plus the extensions worth building |
| 10 | The 36-skill STLC suite | All 14 STLC skills, both framework packs, and which five to install first |
| 11 | n8n & LangFlow | The same agent as a four-node flow and a five-component graph, with install commands |
| 12 | Governance & rollout | Review gate, never-invent rule, metrics, anti-patterns, team playbook |
Start here
The five skills you install in week one
| # | Skill | Why it is first |
|---|---|---|
| 1 | jira-requirement-analyzer | The only skill that saves you work by telling you not to work |
| 2 | test-plan-generator | The one you build. Changes how the sprint feels within two stories. |
| 3 | test-case-writer | Where your hours actually go — and this takes them back |
| 4 | bug-reporter | Highest-frequency writing task in QA, most often rushed |
| 5 | pw-locator-fixer / se-wait-fixer | Pick by stack. Both kill “works locally, fails in CI”. |
The shift
Before and after
| The task | Before | After |
|---|---|---|
| Reading a new story | You plan around AC that turn out to be untestable | A testability verdict plus the questions to take back to the author |
| Writing a test plan | Half a day, negative cases thin out by 5 p.m. | Minutes to draft; your time goes to reviewing, not typing |
| Detailed test cases | The expensive, unglamorous hours | Drafted against every AC, with a rule forcing a negative case per criterion |
| Test data | You forget the empty string. Again. | Valid, invalid, boundary, unicode, and edge dates by name |
| A flaky test | Rerun it and hope | Flaky scored apart from broken, with an HTML report |
| Filing a bug | Rushed; developer replies “cannot reproduce” | A consistent, reproducible format — bounce-backs drop |
| Closure report | Written the night before the review | Drafted from your execution log, coverage gaps attached |
| Sharing your standards | A wiki page nobody reads | A committed skill the newest joiner inherits on clone |
Honest framing. This does not remove QA work — it moves it. Less writing, more reviewing and judging risk. That was always the valuable part of the job.
30-day money-back guarantee
Work through it. If it does not help, ask for your money back.
Build the skill, install the five, run it on a real story from your sprint. If it has not changed how you work, email us within 30 days and you get a refund. No form to fill in, no questions designed to talk you out of it.
Before you pay
The questions people actually ask
Do I need to know how to code?
No, for most of it. Fourteen of the 36 skills are plain-English instruction files. The worked build uses two Python scripts that are given to you complete — you copy them and run them. If you can run a command in a terminal, you can finish this.
Copilot or Claude Code — which do I need?
Either. A skill is a folder with a SKILL.md and the format is portable. We show both paths, plus how to convert a suite skill into a Copilot
.prompt.md.Do I need to pay for an API key too?
No. Your existing Copilot or Claude subscription is enough. No separate model bill, no cloud account, nothing to provision.
When do I get access?
Immediately after payment. Your login is emailed and the full curriculum unlocks — recordings and both written lessons. Nothing is drip-scheduled.
Is the 36-skill suite really free and MIT licensed?
Yes. The files are free; the masterclass is where you learn how the format works, how to write a description that fires, how to debug the Jira call, and how to govern the output.
Will this let AI sign off on my releases?
No, and we deliberately do not help you build that. Every skill stops at a human review gate: it drafts, states assumptions, and hands back. If unreviewed AI sign-off is your goal, this is the wrong purchase.
My Jira is Server / Data Center, not Cloud.
Concepts and the whole suite work unchanged. The fetch script targets Jira Cloud REST v3, so you adjust the endpoint and auth. We cover finding your own field ids, which is the part that genuinely differs.
Playwright or Selenium?
Both are covered with a dedicated 11-skill pack each. Playwright is TypeScript, Selenium is Java + TestNG. Pick the one your team runs — you do not need both.
How long does it take?
One afternoon gets you the working skill and the five-skill install, which is most of the practical value. There is a 4-week path if you want to take a full story through the whole STLC.
Do I get written notes or only video?
Both. AI Agent Skills Basics and Install (diagrammed build lesson) and Full Notes — a 46-section reference with every command, both scripts explained, all 36 skills, troubleshooting, glossary, and quizzes.
What if it is not for me?
30-day money-back guarantee. Ask and you get a refund.
Is my ticket data safe?
That is a decision you should make deliberately, and we show you what to check. The fetch script requests six fields rather than the whole issue precisely so you know what leaves your machine.
Complete your enrolment above
One skill this week. Thirty-six next week.
You leave with a working
test-plan-from-jira skill in your repo, the full 36-skill STLC suite, a 46-section written reference, and a governance model you can defend in a review.✓ Instant access✓ Lifetime access✓ 5 recordings + 2 written lessons✓ 36 MIT-licensed skills✓ 30-day money back
