Hands On Test
ktnyt/cclsp
Performs manual hands-on testing of a web application using playwright-cli.
Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration.
Install Testing Course Samples
$ npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/ai-agents-for-beginners testing-course-samples --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .claude/skills && cp -r skills-src/translations/pcm/.agents/skills/testing-course-samples .claude/skills/testing-course-samples && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "testing-course-samples" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/translations/pcm/.agents/skills/testing-course-samples into .claude/skills/testing-course-samples/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-course-samples", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/microsoft/ai-agents-for-beginners/tree/main/translations/pcm/.agents/skills/testing-course-samplesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/ai-agents-for-beginners testing-course-samples --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .agents/skills && cp -r skills-src/translations/pcm/.agents/skills/testing-course-samples .agents/skills/testing-course-samples && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "testing-course-samples" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/translations/pcm/.agents/skills/testing-course-samples into .agents/skills/testing-course-samples/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-course-samples", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/ai-agents-for-beginners testing-course-samples --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/translations/pcm/.agents/skills/testing-course-samples .cursor/skills/testing-course-samples && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "testing-course-samples" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/translations/pcm/.agents/skills/testing-course-samples into .cursor/skills/testing-course-samples/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-course-samples", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/microsoft/ai-agents-for-beginners.git --path translations/pcm/.agents/skills/testing-course-samples--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/ai-agents-for-beginners testing-course-samples --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/translations/pcm/.agents/skills/testing-course-samples .gemini/skills/testing-course-samples && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "testing-course-samples" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/translations/pcm/.agents/skills/testing-course-samples into .gemini/skills/testing-course-samples/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-course-samples", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install microsoft/ai-agents-for-beginners testing-course-samplesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .github/skills && cp -r skills-src/translations/pcm/.agents/skills/testing-course-samples .github/skills/testing-course-samples && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "testing-course-samples" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/translations/pcm/.agents/skills/testing-course-samples into .github/skills/testing-course-samples/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-course-samples", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/ai-agents-for-beginners testing-course-samples --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/ai-agents-for-beginners.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/translations/pcm/.agents/skills/testing-course-samples .opencode/skills/testing-course-samples && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "testing-course-samples" agent skill from https://github.com/microsoft/ai-agents-for-beginners/tree/main/translations/pcm/.agents/skills/testing-course-samples into .opencode/skills/testing-course-samples/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-course-samples", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
testing-course-samples- GitHub stars
- 77k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 557 words
- Files
- 1
- Skills in repo
- 123
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration.
- Works in 4 steps: Python 3.12+ with all di course… → .env for di root of di repo (copy am… → You don do az login finish — di samples… → …
- Tasks that involve QA and bug reports
- SKILL.md covers Wen you go use am, Wetin you go need (check first), How to run the validation and How to understand di results, plus 2 more sections
- Calls pwsh, az and python
What it does
Testing Course Samples is an agent skill from microsoft/ai-agents-for-beginners, published by the product's own GitHub organization. Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration. E cover environment setup (.env, az login, packages), di scripts/validate-notebooks.ps1 runner, how to understand PASS/FAIL results, and which lessons need extra resources (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA, covering QA and bug reports and Browser testing. It works with Playwright, Azure OpenAI, Microsoft Azure and Azure AI Search. The repository describes itself as: 18 Lessons to Get Started Building AI Agents. The licence is MIT.
When your agent uses it
- Tasks that involve QA and bug reports
- Tasks that involve Browser testing
Example prompts
- “/testing-course-samples”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Python 3.12+ with all di course dependencies: python -m pip install -r requirements.txt
- .env for di root of di repo (copy am from .env.example) with at least
- You don do az login finish — di samples dey use AzureCliCredential (Entra ID, no need key).
- Make sure say di model deployment dey
What it can do on your machine
Read from SKILL.md and the folder at commit 25b7985. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pwshazpythonplaywright
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Testing Course Samples loads about 1.3k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 557 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:5
cover environment setup (.env, az login, packages), di scripts/validate-notebooks.ps1 - NoteMentions a .env fileSKILL.md:28
2. **`.env` for di root of di repo** (copy am from [`.env.example`](../../../../../.env.example)) with at least:
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from microsoft/ai-agents-for-beginners at commit 25b7985, republished under its MIT licence (© microsoft). 557 words, ~1,293 tokens.
Download SKILL.mdSave it as
.claude/skills/testing-course-samples/SKILL.md (or your agent's skills folder).- name
- testing-course-samples
- description
- Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration. E cover environment setup (.env, az login, packages), di scripts/validate-notebooks.ps1 runner, how to understand PASS/FAIL results, and which lessons need extra resources (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
Testing di Course Samples
Make sure say di lesson notebooks and code samples dey run well well for one live
Microsoft Foundry / Azure OpenAI setup. Di repo get one runner wey dey for
scripts/validate-notebooks.ps1 wey
dey run every Python notebook without display and e go show PASS/FAIL matrix.
Wen you go use am
- "Make sure say all di notebooks / samples dey work for my Azure subscription."
- "Quick check di course after you upgrade packages or change models."
- "Which lessons still dey pass / fail for live?"
No use am for di AI Smoke Test GitHub Action (wey dey check deployed
hosted agents — see tests/README.md). Dis skill
dey run di notebooks for local machine.
Wetin you go need (check first)
- Python 3.12+ with all di course dependencies:
python -m pip install -r requirements.txtplus di executor:python -m pip install nbconvert ipykernel. .envfor di root of di repo (copy am from.env.example) with at least:AZURE_AI_PROJECT_ENDPOINT— Foundry project endpoint (https://<account>.services.ai.azure.com/api/projects/<project>)AZURE_AI_MODEL_DEPLOYMENT_NAME— one deployment wey no old (e.g.gpt-5-mini)AZURE_OPENAI_ENDPOINT(https://<account>.openai.azure.com) andAZURE_OPENAI_DEPLOYMENTfor di lessons wey dey call Azure OpenAI directly (Lesson 06, 02-azure-openai, 14 handoff/human-loop).
- You don do
az loginfinish — di samples dey useAzureCliCredential(Entra ID, no need key). - Make sure say di model deployment dey:
az cognitiveservices account deployment list -g <rg> -n <account> -o table.
How to run the validation
# All Python notebooks (no go include .NET, .venv, site-packages, translations, skill assets)
pwsh scripts/validate-notebooks.ps1
# One lesson, wit longer time wey e fit run per cell
pwsh scripts/validate-notebooks.ps1 -Filter '08-*' -Timeout 600
# Only show wetin go run (no dey run anything)
pwsh scripts/validate-notebooks.ps1 -List
# Clear interpreter (if `python` no dey for PATH, like Windows Store alias)
pwsh scripts/validate-notebooks.ps1 -Python "C:/path/to/python.exe"Di script dey write di runs copy, per-notebook logs, and results.json go
$env:TEMP\aiab-nbval and e go exit with di number of failures.
Temporary failures (shared-subscription HTTP 429 rate limits, one-time
AzureCliCredential token wahala, or timeout) e go try again automatically
(-Retries, default 2, plus -RetryDelaySeconds backoff, default 20). If
one model deployment dey always 429, check di subscription's GlobalStandard
TPM quota (az cognitiveservices usage list -l <region>) — even if you raise one
deployment capacity e no go help if di subscription quota don finish.
Show full SKILL.md (253 more words)Show less
How to understand di results
PASS— di notebook run finish without any cell error.FAIL— di first*Error/*Exceptionline dey appear; open di rightlog_*.txtfor di output folder to see di full problem.- One single notebook failure dey controlled by
-Timeout(per cell), so if one human-in-the-loop cell jam, e go showStdinNotImplementedErrorinstead of hang.
Lessons wey need extra things (dem go fail if no get dem)
| Lesson | Extra requirement |
|---|---|
| 05 Agentic RAG | Azure AI Search (AZURE_SEARCH_SERVICE_ENDPOINT, key) — get fallback way wey dey memory |
| 11 MCP / GitHub | GitHub MCP server + PAT |
| 13 memory (cognee) | cognee setup with one model provider |
| 15 browser-use | Playwright browsers installed (playwright install) + AZURE_OPENAI_CHAT_DEPLOYMENT_NAME |
| 17 local agent | Foundry Local runtime + Qwen model wey you don download (on-device, no cloud) |
*-dotnet-* notebooks | .NET Interactive kernel (no include by default; use -IncludeDotnet) |
How to report back
Summarize am as PASS/FAIL table grouped by lesson. Separate real regressions
(code/config bugs wey need fix) from environment problems (missing Search/Foundry Local/PAT),
and talk about di failing log_*.txt for each real failure.
<!-- CO-OP TRANSLATOR DISCLAIMER START -->Disclaimer: Dis document don translate wit AI translation service Co-op Translator. Even tho we dey try make am correct, abeg make you know say automated translation fit get errors or mistakes. Di original document for dia own language na im be di correct source. For important info, make person wey sabi human translation do am. We no go responsible for any misunderstanding or wrong understanding wey fit happen because of dis translation.
<!-- CO-OP TRANSLATOR DISCLAIMER END -->© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in translations/pcm/.agents/skills/testing-course-samples of microsoft/ai-agents-for-beginners.
Open the folder on GitHubat commit 25b7985
Compare with similar skills
Testing Course Samples next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Testing Course Samples this skillmicrosoft/ai-agents-for-beginners | 77k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Hands On Testktnyt/cclsp | 675 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Windows QA EngineerCodeAlive-AI/ai-driven-development | 157 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Agentic Browser Testingpetrkindlmann/qa-skills | 165 | — | ~4.5k | Automated safety check: Pass | MIT | |
| Record E2E Giflablup/backend.ai-webui | 133 | — | ~907 | Automated safety check: Notes | LGPL-3.0 | |
| Permission ManageraAAaqwq/AGI-Super-Team | 105 | 1 repos | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Windows QA Engineer
CodeAlive-AI/ai-driven-development
A skill your agent uses when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP.
Agentic Browser Testing
petrkindlmann/qa-skills
Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script.
Record E2E Gif
lablup/backend.ai-webui
Record Playwright e2e tests as one GIF per test case (video → ffmpeg palette GIF) and return a markdown table for a PR description.
Permission Manager
aAAaqwq/AGI-Super-Team
管理Claude Code的全局工具权限配置，自动将MCP命令或其他工具添加到allowedTools中，避免每次使用时都需要手动批准。工作流程：确认用户需要添加的命令 - 确认添加级别(默认全局~/.claude.json) - 执行添加 - 验证并提醒重启。
LangBot Environment Setup
langbot-app/LangBot
Prepares a LangBot development and testing environment for an agent, covering service startup, proxy settings and browser access through Computer Use or Playwright MCP.
More from microsoft/ai-agents-for-beginners
All 123 skills in this repo- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
A skill your agent uses when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script…
- Official
Azure Openai To Responses
microsoft/ai-agents-for-beginners
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API.
- Official
Azure Openai To Responses
microsoft/ai-agents-for-beginners
Shift Python apps dem from Azure OpenAI Chat Completions go Responses API.
- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
Kasuta, kui kasutaja palub luua, üles ehitada või redigeerida Jupyteri märkmikke (.ipynb) katsetuste, uurimiste või juhendite jaoks; eelista kaasasolevaid malle ja käivita abiskript newnotebook.py…
- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
Käytetään, kun käyttäjä pyytää luomaan, alustamaan tai muokkaamaan Jupyter-muistikirjoja (.ipynb) kokeita, tutkimuksia tai opetusohjelmia varten; käytä mieluummin mukana olevia mallipohjia ja…
- Official
Jupyter Notebook
microsoft/ai-agents-for-beginners
À utiliser lorsque l'utilisateur demande de créer, structurer ou modifier des notebooks Jupyter (.ipynb) pour des expériences, explorations ou tutoriels ; privilégiez les modèles fournis et exécutez…
Related
Categories
Questions about Testing Course Samples
What does Testing Course Samples do?
Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration. Testing Course Samples is an agent skill from microsoft/ai-agents-for-beginners, published by the product's own GitHub organization. Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration.
When should I use Testing Course Samples?
Testing Course Samples fits situations like: tasks that involve QA and bug reports; tasks that involve Browser testing.
How do I install Testing Course Samples in Claude Code?
Run `npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a claude-code`. Or copy the skill folder (translations/pcm/.agents/skills/testing-course-samples in microsoft/ai-agents-for-beginners) into .claude/skills/testing-course-samples in your project. Claude Code loads it when a task matches its description.
How do I install Testing Course Samples in Codex?
Run `npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a codex`. Or copy the skill folder (translations/pcm/.agents/skills/testing-course-samples in microsoft/ai-agents-for-beginners) into .agents/skills/testing-course-samples in your project. Codex loads it when a task matches its description.
Can I use Testing Course Samples in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/ai-agents-for-beginners --skill testing-course-samples -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/testing-course-samples, .gemini/skills/testing-course-samples, .github/skills/testing-course-samples and .opencode/skills/testing-course-samples in your project.
What does Testing Course Samples need to run?
Going by SKILL.md and its folder, Testing Course Samples needs the command-line tools its instructions call (pwsh, az, python and playwright). Our summary lists: Python 3.
Does Testing Course Samples access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Testing Course Samples safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Testing Course Samples use?
Testing Course Samples is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Testing Course Samples use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Testing Course Samples?
Skills that share tags, products or a category with Testing Course Samples: Hands On Test (ktnyt/cclsp, 675 stars), Windows QA Engineer (CodeAlive-AI/ai-driven-development, 157 stars), Agentic Browser Testing (petrkindlmann/qa-skills, 165 stars) and Record E2E Gif (lablup/backend.ai-webui, 133 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Testing Course Samples?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/ai-agents-for-beginners, which has 76,612 GitHub stars. The repository holds 123 skills in this directory. The repository was last updated on September 19, 2026.
Source: microsoft/ai-agents-for-beginners on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.