session-debug
Diagnose issues in the current Amplifier session — misconfigured tools, failing operations, unexpected behavior. Use when something isn't working right.
⌘ K
Newest skills
287 skills
second-opinion
Independent review of current work or a past session. USE WHEN a user wants a second opinion. DO NOT USE WHEN ordinary code review is wanted — use code-review.
code-review
Review changed code for reuse, quality, and efficiency, then fix any issues found.
goal-batch
Batch independent work into isolated /goal lanes — one worktree, branch, and tmux session each — get your approval, then verify and merge every lane yourself. Use when work decomposes into pieces that can run at the same time: "run these in parallel", "goal-batch", "launch lanes for these", "work these N tasks simultaneously", "batch these as goals". Nothing launches until you've seen the lane split and said go, and this is NOT fire-and-forget: the orchestrating session re-runs the full suite after every merge and never accepts a lane's own claim that it finished. NOT for bounded edits that ea
amplifier-config
Explain, inspect, troubleshoot, and safely modify Amplifier CLI configuration — providers, settings scopes, bundles, routing, skills, and source overrides. Use when someone describes desired Amplifier CLI behavior and needs effective-value provenance, a safe change plan, implementation, or outcome-based verification.
pre-push-review
Pre-PR self-review using the same criteria as the automated review-pr-opened GitHub Action. Catches stale mock patch targets, dead imports with noqa suppressors, fixture env-var leaks, and silent ineffective patches BEFORE they are flagged by CI. Run before pushing any branch to a PR on microsoft/amplifier-resolve. Triggers on: "review before push", "pre-PR check", "self-review before pushing", "catch issues before CI", "is this ready to push".
testing-course-samples
Gamitin kapag hiniling na i-validate, subukan, smoke-test, o patakbuhin ang notebook ng kurso at mga halimbawa ng code laban sa isang live na Microsoft Foundry / Azure OpenAI na configuration. Saklaw nito ang pag-setup ng kapaligiran (.env, az login, mga package), ang scripts/validate-notebooks.ps1 runner, ang pagpapakahulugan ng mga resulta na PASS/FAIL, at kung aling mga aralin ang nangangailangan ng karagdagang mga mapagkukunan (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
Tumia wakati unapoombwa kuthibitisha, kujaribu, kufanya mtihani wa haraka, au kuendesha daftari la kozi na mifano ya msimbo dhidi ya usanidi hai wa Microsoft Foundry / Azure OpenAI. Inajumuisha usanidi wa mazingira (.env, az login, vifurushi), mchezaji wa scripts/validate-notebooks.ps1, kutafsiri matokeo ya PASS/FAIL, na ni masomo yapi yanayohitaji rasilimali za ziada (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
Použite, keď sa vyžaduje overenie, testovanie, rýchle testovanie alebo spustenie poznámkového bloku kurzu a ukážok kódu proti živej konfigurácii Microsoft Foundry / Azure OpenAI. Pokrýva nastavenie prostredia (.env, az login, balíky), skript runner scripts/validate-notebooks.ps1, interpretáciu výsledkov PASS/FAIL a ktoré lekcie potrebujú ďalšie zdroje (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
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-course-samples
Brukes når du blir bedt om å validere, teste, røykteste eller kjøre kursets notatbok og kodeeksempler mot en aktiv Microsoft Foundry / Azure OpenAI-konfigurasjon. Dekker miljøoppsett (.env, az login, pakker), skriptet/validate-notebooks.ps1-kjøreren, tolkning av PASS/FAIL-resultater, og hvilke leksjoner som trenger ekstra ressurser (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
Gunakan apabila diminta untuk mengesahkan, menguji, melakukan ujian asap, atau menjalankan buku nota dan contoh kod kursus terhadap konfigurasi Microsoft Foundry / Azure OpenAI secara langsung. Meliputi penyediaan persekitaran (.env, az login, pakej), skrip/validate-notebooks.ps1 sebagai pelancar, mentafsir keputusan LULUS/GAGAL, dan pelajaran mana yang memerlukan sumber tambahan (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
Koristite kada se zatraži validacija, testiranje, smoke-test ili pokretanje bilježnica i primjera koda tečaja protiv aktivne Microsoft Foundry / Azure OpenAI konfiguracije. Obuhvaća postavljanje okruženja (.env, az login, pakete), pokretač scripts/validate-notebooks.ps1, tumačenje PASS/FAIL rezultata i koje lekcije zahtijevaju dodatne resurse (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
השתמש כאשר מתבקשים לבדוק תוקף, לבצע בדיקת פונקציונליות בסיסית, או להריץ את המחברת ודוגמאות הקוד של הקורס נגד תצורת Microsoft Foundry / Azure OpenAI חיה. כולל הגדרת סביבה (.env, az login, חבילות), הרצת הסקריפט scripts/validate-notebooks.ps1, פירוש תוצאות PASS/FAIL, ואילו שיעורים דורשים משאבים נוספים (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
Use when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration. Covers environment setup (.env, az login, packages), the scripts/validate-notebooks.ps1 runner, interpreting PASS/FAIL results, and which lessons need extra resources (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
testing-course-samples
Use when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration. Covers environment setup (.env, az login, packages), the scripts/validate-notebooks.ps1 runner, interpreting PASS/FAIL results, and which lessons need extra resources (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
test-local
Runs an Agent 365 AI Teammate agent locally and opens AgentsPlayground for interactive local testing. Works with any AI Teammate stack — .NET (AgentFramework, Semantic Kernel), Node.js (LangChain, OpenAI, Claude SDK, Semantic Kernel, Google ADK), or Python (AgentFramework, LangChain, OpenAI, Claude, Semantic Kernel, Google ADK). Checks prerequisites (agentsplayground CLI, build tools), builds the agent, starts it in the background, and launches the playground UI pointed at the local endpoint. AgentsPlayground connects to /api/messages over HTTP — the LLM framework does not matter.
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
verify-dotnet-samples
How to build, run and verify the .NET sample projects in the Agent Framework repository. Use this when a user wants to verify that the samples still function as expected.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.