[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699WJBRX69XANKJMPSXCEJG":3,"skill-same:01M699WJBRX69XANKJMPSXCEJG":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":31,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M699WJBRX69XANKJMPSXCEJG","testing-course-samples",null,"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 \u002F Azure OpenAI. Inajumuisha usanidi wa mazingira (.env, az login, vifurushi), mchezaji wa scripts\u002Fvalidate-notebooks.ps1, kutafsiri matokeo ya PASS\u002FFAIL, na ni masomo yapi yanayohitaji rasilimali za ziada (Azure AI Search, GitHub MCP, Foundry Local, Playwright).","microsoft\u002Fai-agents-for-beginners","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6998ZK2275KMJE6Y5SEA2X2",79423,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fsw\u002F.agents\u002Fskills\u002Ftesting-course-samples\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[32,33,34,35,36,9,37,38,39,40,41],"testing","testing course samples","MCP","github","playwright","foundry","foundry local","microsoft foundry","validate","azure ai","2026-11-10 10:12:30",false,"---\nname: testing-course-samples\ndescription: Tumia wakati unapoombwa kuthibitisha, kujaribu, kufanya mtihani wa haraka,\n  au kuendesha daftari la kozi na mifano ya msimbo dhidi ya usanidi hai wa Microsoft\n  Foundry \u002F Azure OpenAI. Inajumuisha usanidi wa mazingira (.env, az login, vifurushi),\n  mchezaji wa scripts\u002Fvalidate-notebooks.ps1, kutafsiri matokeo ya PASS\u002FFAIL, na ni\n  masomo yapi yanayohitaji rasilimali za ziada (Azure AI Search, GitHub MCP, Foundry\n  Local, Playwright).\n---\n# Kupima Sampuli za Kozi\n\nThibitisha kuwa daftari za mafunzo na sampuli za msimbo zinafanya kazi dhidi ya\nusanidi wa Microsoft Foundry \u002F Azure OpenAI unaoishi. Hifadhidata inaendesha\n[`scripts\u002Fvalidate-notebooks.ps1`](..\u002F..\u002F..\u002F..\u002F..\u002Fscripts\u002Fvalidate-notebooks.ps1) ambayo\ninaendesha kila daftari la Python bila kichwa na inachapisha matriki ya PASS\u002FFAIL.\n\n## Wakati wa kutumia\n- \"Thibitisha daftari zote \u002F sampuli dhidi ya usajili wangu wa Azure.\"\n- \"Fanya mtihani mdogo wa kozi baada ya kusasisha vifurushi au kubadilisha mifano.\"\n- \"Ni masomo gani bado yanapita \u002F kushindwa kuishi?\"\n\nUsitumie hii kwa AI Smoke Test GitHub Action (ambayo inathibitisha mawakala waliowekwa *wazi*\n— angalia [`tests\u002FREADME.md`](..\u002F..\u002F..\u002Ftests\u002FREADME.md)). Ujuzi huu unaendesha daftari\nkiasili.\n\n## Masharti ya awali (angalia kwanza)\n1. **Python 3.12+** pamoja na tegemezi za kozi: `python -m pip install -r requirements.txt`\n   pamoja na mtekelezaji: `python -m pip install nbconvert ipykernel`.\n2. **`.env` kwenye mizizi ya hifadhidata** (nakili kutoka [`.env.example`](..\u002F..\u002F..\u002F..\u002F..\u002F.env.example)) kwa angalau:\n   - `AZURE_AI_PROJECT_ENDPOINT` — kiungo cha mradi wa Foundry\n     (`https:\u002F\u002F\u003Caccount>.services.ai.azure.com\u002Fapi\u002Fprojects\u002F\u003Cproject>`)\n   - `AZURE_AI_MODEL_DEPLOYMENT_NAME` — usambazaji usioharibika (mfano `gpt-5-mini`)\n   - `AZURE_OPENAI_ENDPOINT` (`https:\u002F\u002F\u003Caccount>.openai.azure.com`) na `AZURE_OPENAI_DEPLOYMENT`\n     kwa masomo yanayopiga Azure OpenAI moja kwa moja (Somo 06, 02-azure-openai, 14 handoff\u002Fhuman-loop).\n3. **`az login`** imekamilika — sampuli zinathibitishwa na `AzureCliCredential` (Entra ID, bila funguo).\n4. Thibitisha usambazaji wa mfano uko:\n   `az cognitiveservices account deployment list -g \u003Crg> -n \u003Caccount> -o table`.\n\n## Kuendesha uthibitisho\n```powershell\n# Vitabu vyote vya Python (huacha .NET, .venv, site-packages, tafsiri, mali za ujuzi)\npwsh scripts\u002Fvalidate-notebooks.ps1\n\n# Somo moja tu, na muda mrefu wa kusubiri kwa kila seli\npwsh scripts\u002Fvalidate-notebooks.ps1 -Filter '08-*' -Timeout 600\n\n# Orodhesha tu kile kitakachotekelezwa (bila kuendesha)\npwsh scripts\u002Fvalidate-notebooks.ps1 -List\n\n# Mfasiri waziwazi (ikiwa `python` haipo PATH, mfano lahaja ya Duka la Windows)\npwsh scripts\u002Fvalidate-notebooks.ps1 -Python \"C:\u002Fpath\u002Fto\u002Fpython.exe\"\n```\nSkripti inaandika nakala zilizotekelezwa, rekodi za kila daftari, na `results.json` kwenye\n`$env:TEMP\\aiab-nbval` na inatoka kwa idadi ya kushindwa.\n\nKushindwa kwa muda mfupi (vizuizi vya kiwango cha HTTP 429 vya usajili wa pamoja, tatizo la\n`AzureCliCredential` mara moja kwa wakati, au muda wa kusubiri) hurudishwa moja kwa moja\n(`-Retries`, chaguo-msingi 2, na `-RetryDelaySeconds` kwa kuchelewesha, chaguo-msingi 20). Ikiwa\nusambazaji wa mfano unapata mara kwa mara 429, angalia malipo ya TPM ya GlobalStandard ya usajili (`az cognitiveservices usage list -l \u003Cregion>`) —\nkuongeza uwezo wa usambazaji mmoja haifai wakati kiwango cha *usajili* kimeisha.\n\n\n## Kufasiri matokeo\n- `PASS` — daftari liliendesha vizuri bila kosa katika seli.\n- `FAIL` — mstari wa kwanza wa `*Error` \u002F `*Exception` unaonyeshwa; fungua\n  `log_*.txt` inayolingana katika saraka ya matokeo kwa urambazaji kamili.\n- Kushindwa kwa daftari moja kuna kikomo cha `-Timeout` (kila seli), hivyo seli inayosumbua\n  na mtu anayeingilia inaonyesha kama `StdinNotImplementedError` badala ya kusimamisha.\n\n## Masomo yanayohitaji rasilimali za ziada (inayotarajiwa kushindwa bila hizo)\n| Somo | Hitaji Ziada |\n|--------|-------------------|\n| 05 Agentic RAG | Azure AI Search (`AZURE_SEARCH_SERVICE_ENDPOINT`, ufunguo) — ina njia mbadala ya kumbukumbu ndani |\n| 11 MCP \u002F GitHub | Seva ya MCP ya GitHub + PAT |\n| 13 memory (cognee) | `cognee` imewekwa na mwanzilishi wa mfano |\n| 15 browser-use | Vivinjari vya Playwright vimewekwa (`playwright install`) + `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME` |\n| 17 local agent | Foundry Local runtime + mfano wa Qwen aliyopakuliwa (kifaa, si wingu) |\n| daftari za `*-dotnet-*` | Kernel ya .NET Interactive (haijajumuishwa kwa chaguo-msingi; tumia `-IncludeDotnet`) |\n\n## Kuripoti nyuma\nFupisha kama jedwali la PASS\u002FFAIL lililoainishwa kwa somo. Tambua tofauti za kweli\n(viholela vya msimbo\u002Fusanidi vya kurekebisha) dhidi ya mapungufu ya mazingira (kutokuwepo kwa Search\u002FFoundry Local\u002FPAT),\nna taja `log_*.txt` zinazoshindwa kwa kila kushindwa halisi.\n\n---\n\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER START -->\n**Kionyozo**:\nHati hii imetafsiriwa kwa kutumia huduma ya tafsiri ya AI [Co-op Translator](https:\u002F\u002Fgithub.com\u002FAzure\u002Fco-op-translator). Ingawa tunajitahidi kupata usahihi, tafadhali fahamu kwamba tafsiri za kiotomatiki zinaweza kuwa na makosa au upungufu wa usahihi. Hati ya asili katika lugha yake halisi inapaswa kuchukuliwa kama chanzo cha mamlaka. Kwa taarifa muhimu, tafsiri ya kitaalamu inayofanywa na binadamu inapendekezwa. Hatutojibu kwa kuelewa vibaya au tafsiri potofu zinazotokea kutokana na matumizi ya tafsiri hii.\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER END -->","# Kupima Sampuli za Kozi\n\nThibitisha kuwa daftari za mafunzo na sampuli za msimbo zinafanya kazi dhidi ya\nusanidi wa Microsoft Foundry \u002F Azure OpenAI unaoishi. Hifadhidata inaendesha\n[`scripts\u002Fvalidate-notebooks.ps1`](..\u002F..\u002F..\u002F..\u002F..\u002Fscripts\u002Fvalidate-notebooks.ps1) ambayo\ninaendesha kila daftari la Python bila kichwa na inachapisha matriki ya PASS\u002FFAIL.\n\n## Wakati wa kutumia\n- \"Thibitisha daftari zote \u002F sampuli dhidi ya usajili wangu wa Azure.\"\n- \"Fanya mtihani mdogo wa kozi baada ya kusasisha vifurushi au kubadilisha mifano.\"\n- \"Ni masomo gani bado yanapita \u002F kushindwa kuishi?\"\n\nUsitumie hii kwa AI Smoke Test GitHub Action (ambayo inathibitisha mawakala waliowekwa *wazi*\n— angalia [`tests\u002FREADME.md`](..\u002F..\u002F..\u002Ftests\u002FREADME.md)). Ujuzi huu unaendesha daftari\nkiasili.\n\n## Masharti ya awali (angalia kwanza)\n1. **Python 3.12+** pamoja na tegemezi za kozi: `python -m pip install -r requirements.txt`\n   pamoja na mtekelezaji: `python -m pip install nbconvert ipykernel`.\n2. **`.env` kwenye mizizi ya hifadhidata** (nakili kutoka [`.env.example`](..\u002F..\u002F..\u002F..\u002F..\u002F.env.example)) kwa angalau:\n   - `AZURE_AI_PROJECT_ENDPOINT` — kiungo cha mradi wa Foundry\n     (`https:\u002F\u002F\u003Caccount>.services.ai.azure.com\u002Fapi\u002Fprojects\u002F\u003Cproject>`)\n   - `AZURE_AI_MODEL_DEPLOYMENT_NAME` — usambazaji usioharibika (mfano `gpt-5-mini`)\n   - `AZURE_OPENAI_ENDPOINT` (`https:\u002F\u002F\u003Caccount>.openai.azure.com`) na `AZURE_OPENAI_DEPLOYMENT`\n     kwa masomo yanayopiga Azure OpenAI moja kwa moja (Somo 06, 02-azure-openai, 14 handoff\u002Fhuman-loop).\n3. **`az login`** imekamilika — sampuli zinathibitishwa na `AzureCliCredential` (Entra ID, bila funguo).\n4. Thibitisha usambazaji wa mfano uko:\n   `az cognitiveservices account deployment list -g \u003Crg> -n \u003Caccount> -o table`.\n\n## Kuendesha uthibitisho\n```powershell\n# Vitabu vyote vya Python (huacha .NET, .venv, site-packages, tafsiri, mali za ujuzi)\npwsh scripts\u002Fvalidate-notebooks.ps1\n\n# Somo moja tu, na muda mrefu wa kusubiri kwa kila seli\npwsh scripts\u002Fvalidate-notebooks.ps1 -Filter '08-*' -Timeout 600\n\n# Orodhesha tu kile kitakachotekelezwa (bila kuendesha)\npwsh scripts\u002Fvalidate-notebooks.ps1 -List\n\n# Mfasiri waziwazi (ikiwa `python` haipo PATH, mfano lahaja ya Duka la Windows)\npwsh scripts\u002Fvalidate-notebooks.ps1 -Python \"C:\u002Fpath\u002Fto\u002Fpython.exe\"\n```\nSkripti inaandika nakala zilizotekelezwa, rekodi za kila daftari, na `results.json` kwenye\n`$env:TEMP\\aiab-nbval` na inatoka kwa idadi ya kushindwa.\n\nKushindwa kwa muda mfupi (vizuizi vya kiwango cha HTTP 429 vya usajili wa pamoja, tatizo la\n`AzureCliCredential` mara moja kwa wakati, au muda wa kusubiri) hurudishwa moja kwa moja\n(`-Retries`, chaguo-msingi 2, na `-RetryDelaySeconds` kwa kuchelewesha, chaguo-msingi 20). Ikiwa\nusambazaji wa mfano unapata mara kwa mara 429, angalia malipo ya TPM ya GlobalStandard ya usajili (`az cognitiveservices usage list -l \u003Cregion>`) —\nkuongeza uwezo wa usambazaji mmoja haifai wakati kiwango cha *usajili* kimeisha.\n\n\n## Kufasiri matokeo\n- `PASS` — daftari liliendesha vizuri bila kosa katika seli.\n- `FAIL` — mstari wa kwanza wa `*Error` \u002F `*Exception` unaonyeshwa; fungua\n  `log_*.txt` inayolingana katika saraka ya matokeo kwa urambazaji kamili.\n- Kushindwa kwa daftari moja kuna kikomo cha `-Timeout` (kila seli), hivyo seli inayosumbua\n  na mtu anayeingilia inaonyesha kama `StdinNotImplementedError` badala ya kusimamisha.\n\n## Masomo yanayohitaji rasilimali za ziada (inayotarajiwa kushindwa bila hizo)\n| Somo | Hitaji Ziada |\n|--------|-------------------|\n| 05 Agentic RAG | Azure AI Search (`AZURE_SEARCH_SERVICE_ENDPOINT`, ufunguo) — ina njia mbadala ya kumbukumbu ndani |\n| 11 MCP \u002F GitHub | Seva ya MCP ya GitHub + PAT |\n| 13 memory (cognee) | `cognee` imewekwa na mwanzilishi wa mfano |\n| 15 browser-use | Vivinjari vya Playwright vimewekwa (`playwright install`) + `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME` |\n| 17 local agent | Foundry Local runtime + mfano wa Qwen aliyopakuliwa (kifaa, si wingu) |\n| daftari za `*-dotnet-*` | Kernel ya .NET Interactive (haijajumuishwa kwa chaguo-msingi; tumia `-IncludeDotnet`) |\n\n## Kuripoti nyuma\nFupisha kama jedwali la PASS\u002FFAIL lililoainishwa kwa somo. Tambua tofauti za kweli\n(viholela vya msimbo\u002Fusanidi vya kurekebisha) dhidi ya mapungufu ya mazingira (kutokuwepo kwa Search\u002FFoundry Local\u002FPAT),\nna taja `log_*.txt` zinazoshindwa kwa kila kushindwa halisi.\n\n---\n\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER START -->\n**Kionyozo**:\nHati hii imetafsiriwa kwa kutumia huduma ya tafsiri ya AI [Co-op Translator](https:\u002F\u002Fgithub.com\u002FAzure\u002Fco-op-translator). Ingawa tunajitahidi kupata usahihi, tafadhali fahamu kwamba tafsiri za kiotomatiki zinaweza kuwa na makosa au upungufu wa usahihi. Hati ya asili katika lugha yake halisi inapaswa kuchukuliwa kama chanzo cha mamlaka. Kwa taarifa muhimu, tafsiri ya kitaalamu inayofanywa na binadamu inapendekezwa. Hatutojibu kwa kuelewa vibaya au tafsiri potofu zinazotokea kutokana na matumizi ya tafsiri hii.\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER END -->",{"name":5,"description":7},"main","f09e94ffe170f8af6d3db7c42987bbe4db227723","translations\u002Fsw\u002F.agents\u002Fskills\u002Ftesting-course-samples",26019,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners","https:\u002F\u002Faka.ms\u002Fai-agents-beginners","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-07 12:51:12",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add microsoft\u002Fai-agents-for-beginners --skill testing-course-samples",{"tool":63,"command":64},"bunx","bunx skills add microsoft\u002Fai-agents-for-beginners --skill testing-course-samples",{"tool":66,"command":67},"pnpm","pnpm dlx skills add microsoft\u002Fai-agents-for-beginners --skill testing-course-samples","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fsw\u002F.agents\u002Fskills\u002Ftesting-course-samples\u002FSKILL.md",true,[],[72,79,88,96,104,111],{"skillNo":73,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":78,"publishedAt":42},"01M69A206TRZ8KK0CW0HYJF5V5","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Ftesting-course-samples\u002FSKILL.md",[76,77],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[32,33],{"skillNo":80,"name":81,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":85,"publishedAt":42},"01M69A1XRB2SFHYRMEH0K08EKZ","microsoft-docs","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[84],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[86,9,87],"docs","microsoft docs",{"skillNo":89,"name":90,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":42},"01M69A1VPZFJQ1HNGTZQ5P3WSC","local-ai-agents","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Flocal-ai-agents\u002FSKILL.md",[],[94,95],"ai agents","local ai agents",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":42},"01M69A1S947N7MM6V9JF85S2E7","jupyter-notebook","當使用者要求建立、搭建或編輯 Jupyter 筆記本（`.ipynb`）用於實驗、探索或教學時使用；優先使用隨附範本並執行輔助腳本 `new_notebook.py` 來產生一個乾淨的起始筆記本。","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002FSKILL.md",[],[103],"jupyter notebook",{"skillNo":105,"name":106,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":42},"01M69A1Q8EXPWKZSQK69V6WF22","deploying-scalable-agents","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fdeploying-scalable-agents\u002FSKILL.md",[],[110],"deploying scalable agents",{"skillNo":112,"name":113,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":42},"01M69A1MHZTH3RH9N8VYSYG74X","azure-openai-to-responses","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fazure-openai-to-responses\u002FSKILL.md",[],[117],"azure openai to responses"]