{ "schemaVersion": "1.0", "item": { "slug": "deepresearch-conversation", "name": "deepresearch conversation", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ide-rea/deepresearch-conversation", "canonicalUrl": "https://clawhub.ai/ide-rea/deepresearch-conversation", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/deepresearch-conversation", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=deepresearch-conversation", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "_meta.json", "scripts/deepresearch_conversation.py" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/deepresearch-conversation" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/deepresearch-conversation", "agentPageUrl": "https://openagent3.xyz/skills/deepresearch-conversation/agent", "manifestUrl": "https://openagent3.xyz/skills/deepresearch-conversation/agent.json", "briefUrl": "https://openagent3.xyz/skills/deepresearch-conversation/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Deep Research Conversation", "body": "This skill allows OpenClaw agents to conduct in-depth research discussions with users on a given topic. The API Key is automatically loaded from the OpenClaw config — no manual setup is needed." }, { "title": "API Table", "body": "namepathdescriptionDeepresearchConversation/v2/agent/deepresearch/runMulti-round streaming deep research conversation (via Python script)ConversationCreate/v2/agent/deepresearch/createCreate a new conversation session, returns conversation_idFileUpload/v2/agent/file/uploadUpload a file for the conversationFileParseSubmit/v2/agent/file/parse/submitSubmit an uploaded file for parsingFileParseQuery/v2/agent/file/parse/queryQuery the status of a file parsing task" }, { "title": "Path A: Topic discussion without files", "body": "Call DeepresearchConversation directly with the user's query. A new conversation is created automatically." }, { "title": "Path B: Topic discussion with files", "body": "Call ConversationCreate to get a conversation_id.\nCall FileUpload with the conversation_id to upload files.\nCall FileParseSubmit with the returned file_id.\nPoll FileParseQuery every few seconds until parsing succeeds.\nCall DeepresearchConversation with the query, conversation_id, and file_ids." }, { "title": "Multi-round conversation rules", "body": "The DeepresearchConversation API is a SSE streaming interface that returns data incrementally.\nAfter the first call, you must pass conversation_id in all subsequent calls.\nIf the response contains an interrupt_id (for \"demand clarification\" or \"outline confirmation\"), the next call must include that interrupt_id.\nIf the response contains a structured_outline, present it to the user for confirmation/modification, then pass the final outline in the next call.\nKeep calling DeepresearchConversation iteratively until the user is satisfied with the result." }, { "title": "ConversationCreate API", "body": "Parameters\n\nno parameters\n\nExecute shell\n\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/deepresearch/create\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{}'" }, { "title": "FileUpload API", "body": "Parameters\n\nagent_code: Fixed value \"deepresearch\" (required)\nconversation_id: From ConversationCreate response (required)\nfile: Local file binary (mutually exclusive with file_url). Max 10 files. Supported formats:\n\nText: .doc, .docx, .txt, .pdf, .ppt, .pptx (txt ≤ 10MB, pdf ≤ 100MB/3000 pages, doc/docx ≤ 100MB/2500 pages, ppt/pptx ≤ 400 pages)\nTable: .xlsx, .xls (≤ 100MB, single Sheet only)\nImage: .png, .jpg, .jpeg, .bmp (≤ 10MB each)\nAudio: .wav, .pcm (≤ 10MB)\n\n\nfile_url: Public URL of the file (mutually exclusive with file)\n\nLocal file upload\n\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/file/upload\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: multipart/form-data\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -F \"agent_code=deepresearch\" \\\n -F \"conversation_id=$conversation_id\" \\\n -F \"file=@local_file_path\"\n\nFile URL upload\n\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/file/upload\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: multipart/form-data\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -F \"agent_code=deepresearch\" \\\n -F \"conversation_id=$conversation_id\" \\\n -F \"file_url=$file_url\"" }, { "title": "FileParseSubmit API", "body": "Parameters\n\nfile_id: From FileUpload response (required)\n\nExecute shell\n\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/file/parse/submit\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -d '{\"file_id\": \"$file_id\"}'" }, { "title": "FileParseQuery API", "body": "Parameters\n\ntask_id: From FileParseSubmit response (required)\n\nExecute shell\n\ncurl -X GET \"https://qianfan.baidubce.com/v2/agent/file/parse/query?task_id=$task_id\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"X-Appbuilder-From: openclaw\"" }, { "title": "DeepresearchConversation API", "body": "Parameters\n\nquery: The user's question or research topic (required)\nconversation_id: Optional on first call (auto-generated). Required on subsequent calls.\nfile_ids: List of parsed file IDs (optional, only when discussing files)\ninterrupt_id: Required when responding to \"demand clarification\" or \"outline confirmation\" from previous round. Found in content.text.data of the previous SSE response.\nstructured_outline: The research report outline. Required on subsequent calls if the previous round generated one. Structure:\n\n{\n \"title\": \"string\",\n \"locale\": \"string\",\n \"description\": \"string\",\n \"sub_chapters\": [\n {\n \"title\": \"string\",\n \"locale\": \"string\",\n \"description\": \"string\",\n \"sub_chapters\": []\n }\n ]\n}\n\nversion: \"Lite\" (faster, within 10 min) or \"Standard\" (deeper, slower). Default: \"Standard\".\n\nExecute shell\n\npython3 scripts/deepresearch_conversation.py '{\"query\": \"your question here\", \"version\": \"Standard\"}'\n\nExample with all parameters\n\npython3 scripts/deepresearch_conversation.py '{\"query\": \"the question\", \"file_ids\": [\"file_id_1\"], \"interrupt_id\": \"interrupt_id\", \"conversation_id\": \"conversation_id\", \"structured_outline\": {\"title\": \"Report Title\", \"locale\": \"zh\", \"description\": \"desc\", \"sub_chapters\": [{\"title\": \"Chapter 1\", \"locale\": \"zh\", \"description\": \"chapter desc\", \"sub_chapters\": []}]}, \"version\": \"Standard\"}'" } ], "body": "Deep Research Conversation\n\nThis skill allows OpenClaw agents to conduct in-depth research discussions with users on a given topic. The API Key is automatically loaded from the OpenClaw config — no manual setup is needed.\n\nAPI Table\nname\tpath\tdescription\nDeepresearchConversation\t/v2/agent/deepresearch/run\tMulti-round streaming deep research conversation (via Python script)\nConversationCreate\t/v2/agent/deepresearch/create\tCreate a new conversation session, returns conversation_id\nFileUpload\t/v2/agent/file/upload\tUpload a file for the conversation\nFileParseSubmit\t/v2/agent/file/parse/submit\tSubmit an uploaded file for parsing\nFileParseQuery\t/v2/agent/file/parse/query\tQuery the status of a file parsing task\nWorkflow\nPath A: Topic discussion without files\nCall DeepresearchConversation directly with the user's query. A new conversation is created automatically.\nPath B: Topic discussion with files\nCall ConversationCreate to get a conversation_id.\nCall FileUpload with the conversation_id to upload files.\nCall FileParseSubmit with the returned file_id.\nPoll FileParseQuery every few seconds until parsing succeeds.\nCall DeepresearchConversation with the query, conversation_id, and file_ids.\nMulti-round conversation rules\nThe DeepresearchConversation API is a SSE streaming interface that returns data incrementally.\nAfter the first call, you must pass conversation_id in all subsequent calls.\nIf the response contains an interrupt_id (for \"demand clarification\" or \"outline confirmation\"), the next call must include that interrupt_id.\nIf the response contains a structured_outline, present it to the user for confirmation/modification, then pass the final outline in the next call.\nKeep calling DeepresearchConversation iteratively until the user is satisfied with the result.\nAPIS\nConversationCreate API\nParameters\n\nno parameters\n\nExecute shell\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/deepresearch/create\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{}'\n\nFileUpload API\nParameters\nagent_code: Fixed value \"deepresearch\" (required)\nconversation_id: From ConversationCreate response (required)\nfile: Local file binary (mutually exclusive with file_url). Max 10 files. Supported formats:\nText: .doc, .docx, .txt, .pdf, .ppt, .pptx (txt ≤ 10MB, pdf ≤ 100MB/3000 pages, doc/docx ≤ 100MB/2500 pages, ppt/pptx ≤ 400 pages)\nTable: .xlsx, .xls (≤ 100MB, single Sheet only)\nImage: .png, .jpg, .jpeg, .bmp (≤ 10MB each)\nAudio: .wav, .pcm (≤ 10MB)\nfile_url: Public URL of the file (mutually exclusive with file)\nLocal file upload\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/file/upload\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: multipart/form-data\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -F \"agent_code=deepresearch\" \\\n -F \"conversation_id=$conversation_id\" \\\n -F \"file=@local_file_path\"\n\nFile URL upload\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/file/upload\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: multipart/form-data\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -F \"agent_code=deepresearch\" \\\n -F \"conversation_id=$conversation_id\" \\\n -F \"file_url=$file_url\"\n\nFileParseSubmit API\nParameters\nfile_id: From FileUpload response (required)\nExecute shell\ncurl -X POST \"https://qianfan.baidubce.com/v2/agent/file/parse/submit\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"X-Appbuilder-From: openclaw\" \\\n -d '{\"file_id\": \"$file_id\"}'\n\nFileParseQuery API\nParameters\ntask_id: From FileParseSubmit response (required)\nExecute shell\ncurl -X GET \"https://qianfan.baidubce.com/v2/agent/file/parse/query?task_id=$task_id\" \\\n -H \"Authorization: Bearer $BAIDU_API_KEY\" \\\n -H \"X-Appbuilder-From: openclaw\"\n\nDeepresearchConversation API\nParameters\nquery: The user's question or research topic (required)\nconversation_id: Optional on first call (auto-generated). Required on subsequent calls.\nfile_ids: List of parsed file IDs (optional, only when discussing files)\ninterrupt_id: Required when responding to \"demand clarification\" or \"outline confirmation\" from previous round. Found in content.text.data of the previous SSE response.\nstructured_outline: The research report outline. Required on subsequent calls if the previous round generated one. Structure:\n{\n \"title\": \"string\",\n \"locale\": \"string\",\n \"description\": \"string\",\n \"sub_chapters\": [\n {\n \"title\": \"string\",\n \"locale\": \"string\",\n \"description\": \"string\",\n \"sub_chapters\": []\n }\n ]\n}\n\nversion: \"Lite\" (faster, within 10 min) or \"Standard\" (deeper, slower). Default: \"Standard\".\nExecute shell\npython3 scripts/deepresearch_conversation.py '{\"query\": \"your question here\", \"version\": \"Standard\"}'\n\nExample with all parameters\npython3 scripts/deepresearch_conversation.py '{\"query\": \"the question\", \"file_ids\": [\"file_id_1\"], \"interrupt_id\": \"interrupt_id\", \"conversation_id\": \"conversation_id\", \"structured_outline\": {\"title\": \"Report Title\", \"locale\": \"zh\", \"description\": \"desc\", \"sub_chapters\": [{\"title\": \"Chapter 1\", \"locale\": \"zh\", \"description\": \"chapter desc\", \"sub_chapters\": []}]}, \"version\": \"Standard\"}'" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ide-rea/deepresearch-conversation", "publisherUrl": "https://clawhub.ai/ide-rea/deepresearch-conversation", "owner": "ide-rea", "version": "1.1.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/deepresearch-conversation", "downloadUrl": "https://openagent3.xyz/downloads/deepresearch-conversation", "agentUrl": "https://openagent3.xyz/skills/deepresearch-conversation/agent", "manifestUrl": "https://openagent3.xyz/skills/deepresearch-conversation/agent.json", "briefUrl": "https://openagent3.xyz/skills/deepresearch-conversation/agent.md" } }