{ "schemaVersion": "1.0", "item": { "slug": "twinify", "name": "Twinify", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/neobotjan2026/twinify", "canonicalUrl": "https://clawhub.ai/neobotjan2026/twinify", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/twinify", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=twinify", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "LICENSE.txt", "SKILL.md", "references/agents-guide.md", "references/anti-examples-guide.md", "references/examples-guide.md", "references/memory-guide.md" ], "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/twinify" }, "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/twinify", "agentPageUrl": "https://openagent3.xyz/skills/twinify/agent", "manifestUrl": "https://openagent3.xyz/skills/twinify/agent.json", "briefUrl": "https://openagent3.xyz/skills/twinify/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": "Doppel — AI Digital Twins from Chat History", "body": "Create realistic AI digital twins of real people by analyzing their WhatsApp chat exports." }, { "title": "⚠️ Ethics & Consent", "body": "Informed consent is required. Before creating a digital twin of any person, you must obtain their explicit, informed consent. This means:\n\nInform the person that their chat messages will be used to create an AI agent that mimics their personality and communication style.\nExplain what the twin will be used for (personal use, entertainment, testing, etc.).\nObtain explicit permission — verbal or written — before proceeding.\nRespect refusal. If the person declines, do not create the twin.\nAllow withdrawal. The person may request deletion of the twin at any time.\n\nCreating a digital twin without the subject's knowledge or consent is a violation of their privacy and autonomy. This skill is designed for use between friends, family, or colleagues who have mutually agreed to participate. It is not intended for impersonation, deception, harassment, or any use that could harm the subject.\n\nThe agent must confirm consent before proceeding. When a user requests a twin, ask: \"Do you have this person's permission to create an AI twin of them?\" Do not proceed unless the user confirms." }, { "title": "How It Works", "body": "User provides a WhatsApp chat export (.txt file)\nParser script extracts and categorizes messages by sender\nLLM analyzes the parsed messages to generate personality profile files\nA new OpenClaw agent is created with the twin's identity" }, { "title": "Step 1: Get the Chat Export", "body": "Tell the user to export the chat from WhatsApp:\n\nOpen the chat → ⋮ → More → Export Chat → Without Media\nSend the .txt or .zip file" }, { "title": "Step 2: Parse the Chat", "body": "Run the parser to extract messages:\n\npython3 scripts/parse_chat.py \n\nArguments:\n\nchat_export.txt — Path to the WhatsApp export file\ntarget_name — Name of the person to clone (as it appears in the chat)\noutput_dir — Directory to save parsed output\n\nThis generates /parsed_messages.json with categorized messages." }, { "title": "Step 3: Generate Twin Profile", "body": "Using the parsed messages, create these files in the twin's workspace:\n\nSOUL.md — Read references/soul-guide.md for structure\nEXAMPLES.md — Read references/examples-guide.md for structure\nANTI-EXAMPLES.md — Read references/anti-examples-guide.md for structure\nMEMORY.md — Read references/memory-guide.md for structure\n\nAnalyze the parsed messages thoroughly. Quality depends on:\n\nIdentifying ALL recurring phrases, gírias, and expressions\nCapturing emotional patterns and tone shifts\nNoting relationship dynamics with the chat partner\nExtracting real events, people, and shared history" }, { "title": "Step 4: Create the Agent", "body": "Create workspace: ~/.openclaw/workspace-/\nCreate agent dir: ~/.openclaw/agents//agent/\nPlace SOUL.md, EXAMPLES.md, ANTI-EXAMPLES.md, MEMORY.md in workspace\nCreate AGENTS.md in agent dir — read references/agents-guide.md for template\nRegister agent in OpenClaw config via gateway config.patch" }, { "title": "Step 5: Test", "body": "Send a message to the twin and verify it responds in character. Iterate on SOUL.md if needed." }, { "title": "Privacy & Data Handling", "body": "Chat exports should be processed locally and never transmitted to external services beyond the LLM API call.\nParsed data and generated profiles are stored in the user's local OpenClaw workspace.\nUsers are responsible for securing twin data and respecting the subject's privacy.\nIf the subject requests deletion, remove all workspace files, agent configuration, and parsed data." }, { "title": "Tips for Better Twins", "body": "More messages = better twin. 50+ messages from the target person recommended.\nText messages matter most. Audio/image/sticker messages are lost in export.\nRecent chats are better. People's communication style evolves.\nMultiple chats help. If available, combine exports from different chats with the same person.\nIterate. Test the twin, identify gaps, refine SOUL.md." } ], "body": "Doppel — AI Digital Twins from Chat History\n\nCreate realistic AI digital twins of real people by analyzing their WhatsApp chat exports.\n\n⚠️ Ethics & Consent\n\nInformed consent is required. Before creating a digital twin of any person, you must obtain their explicit, informed consent. This means:\n\nInform the person that their chat messages will be used to create an AI agent that mimics their personality and communication style.\nExplain what the twin will be used for (personal use, entertainment, testing, etc.).\nObtain explicit permission — verbal or written — before proceeding.\nRespect refusal. If the person declines, do not create the twin.\nAllow withdrawal. The person may request deletion of the twin at any time.\n\nCreating a digital twin without the subject's knowledge or consent is a violation of their privacy and autonomy. This skill is designed for use between friends, family, or colleagues who have mutually agreed to participate. It is not intended for impersonation, deception, harassment, or any use that could harm the subject.\n\nThe agent must confirm consent before proceeding. When a user requests a twin, ask: \"Do you have this person's permission to create an AI twin of them?\" Do not proceed unless the user confirms.\n\nHow It Works\nUser provides a WhatsApp chat export (.txt file)\nParser script extracts and categorizes messages by sender\nLLM analyzes the parsed messages to generate personality profile files\nA new OpenClaw agent is created with the twin's identity\nQuick Start\nStep 1: Get the Chat Export\n\nTell the user to export the chat from WhatsApp:\n\nOpen the chat → ⋮ → More → Export Chat → Without Media\nSend the .txt or .zip file\nStep 2: Parse the Chat\n\nRun the parser to extract messages:\n\npython3 scripts/parse_chat.py \n\n\nArguments:\n\nchat_export.txt — Path to the WhatsApp export file\ntarget_name — Name of the person to clone (as it appears in the chat)\noutput_dir — Directory to save parsed output\n\nThis generates /parsed_messages.json with categorized messages.\n\nStep 3: Generate Twin Profile\n\nUsing the parsed messages, create these files in the twin's workspace:\n\nSOUL.md — Read references/soul-guide.md for structure\nEXAMPLES.md — Read references/examples-guide.md for structure\nANTI-EXAMPLES.md — Read references/anti-examples-guide.md for structure\nMEMORY.md — Read references/memory-guide.md for structure\n\nAnalyze the parsed messages thoroughly. Quality depends on:\n\nIdentifying ALL recurring phrases, gírias, and expressions\nCapturing emotional patterns and tone shifts\nNoting relationship dynamics with the chat partner\nExtracting real events, people, and shared history\nStep 4: Create the Agent\nCreate workspace: ~/.openclaw/workspace-/\nCreate agent dir: ~/.openclaw/agents//agent/\nPlace SOUL.md, EXAMPLES.md, ANTI-EXAMPLES.md, MEMORY.md in workspace\nCreate AGENTS.md in agent dir — read references/agents-guide.md for template\nRegister agent in OpenClaw config via gateway config.patch\nStep 5: Test\n\nSend a message to the twin and verify it responds in character. Iterate on SOUL.md if needed.\n\nPrivacy & Data Handling\nChat exports should be processed locally and never transmitted to external services beyond the LLM API call.\nParsed data and generated profiles are stored in the user's local OpenClaw workspace.\nUsers are responsible for securing twin data and respecting the subject's privacy.\nIf the subject requests deletion, remove all workspace files, agent configuration, and parsed data.\nTips for Better Twins\nMore messages = better twin. 50+ messages from the target person recommended.\nText messages matter most. Audio/image/sticker messages are lost in export.\nRecent chats are better. People's communication style evolves.\nMultiple chats help. If available, combine exports from different chats with the same person.\nIterate. Test the twin, identify gaps, refine SOUL.md." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/neobotjan2026/twinify", "publisherUrl": "https://clawhub.ai/neobotjan2026/twinify", "owner": "neobotjan2026", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/twinify", "downloadUrl": "https://openagent3.xyz/downloads/twinify", "agentUrl": "https://openagent3.xyz/skills/twinify/agent", "manifestUrl": "https://openagent3.xyz/skills/twinify/agent.json", "briefUrl": "https://openagent3.xyz/skills/twinify/agent.md" } }