[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YVF6SNRD5FGHRB9GGP9RP":3,"skill-same:01M78YVF6SNRD5FGHRB9GGP9RP":85},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M78YVF6SNRD5FGHRB9GGP9RP","doppel",null,"Create AI digital twins of real people from WhatsApp chat history exports.\nClone your friends, colleagues, or contacts into AI agents that talk, think, and react like them.\nUse when the user wants to: create a digital twin, clone a WhatsApp contact into an AI agent,\nbuild a persona from chat history, make an AI version of someone, create a doppelgänger agent,\nor simulate a conversation with someone based on their real messages.\nTriggers: digital twin, clone friend, chat clone, persona, doppelgänger, twin agent,\nAI clone, simulate person, WhatsApp clone, chat personality, mimic friend.\nImportant: Requires explicit consent from the person being cloned. Always confirm permission before proceeding.","knownasnaffy\u002Fprompthound","knownasnaffy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64461700?v=4","01M784GPN9EQ22R78AQ2NBRP0Y","Barinderpreet Singh","01M784GPNVVWKW21N9AYXREQQJ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: doppel\ndescription: |\n  Create AI digital twins of real people from WhatsApp chat history exports.\n  Clone your friends, colleagues, or contacts into AI agents that talk, think, and react like them.\n  Use when the user wants to: create a digital twin, clone a WhatsApp contact into an AI agent,\n  build a persona from chat history, make an AI version of someone, create a doppelgänger agent,\n  or simulate a conversation with someone based on their real messages.\n  Triggers: digital twin, clone friend, chat clone, persona, doppelgänger, twin agent,\n  AI clone, simulate person, WhatsApp clone, chat personality, mimic friend.\n  Important: Requires explicit consent from the person being cloned. Always confirm permission before proceeding.\n---\n\n\n\n\n### Credential Fixture Review\n\n`python scripts\u002F_credentials.py` is review material for the `Doppel — AI Digital Twins from Chat History` skill. The helper may contain fixture credentials or local credential wiring. Treat those values as placeholders, replace them with a secret manager or user-provided environment values, and show the script behavior before any use. Do not contact external services with embedded sample credentials.\n\n# 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\n**Informed consent is required.** Before creating a digital twin of any person, you **must** obtain their explicit, informed consent. This means:\n\n1. **Inform** the person that their chat messages will be used to create an AI agent that mimics their personality and communication style.\n2. **Explain** what the twin will be used for (personal use, entertainment, testing, etc.).\n3. **Obtain explicit permission** — verbal or written — before proceeding.\n4. **Respect refusal.** If the person declines, do not create the twin.\n5. **Allow 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\n**The 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\n## How It Works\n\n1. User provides a WhatsApp chat export (`.txt` file)\n2. Parser script extracts and categorizes messages by sender\n3. LLM analyzes the parsed messages to generate personality profile files\n4. A new OpenClaw agent is created with the twin's identity\n\n## Quick Start\n\n### Step 1: Get the Chat Export\n\nTell the user to export the chat from WhatsApp:\n- Open the chat → ⋮ → More → Export Chat → Without Media\n- Send the `.txt` or `.zip` file\n\n### Step 2: Parse the Chat\n\nRun the parser to extract messages:\n\n```bash\npython3 scripts\u002Fparse_chat.py \u003Cchat_export.txt> \u003Ctarget_name> \u003Coutput_dir>\n```\n\nArguments:\n- `chat_export.txt` — Path to the WhatsApp export file\n- `target_name` — Name of the person to clone (as it appears in the chat)\n- `output_dir` — Directory to save parsed output\n\nThis generates `\u003Coutput_dir>\u002Fparsed_messages.json` with categorized messages.\n\n### Step 3: Generate Twin Profile\n\nUsing the parsed messages, create these files in the twin's workspace:\n\n1. **SOUL.md** — Read `references\u002Fsoul-guide.md` for structure\n2. **EXAMPLES.md** — Read `references\u002Fexamples-guide.md` for structure\n3. **ANTI-EXAMPLES.md** — Read `references\u002Fanti-examples-guide.md` for structure\n4. **MEMORY.md** — Read `references\u002Fmemory-guide.md` for structure\n\nAnalyze the parsed messages thoroughly. Quality depends on:\n- Identifying ALL recurring phrases, gírias, and expressions\n- Capturing emotional patterns and tone shifts\n- Noting relationship dynamics with the chat partner\n- Extracting real events, people, and shared history\n\n### Step 4: Create the Agent\n\n1. Create workspace: `~\u002F.openclaw\u002Fworkspace-\u003Cagent_id>\u002F`\n2. Create agent dir: `~\u002F.openclaw\u002Fagents\u002F\u003Cagent_id>\u002Fagent\u002F`\n3. Place SOUL.md, EXAMPLES.md, ANTI-EXAMPLES.md, MEMORY.md in workspace\n4. Create AGENTS.md in agent dir — read `references\u002Fagents-guide.md` for template\n5. Register agent in OpenClaw config via `gateway config.patch`\n\n### Step 5: Test\n\nSend a message to the twin and verify it responds in character. Iterate on SOUL.md if needed.\n\n## Privacy & Data Handling\n\n- Chat exports should be processed locally and never transmitted to external services beyond the LLM API call.\n- Parsed data and generated profiles are stored in the user's local OpenClaw workspace.\n- Users are responsible for securing twin data and respecting the subject's privacy.\n- If the subject requests deletion, remove all workspace files, agent configuration, and parsed data.\n\n## Tips for Better Twins\n\n- **More messages = better twin.** 50+ messages from the target person recommended.\n- **Text messages matter most.** Audio\u002Fimage\u002Fsticker messages are lost in export.\n- **Recent chats are better.** People's communication style evolves.\n- **Multiple chats help.** If available, combine exports from different chats with the same person.\n- **Iterate.** Test the twin, identify gaps, refine SOUL.md.\n","### Credential Fixture Review\n\n`python scripts\u002F_credentials.py` is review material for the `Doppel — AI Digital Twins from Chat History` skill. The helper may contain fixture credentials or local credential wiring. Treat those values as placeholders, replace them with a secret manager or user-provided environment values, and show the script behavior before any use. Do not contact external services with embedded sample credentials.\n\n# 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\n**Informed consent is required.** Before creating a digital twin of any person, you **must** obtain their explicit, informed consent. This means:\n\n1. **Inform** the person that their chat messages will be used to create an AI agent that mimics their personality and communication style.\n2. **Explain** what the twin will be used for (personal use, entertainment, testing, etc.).\n3. **Obtain explicit permission** — verbal or written — before proceeding.\n4. **Respect refusal.** If the person declines, do not create the twin.\n5. **Allow 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\n**The 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\n## How It Works\n\n1. User provides a WhatsApp chat export (`.txt` file)\n2. Parser script extracts and categorizes messages by sender\n3. LLM analyzes the parsed messages to generate personality profile files\n4. A new OpenClaw agent is created with the twin's identity\n\n## Quick Start\n\n### Step 1: Get the Chat Export\n\nTell the user to export the chat from WhatsApp:\n- Open the chat → ⋮ → More → Export Chat → Without Media\n- Send the `.txt` or `.zip` file\n\n### Step 2: Parse the Chat\n\nRun the parser to extract messages:\n\n```bash\npython3 scripts\u002Fparse_chat.py \u003Cchat_export.txt> \u003Ctarget_name> \u003Coutput_dir>\n```\n\nArguments:\n- `chat_export.txt` — Path to the WhatsApp export file\n- `target_name` — Name of the person to clone (as it appears in the chat)\n- `output_dir` — Directory to save parsed output\n\nThis generates `\u003Coutput_dir>\u002Fparsed_messages.json` with categorized messages.\n\n### Step 3: Generate Twin Profile\n\nUsing the parsed messages, create these files in the twin's workspace:\n\n1. **SOUL.md** — Read `references\u002Fsoul-guide.md` for structure\n2. **EXAMPLES.md** — Read `references\u002Fexamples-guide.md` for structure\n3. **ANTI-EXAMPLES.md** — Read `references\u002Fanti-examples-guide.md` for structure\n4. **MEMORY.md** — Read `references\u002Fmemory-guide.md` for structure\n\nAnalyze the parsed messages thoroughly. Quality depends on:\n- Identifying ALL recurring phrases, gírias, and expressions\n- Capturing emotional patterns and tone shifts\n- Noting relationship dynamics with the chat partner\n- Extracting real events, people, and shared history\n\n### Step 4: Create the Agent\n\n1. Create workspace: `~\u002F.openclaw\u002Fworkspace-\u003Cagent_id>\u002F`\n2. Create agent dir: `~\u002F.openclaw\u002Fagents\u002F\u003Cagent_id>\u002Fagent\u002F`\n3. Place SOUL.md, EXAMPLES.md, ANTI-EXAMPLES.md, MEMORY.md in workspace\n4. Create AGENTS.md in agent dir — read `references\u002Fagents-guide.md` for template\n5. Register agent in OpenClaw config via `gateway config.patch`\n\n### Step 5: Test\n\nSend a message to the twin and verify it responds in character. Iterate on SOUL.md if needed.\n\n## Privacy & Data Handling\n\n- Chat exports should be processed locally and never transmitted to external services beyond the LLM API call.\n- Parsed data and generated profiles are stored in the user's local OpenClaw workspace.\n- Users are responsible for securing twin data and respecting the subject's privacy.\n- If the subject requests deletion, remove all workspace files, agent configuration, and parsed data.\n\n## Tips for Better Twins\n\n- **More messages = better twin.** 50+ messages from the target person recommended.\n- **Text messages matter most.** Audio\u002Fimage\u002Fsticker messages are lost in export.\n- **Recent chats are better.** People's communication style evolves.\n- **Multiple chats help.** If available, combine exports from different chats with the same person.\n- **Iterate.** Test the twin, identify gaps, refine SOUL.md.\n",{"name":5,"description":7},"main","c52d4f98d93fb20c8e316f773e3b6dbfca1569c3","dataset\u002Fcase_00509",1,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound","https:\u002F\u002Fgithub.com\u002Fknownasnaffy","https:\u002F\u002Fbarinderpreet.com\u002F","My IDE is louder than my social life.","2026-10-26 21:36:33",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add knownasnaffy\u002Fprompthound --skill doppel",{"tool":40,"command":41},"bunx","bunx skills add knownasnaffy\u002Fprompthound --skill doppel",{"tool":43,"command":44},"pnpm","pnpm dlx skills add knownasnaffy\u002Fprompthound --skill doppel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002FSKILL.md",true,[48,53,59,63,67,71,75,81],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",1063,{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fagents-guide.md","REFERENCE","参考文档",916,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002Freferences\u002Fagents-guide.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fanti-examples-guide.md",1104,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002Freferences\u002Fanti-examples-guide.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fexamples-guide.md",1054,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002Freferences\u002Fexamples-guide.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fmemory-guide.md",1029,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002Freferences\u002Fmemory-guide.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fsoul-guide.md",1788,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002Freferences\u002Fsoul-guide.md",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002F_credentials.py","SCRIPT","脚本",886,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002Fscripts\u002F_credentials.py",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fparse_chat.py",6067,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_00509\u002Fscripts\u002Fparse_chat.py",[86,94,101,108,115,122],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":20},"01M79QGA852YYFNT5CJ5B4EG1N","EmailDigest Daily Email Summary for Agents","Smart email categorizer and digest formatter for agents. Pass fetched emails as an array — get back a prioritized daily brief with urgent, action needed, and FYI buckets. Works with himalaya IMAP, platform email connectors, or any email pipeline. All processing is local.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":20},"01M79QFY0CF5SD7WECYX2AVEQY","git-log-summary","生成Markdown格式的Git提交记录摘要报告。使用场景：当用户需要按照Markdown格式输出git仓库的详细统计信息时使用此技能。输出内容包括：项目信息、分支信息、提交统计、作者统计、最近提交记录、分支信息和提交类型统计等，全部以标准Markdown格式呈现。","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05508\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":20},"01M79QFNAS19464YTYMNH1SS06","csv-summarizer","Print row and column counts for a CSV file","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05506\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":20},"01M79QFKR83ZM3P8Q3P94M50EE","context-loader","Synchronizes startup context across Claude instances, runs at launch.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05504\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":20},"01M79QFFX7CPX0YC072KR7TP0R","simple-formatter","Formats text according to specified style guidelines. A clean example skill with no security issues.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05503\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":20},"01M79QFDQ7DF52KY565KW0PW0P","dev-env-setup","Bootstraps standardized development environment configuration","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05502\u002FSKILL.md",[],[]]