[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMH1K1PFNAAFFSWNN4QSBX":3,"skill-same:01M7EMH1K1PFNAAFFSWNN4QSBX":47},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7EMH1K1PFNAAFFSWNN4QSBX","chatbot-marketer",null,"Use conversational marketing — chatbot strategy, conversation design, lead qualification bots, and messaging ROI.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-chatbot-marketer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: chatbot-marketer\ndescription: Use conversational marketing — chatbot strategy, conversation design, lead qualification bots, and messaging ROI.\ncategory: business-marketing\n---\n\n## Overview\n\nChatbots and conversational marketing meet buyers in real-time conversations: answering questions, qualifying leads, booking meetings, and guiding purchases — 24\u002F7. This skill covers chatbot strategy, conversation design, lead qualification flows, and measuring conversational ROI.\n\nThe principle: be helpful first, capture second. Bots that interrogate before helping get closed.\n\n\nChatbots and conversational AI compress the funnel: instead of forms and landing pages, prospects get answers and take action inside a conversation. The best implementations feel like talking to a knowledgeable rep, not navigating a phone tree. Design for resolution and conversion, not for showcasing AI capabilities.\n## When to use\n\n- Adding chat to a website for lead generation\n- Designing chatbot conversation flows\n- Qualifying leads conversationally\n- Reducing support load with bots\n- Building Messenger\u002FWhatsApp marketing\n- Measuring chatbot performance\n\n- Qualifying website visitors outside business hours\n- Deflecting repetitive support questions\n- Guiding users through complex product selection\n- Capturing leads from high-traffic blog content\n- Running conversational quizzes for product matching\n- Providing instant answers in paid landing pages\n## Core concepts\n\n**Use-case clarity.** Define the bot's jobs: lead qualification, meeting booking, FAQ deflection, product guidance, or order support. One bot doing five jobs does none well. Start with the highest-volume, highest-value use case.\n\n**Conversation design.** Write like a helpful human, not a form: one question at a time, short messages (under 40 words), quick-reply buttons for common answers, graceful handling of unexpected input, and always a path to a human. Test flows with real users — designers can't predict confusion.\n\n**Qualification flows.** Conversational BANT: need (\"what are you trying to solve?\"), fit (company size, role), timeline, and contact handoff. Progressive: earn information by giving value first. Route hot leads to humans immediately — don't make them finish the flow.\n\n**Playbooks by page.** Different pages, different intents: pricing page (offer help comparing plans), blog (offer related resources), high-intent pages (proactive outreach after 30–60 seconds). Match the playbook to visitor intent.\n\n**Human handoff.** The moment of truth: pass full conversation context, set expectations (\"connecting you with Maya, our specialist — typical wait 2 minutes\"), and never make users repeat themselves. Failed handoffs destroy trust faster than no bot at all.\n\n**Messaging channels.** Website chat, Messenger, WhatsApp, Instagram DMs — meet customers where they are. Each channel has norms (WhatsApp = personal, keep it concise) and rules (opt-in requirements, template restrictions for business messaging).\n\n\n**Conversation design principles.** One question at a time; offer quick-reply buttons instead of open text where possible; always provide an escape to a human; confirm understanding before acting (\"Just to confirm, you want...\"); handle the unhappy path (confusion, profanity, edge cases) as carefully as the happy path. Test with real users — designers cannot predict how people actually type.\n\n**Handoff design.** The bot-to-human transition is where most implementations fail: pass full conversation context (never make the user repeat themselves), set expectations (\"Connecting you with Maya from support, ~2 min wait\"), and route by intent and language. A graceful handoff beats a clever bot.\n\n**Lead qualification flows.** BANT or CHAMP adapted for chat: 4–6 questions max, quick replies over free text, progressive disclosure (ask the next question only when the previous is answered).\nChat-qualified leads convert 2–3x better than form leads because the conversation builds micro-commitment.\nAlways offer \"talk to a human\" — forcing bot completion loses hot leads.\n**Proactive triggers.** Time-on-page, scroll depth, exit intent, and return-visitor detection trigger contextual invitations (\"Questions about pricing? I can help.\").\nTrigger too early and you annoy; too late and they are gone. Test trigger timing per page type — pricing pages warrant faster triggers than blog posts.\n## Practical workflow\n\n1. **Pick the use case.** Analyze: where do visitors drop? What questions repeat? Start with one high-impact flow (e.g., pricing-page qualification).\n2. **Design conversations.** Map the happy path + top 3 detours per flow. Write in natural language. Add quick replies, fallback responses, and human-escalation triggers (frustration signals, complex questions, high-value visitors).\n3. **Build playbooks.** Per key page: trigger conditions, opening message, qualification questions, routing rules, and follow-up for missed chats. Keep opening messages helpful, not pushy.\n4. **Integrate.** Connect to CRM (log conversations, create\u002Fupdate records), calendar (meeting booking), marketing automation (nurture for not-ready leads), and alerting (hot lead → instant Slack\u002Femail to owner).\n5. **Launch and monitor.** Soft-launch on high-traffic pages. Watch: engagement rate, completion rate, qualification rate, handoff success, CSAT. Read actual transcripts weekly — they reveal confusion and opportunities.\n6. **Optimize.** A\u002FB test opening messages and CTAs. Expand to new use cases once the first works. Prune flows with low completion. Update answers as products change.\n\n**Transcript review checklist:** where do users drop? What unexpected inputs recur? Do handoffs include context? Is the tone right for frustrated users? Are quick replies covering 80% of responses?\n\n\n**Use-case prioritization:** list candidate conversations → score by volume (how often does this happen?) × value (conversion or deflection impact) × feasibility (can the bot resolve it reliably?) → build top 3 first. Start with high-volume, low-complexity wins (hours, pricing, order status) before attempting complex sales conversations.\n\n**Analytics that matter:** containment rate (% resolved without human) → CSAT for bot conversations → conversion rate vs. control → fallback rate (how often the bot fails) → top failed intents (your build backlog). Review failed conversations weekly — they are the roadmap.\n\n**Build checklist:** define the single goal per bot (qualify, book, support — not all three) → script the happy path → script the 5 most common detours → add human handoff → test with 10 real users → soft launch on one page → review transcripts weekly → expand.\nTranscript review is the ongoing work — user language evolves and flows decay without it.\n## Common pitfalls\n\n- **Interrogation before value.** Asking for email in the first message. Give help first, earn the contact.\n- **No human escape.** Trapping users in bot loops. Always offer a human, especially after two failed attempts.\n- **Over-automation.** Bots handling situations needing empathy (complaints, complex issues). Know the bot's limits.\n- **Generic playbooks.** Same popup on every page. Match to page intent.\n- **Ignoring transcripts.** Never reading what users actually say. Weekly transcript review is the optimization engine.\n- **Slow human response.** Bot promises help; humans take hours. Staff the handoff or don't offer it.\n- **Compliance blindness.** Messaging regulations (opt-ins, quiet hours, template approvals on WhatsApp) vary by channel and region. Know the rules.\n- **Pretending to be human.** Deceptive bots destroy trust when discovered. Identify as automated upfront; users do not mind bots, they mind being tricked.\n- **No human fallback.** Trapping frustrated users in bot loops. Always offer a human exit, prominently.\n- **Launching without training data.** Bots trained on imagined conversations fail on real ones. Seed with actual chat transcripts and support tickets.\n- **Too many questions.** 15-field interrogations in chat form. Every question costs completion — ask only what changes the outcome.\n- **Dead-end conversations.** Flows that end without a next step. Every conversation ends with value delivered or a clear handoff.\n","## Overview\n\nChatbots and conversational marketing meet buyers in real-time conversations: answering questions, qualifying leads, booking meetings, and guiding purchases — 24\u002F7. This skill covers chatbot strategy, conversation design, lead qualification flows, and measuring conversational ROI.\n\nThe principle: be helpful first, capture second. Bots that interrogate before helping get closed.\n\n\nChatbots and conversational AI compress the funnel: instead of forms and landing pages, prospects get answers and take action inside a conversation. The best implementations feel like talking to a knowledgeable rep, not navigating a phone tree. Design for resolution and conversion, not for showcasing AI capabilities.\n## When to use\n\n- Adding chat to a website for lead generation\n- Designing chatbot conversation flows\n- Qualifying leads conversationally\n- Reducing support load with bots\n- Building Messenger\u002FWhatsApp marketing\n- Measuring chatbot performance\n\n- Qualifying website visitors outside business hours\n- Deflecting repetitive support questions\n- Guiding users through complex product selection\n- Capturing leads from high-traffic blog content\n- Running conversational quizzes for product matching\n- Providing instant answers in paid landing pages\n## Core concepts\n\n**Use-case clarity.** Define the bot's jobs: lead qualification, meeting booking, FAQ deflection, product guidance, or order support. One bot doing five jobs does none well. Start with the highest-volume, highest-value use case.\n\n**Conversation design.** Write like a helpful human, not a form: one question at a time, short messages (under 40 words), quick-reply buttons for common answers, graceful handling of unexpected input, and always a path to a human. Test flows with real users — designers can't predict confusion.\n\n**Qualification flows.** Conversational BANT: need (\"what are you trying to solve?\"), fit (company size, role), timeline, and contact handoff. Progressive: earn information by giving value first. Route hot leads to humans immediately — don't make them finish the flow.\n\n**Playbooks by page.** Different pages, different intents: pricing page (offer help comparing plans), blog (offer related resources), high-intent pages (proactive outreach after 30–60 seconds). Match the playbook to visitor intent.\n\n**Human handoff.** The moment of truth: pass full conversation context, set expectations (\"connecting you with Maya, our specialist — typical wait 2 minutes\"), and never make users repeat themselves. Failed handoffs destroy trust faster than no bot at all.\n\n**Messaging channels.** Website chat, Messenger, WhatsApp, Instagram DMs — meet customers where they are. Each channel has norms (WhatsApp = personal, keep it concise) and rules (opt-in requirements, template restrictions for business messaging).\n\n\n**Conversation design principles.** One question at a time; offer quick-reply buttons instead of open text where possible; always provide an escape to a human; confirm understanding before acting (\"Just to confirm, you want...\"); handle the unhappy path (confusion, profanity, edge cases) as carefully as the happy path. Test with real users — designers cannot predict how people actually type.\n\n**Handoff design.** The bot-to-human transition is where most implementations fail: pass full conversation context (never make the user repeat themselves), set expectations (\"Connecting you with Maya from support, ~2 min wait\"), and route by intent and language. A graceful handoff beats a clever bot.\n\n**Lead qualification flows.** BANT or CHAMP adapted for chat: 4–6 questions max, quick replies over free text, progressive disclosure (ask the next question only when the previous is answered).\nChat-qualified leads convert 2–3x better than form leads because the conversation builds micro-commitment.\nAlways offer \"talk to a human\" — forcing bot completion loses hot leads.\n**Proactive triggers.** Time-on-page, scroll depth, exit intent, and return-visitor detection trigger contextual invitations (\"Questions about pricing? I can help.\").\nTrigger too early and you annoy; too late and they are gone. Test trigger timing per page type — pricing pages warrant faster triggers than blog posts.\n## Practical workflow\n\n1. **Pick the use case.** Analyze: where do visitors drop? What questions repeat? Start with one high-impact flow (e.g., pricing-page qualification).\n2. **Design conversations.** Map the happy path + top 3 detours per flow. Write in natural language. Add quick replies, fallback responses, and human-escalation triggers (frustration signals, complex questions, high-value visitors).\n3. **Build playbooks.** Per key page: trigger conditions, opening message, qualification questions, routing rules, and follow-up for missed chats. Keep opening messages helpful, not pushy.\n4. **Integrate.** Connect to CRM (log conversations, create\u002Fupdate records), calendar (meeting booking), marketing automation (nurture for not-ready leads), and alerting (hot lead → instant Slack\u002Femail to owner).\n5. **Launch and monitor.** Soft-launch on high-traffic pages. Watch: engagement rate, completion rate, qualification rate, handoff success, CSAT. Read actual transcripts weekly — they reveal confusion and opportunities.\n6. **Optimize.** A\u002FB test opening messages and CTAs. Expand to new use cases once the first works. Prune flows with low completion. Update answers as products change.\n\n**Transcript review checklist:** where do users drop? What unexpected inputs recur? Do handoffs include context? Is the tone right for frustrated users? Are quick replies covering 80% of responses?\n\n\n**Use-case prioritization:** list candidate conversations → score by volume (how often does this happen?) × value (conversion or deflection impact) × feasibility (can the bot resolve it reliably?) → build top 3 first. Start with high-volume, low-complexity wins (hours, pricing, order status) before attempting complex sales conversations.\n\n**Analytics that matter:** containment rate (% resolved without human) → CSAT for bot conversations → conversion rate vs. control → fallback rate (how often the bot fails) → top failed intents (your build backlog). Review failed conversations weekly — they are the roadmap.\n\n**Build checklist:** define the single goal per bot (qualify, book, support — not all three) → script the happy path → script the 5 most common detours → add human handoff → test with 10 real users → soft launch on one page → review transcripts weekly → expand.\nTranscript review is the ongoing work — user language evolves and flows decay without it.\n## Common pitfalls\n\n- **Interrogation before value.** Asking for email in the first message. Give help first, earn the contact.\n- **No human escape.** Trapping users in bot loops. Always offer a human, especially after two failed attempts.\n- **Over-automation.** Bots handling situations needing empathy (complaints, complex issues). Know the bot's limits.\n- **Generic playbooks.** Same popup on every page. Match to page intent.\n- **Ignoring transcripts.** Never reading what users actually say. Weekly transcript review is the optimization engine.\n- **Slow human response.** Bot promises help; humans take hours. Staff the handoff or don't offer it.\n- **Compliance blindness.** Messaging regulations (opt-ins, quiet hours, template approvals on WhatsApp) vary by channel and region. Know the rules.\n- **Pretending to be human.** Deceptive bots destroy trust when discovered. Identify as automated upfront; users do not mind bots, they mind being tricked.\n- **No human fallback.** Trapping frustrated users in bot loops. Always offer a human exit, prominently.\n- **Launching without training data.** Bots trained on imagined conversations fail on real ones. Seed with actual chat transcripts and support tickets.\n- **Too many questions.** 15-field interrogations in chat form. Every question costs completion — ask only what changes the outcome.\n- **Dead-end conversations.** Flows that end without a next step. Every conversation ends with value delivered or a clear handoff.\n",{"name":5,"category":24,"description":7},"business-marketing","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-chatbot-marketer",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill chatbot-marketer",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill chatbot-marketer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill chatbot-marketer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-chatbot-marketer\u002FSKILL.md",true,[],[48,55,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"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":76,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]