[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMQDS73DM6GJ3BPB2KG76V":3,"skill-same:01M7EMQDS73DM6GJ3BPB2KG76V":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},"01M7EMQDS73DM6GJ3BPB2KG76V","customer-support-playbook",null,"Build SaaS customer support — tiered support models, SLAs, macros, escalation, and support-driven product feedback.","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-customer-support-playbook\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: customer-support-playbook\ndescription: Build SaaS customer support — tiered support models, SLAs, macros, escalation, and support-driven product feedback.\ncategory: curviate\n---\n\n## Overview\n\nSaaS customer support is a retention engine: fast, effective help keeps customers renewing, and support interactions surface product insights. This skill covers building support operations — tiered models, SLAs, knowledge bases, macros, escalation paths, and the feedback loops that turn tickets into product improvements. Platform-neutral.\n\n\nCustomer support operations turn problems into loyalty: great support recovers trust, generates product insight, and differentiates commodities.\nThis skill covers the operational playbook — channel strategy, ticket workflows, macros, QA, metrics, and team design — for support organizations from startup to scale.\n## When to use\n\n- Building a support team or function\n- Defining support tiers and SLAs\n- Reducing response and resolution times\n- Creating escalation processes\n- Turning support feedback into product input\n- Scaling support efficiently\n\n- Building a support team from scratch\n- Reducing ticket backlog and response times\n- Designing support QA and coaching programs\n- Choosing support channels and tooling\n- Turning support insights into product improvements\n## Core concepts\n\n**Tiered support.** L1 (triage, common issues, macros), L2 (technical troubleshooting, account-specific), L3 (engineering escalation, bugs). Clear tier criteria and escalation paths prevent both premature escalation and L1 heroics on engineering problems.\n\n**SLAs.** Response time (first reply) and resolution time targets by priority (P1 critical → P4 question) and plan tier (enterprise gets faster). Publish SLAs honestly — missed SLAs damage trust more than slower honest ones. Measure compliance weekly.\n\n**Knowledge base.** Self-service deflects 30–60% of tickets: task-based articles, troubleshooting guides, video walkthroughs for complex flows, and in-app help links. Maintain ruthlessly — stale articles mislead. Every resolved ticket is a candidate article.\n\n**Macros and templates.** Canned responses for common scenarios with personalization tokens and human-touch room. Review quarterly. Macros speed responses but must never feel robotic — train agents to adapt, not paste.\n\n**Escalation.** Criteria per tier jump, warm handoffs (context transfers — customers never repeat themselves), engineering escalation process (with severity and SLA), and executive escalation for key accounts. Escalation is a designed path, not an admission of failure.\n\n**Support-to-product feedback.** Tag tickets by theme, quantify (how many customers hit this?), and feed prioritized insights to product regularly. Support sees product reality first — the best feature ideas and bug reports live in tickets.\n\n\n**Channel strategy.** Email (async, detailed), chat (real-time, high volume), phone (urgent, complex, high-touch), self-service (deflection), social (public, reputation-sensitive).\nMatch channels to issue types: billing disputes deserve humans; password resets deserve self-service.\nStaff channels by demand patterns — chat peaks differ from email peaks.\n**Ticket triage.** Urgent (system down, data loss) → high (core feature broken) → normal (how-to, minor bugs) → low (feature requests).\nSLAs per priority, publicly committed where appropriate.\nTriage within 1 hour for urgent, 4 for high — speed of acknowledgment matters as much as speed of resolution.\n**Macros and saved replies.** For the top 20 recurring issues: empathetic, accurate, personalized-able templates.\nMacros save time but must not sound robotic — leave placeholders for personalization and empower agents to adapt.\nReview macro usage monthly; heavily-edited macros need rewriting.\n**QA and coaching.** Score tickets on: correctness, tone, completeness, and efficiency.\nSample 5–10 tickets per agent monthly; coach to patterns, not incidents.\nCalibrate scores across reviewers quarterly — inconsistent QA is worse than none.\n## Practical workflow\n\n1. **Define the model.** Tiers, SLAs by priority and plan, channels (chat, email, phone — match to customer expectations), hours\u002Fcoverage, and languages.\n2. **Build foundations.** Help center (top 20 ticket drivers first), macro library, internal runbooks, escalation paths, and tooling (ticketing, chat, phone, screen-share).\n3. **Staff and train.** Hire for empathy + technical aptitude, train on product deeply (support must know the product cold), soft skills (de-escalation, clear writing), and empower with authority (refunds, credits within limits — don't make agents beg for permission).\n4. **Launch with SLAs.** Publish targets, staff to meet them (queue math: volume × handle time ÷ availability), and monitor real-time dashboards.\n5. **Optimize.** Weekly: SLA compliance, CSAT, first-contact resolution, handle times, escalation rates. Monthly: ticket theme analysis → product feedback report. Quarterly: macro\u002Farticle audits, training refreshers.\n6. **Scale smartly.** Self-service investment (deflection), automation (triage bots, suggested macros), tier-0 (community, in-app guidance), and hiring ahead of growth curves.\n\n**Ticket theme report template:** top 10 themes by volume → trend (rising\u002Ffalling) → customer impact quotes → product recommendation → owner → status. Monthly to product leadership.\n\n\n**Support metrics dashboard:** first response time → resolution time → CSAT → first-contact resolution rate → backlog age → ticket volume by category → agent utilization.\nReview weekly; investigate any metric moving 10%+ before it becomes a crisis.\n**Escalation paths:** L1 (generalists, macros, known issues) → L2 (technical specialists) → L3 (engineering) → incident commander (outages).\nDefine handoff criteria explicitly; tickets bouncing between tiers destroy CSAT.\n**Voice-of-customer loop:** tag tickets by theme → monthly report to product (top 10 themes with volume and quotes) → track which themes get addressed → close the loop with customers when fixes ship.\nSupport is the cheapest user research you already pay for — mine it.\n## Common pitfalls\n\n- **No SLAs.** \"We'll get to it.\" Define and publish response targets.\n- **Stale knowledge base.** Articles from three versions ago. Assign owners; review quarterly.\n- **Cold escalations.** Customers repeating their story at each tier. Warm handoffs with full context.\n- **Disempowered agents.** Every refund needing manager approval. Grant authority within limits.\n- **Support-product wall.** Tickets never reaching product. Systematic feedback loops, monthly reports.\n- **Vanity CSAT.** Surveying only resolved tickets. Measure broadly; investigate detractors.\n- **Understaffing growth.** Ticket queues growing while hiring lags. Forecast from growth; hire ahead.\n- **Optimizing handle time over resolution.** Rushing agents creates repeat contacts. First-contact resolution beats average handle time for both CSAT and cost.\n- **No self-service investment.** Answering the same questions forever. Every ticket category with 50+ monthly volume deserves a help article.\n- **Support as cost center.** Starving support of headcount and tools. Great support retains revenue — fund it like the growth lever it is.\n- **Ignoring agent burnout.** High-volume empathy work exhausts people. Monitor workload, rotate difficult queues, and create advancement paths.\n","## Overview\n\nSaaS customer support is a retention engine: fast, effective help keeps customers renewing, and support interactions surface product insights. This skill covers building support operations — tiered models, SLAs, knowledge bases, macros, escalation paths, and the feedback loops that turn tickets into product improvements. Platform-neutral.\n\n\nCustomer support operations turn problems into loyalty: great support recovers trust, generates product insight, and differentiates commodities.\nThis skill covers the operational playbook — channel strategy, ticket workflows, macros, QA, metrics, and team design — for support organizations from startup to scale.\n## When to use\n\n- Building a support team or function\n- Defining support tiers and SLAs\n- Reducing response and resolution times\n- Creating escalation processes\n- Turning support feedback into product input\n- Scaling support efficiently\n\n- Building a support team from scratch\n- Reducing ticket backlog and response times\n- Designing support QA and coaching programs\n- Choosing support channels and tooling\n- Turning support insights into product improvements\n## Core concepts\n\n**Tiered support.** L1 (triage, common issues, macros), L2 (technical troubleshooting, account-specific), L3 (engineering escalation, bugs). Clear tier criteria and escalation paths prevent both premature escalation and L1 heroics on engineering problems.\n\n**SLAs.** Response time (first reply) and resolution time targets by priority (P1 critical → P4 question) and plan tier (enterprise gets faster). Publish SLAs honestly — missed SLAs damage trust more than slower honest ones. Measure compliance weekly.\n\n**Knowledge base.** Self-service deflects 30–60% of tickets: task-based articles, troubleshooting guides, video walkthroughs for complex flows, and in-app help links. Maintain ruthlessly — stale articles mislead. Every resolved ticket is a candidate article.\n\n**Macros and templates.** Canned responses for common scenarios with personalization tokens and human-touch room. Review quarterly. Macros speed responses but must never feel robotic — train agents to adapt, not paste.\n\n**Escalation.** Criteria per tier jump, warm handoffs (context transfers — customers never repeat themselves), engineering escalation process (with severity and SLA), and executive escalation for key accounts. Escalation is a designed path, not an admission of failure.\n\n**Support-to-product feedback.** Tag tickets by theme, quantify (how many customers hit this?), and feed prioritized insights to product regularly. Support sees product reality first — the best feature ideas and bug reports live in tickets.\n\n\n**Channel strategy.** Email (async, detailed), chat (real-time, high volume), phone (urgent, complex, high-touch), self-service (deflection), social (public, reputation-sensitive).\nMatch channels to issue types: billing disputes deserve humans; password resets deserve self-service.\nStaff channels by demand patterns — chat peaks differ from email peaks.\n**Ticket triage.** Urgent (system down, data loss) → high (core feature broken) → normal (how-to, minor bugs) → low (feature requests).\nSLAs per priority, publicly committed where appropriate.\nTriage within 1 hour for urgent, 4 for high — speed of acknowledgment matters as much as speed of resolution.\n**Macros and saved replies.** For the top 20 recurring issues: empathetic, accurate, personalized-able templates.\nMacros save time but must not sound robotic — leave placeholders for personalization and empower agents to adapt.\nReview macro usage monthly; heavily-edited macros need rewriting.\n**QA and coaching.** Score tickets on: correctness, tone, completeness, and efficiency.\nSample 5–10 tickets per agent monthly; coach to patterns, not incidents.\nCalibrate scores across reviewers quarterly — inconsistent QA is worse than none.\n## Practical workflow\n\n1. **Define the model.** Tiers, SLAs by priority and plan, channels (chat, email, phone — match to customer expectations), hours\u002Fcoverage, and languages.\n2. **Build foundations.** Help center (top 20 ticket drivers first), macro library, internal runbooks, escalation paths, and tooling (ticketing, chat, phone, screen-share).\n3. **Staff and train.** Hire for empathy + technical aptitude, train on product deeply (support must know the product cold), soft skills (de-escalation, clear writing), and empower with authority (refunds, credits within limits — don't make agents beg for permission).\n4. **Launch with SLAs.** Publish targets, staff to meet them (queue math: volume × handle time ÷ availability), and monitor real-time dashboards.\n5. **Optimize.** Weekly: SLA compliance, CSAT, first-contact resolution, handle times, escalation rates. Monthly: ticket theme analysis → product feedback report. Quarterly: macro\u002Farticle audits, training refreshers.\n6. **Scale smartly.** Self-service investment (deflection), automation (triage bots, suggested macros), tier-0 (community, in-app guidance), and hiring ahead of growth curves.\n\n**Ticket theme report template:** top 10 themes by volume → trend (rising\u002Ffalling) → customer impact quotes → product recommendation → owner → status. Monthly to product leadership.\n\n\n**Support metrics dashboard:** first response time → resolution time → CSAT → first-contact resolution rate → backlog age → ticket volume by category → agent utilization.\nReview weekly; investigate any metric moving 10%+ before it becomes a crisis.\n**Escalation paths:** L1 (generalists, macros, known issues) → L2 (technical specialists) → L3 (engineering) → incident commander (outages).\nDefine handoff criteria explicitly; tickets bouncing between tiers destroy CSAT.\n**Voice-of-customer loop:** tag tickets by theme → monthly report to product (top 10 themes with volume and quotes) → track which themes get addressed → close the loop with customers when fixes ship.\nSupport is the cheapest user research you already pay for — mine it.\n## Common pitfalls\n\n- **No SLAs.** \"We'll get to it.\" Define and publish response targets.\n- **Stale knowledge base.** Articles from three versions ago. Assign owners; review quarterly.\n- **Cold escalations.** Customers repeating their story at each tier. Warm handoffs with full context.\n- **Disempowered agents.** Every refund needing manager approval. Grant authority within limits.\n- **Support-product wall.** Tickets never reaching product. Systematic feedback loops, monthly reports.\n- **Vanity CSAT.** Surveying only resolved tickets. Measure broadly; investigate detractors.\n- **Understaffing growth.** Ticket queues growing while hiring lags. Forecast from growth; hire ahead.\n- **Optimizing handle time over resolution.** Rushing agents creates repeat contacts. First-contact resolution beats average handle time for both CSAT and cost.\n- **No self-service investment.** Answering the same questions forever. Every ticket category with 50+ monthly volume deserves a help article.\n- **Support as cost center.** Starving support of headcount and tools. Great support retains revenue — fund it like the growth lever it is.\n- **Ignoring agent burnout.** High-volume empathy work exhausts people. Monitor workload, rotate difficult queues, and create advancement paths.\n",{"name":5,"category":24,"description":7},"curviate","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-customer-support-playbook",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 customer-support-playbook",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill customer-support-playbook",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill customer-support-playbook","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-customer-support-playbook\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",[],[]]