[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EWEM95B8N9TMGDPADTX2K2":3,"skill-same:01M7EWEM95B8N9TMGDPADTX2K2":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7EWEM95B8N9TMGDPADTX2K2","ams-workflow-automation",null,"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-workflow-automation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: workflow-automation\ndescription: Design reliable workflow automations: triggers, idempotency, error handling, observability, and choosing the right tool. Use when automating repetitive processes or evaluating automation platforms.\ncategory: workflow-automation\n---\n\n# Workflow Automation\n\n## Overview\n\nWorkflow automation connects triggers to actions: when X happens, do Y — across apps, APIs, and systems.\n\nReliable automation is a design discipline: idempotent actions, explicit error handling, retries with backoff, and observability from day one.\n\nThis skill is platform-agnostic: the principles apply whether you use n8n, Zapier, Make, code, or cron jobs.\n\nThe question is never 'can I automate this?' but 'should I — and how will I know when it breaks?'\n\n## When to use\n\n- Repetitive multi-step processes done manually\n- Connecting apps that don't integrate natively\n- Evaluating automation platforms for a team\n- Automations that keep breaking silently\n- Deciding what to automate vs. leave manual\n\n## Core concepts\n\n- **Triggers.**\n  Events that start the flow: webhooks (instant), polling (scheduled checks), schedules (cron), manual. Prefer webhooks over polling where available — faster and cheaper.\n- **Actions and branching.**\n  Steps that do things, with conditional branches and loops. Keep flows linear where possible; deep branching becomes untestable.\n- **Idempotency.**\n  Running the same flow twice shouldn't duplicate effects. Design actions to be safe on retry: check-before-create, upsert instead of insert, dedupe keys.\n- **Error handling.**\n  Every external call can fail. Retry with exponential backoff, dead-letter queues for poison messages, and alerts — not silent drops.\n- **State and dedup.**\n  Track processed items (IDs, timestamps) to avoid reprocessing. Polling triggers especially need high-water marks.\n- **Observability.**\n  Log runs, alert on failures, dashboard key metrics. An automation you can't monitor is a liability with a timer.\n- **Secrets management.**\n  API keys in vaults\u002Fsecrets managers, never hardcoded. Rotate credentials; scope them to least privilege.\n- **Manual escape hatches.**\n  Every automation needs a pause button, a manual retry, and a way to run steps by hand. You'll need them at 2am.\n\n## Practical workflow\n\n1. **Map the process manually.**\n   Document the current manual process step by step. Automate the stable version — automating a messy process cements the mess.\n2. **Score candidates.**\n   Frequency x time-cost x error-cost. Automate high-frequency, error-prone drudgery first. Leave rare, judgment-heavy work manual.\n3. **Choose the platform.**\n   No-code (fast, limited) vs. code (flexible, maintained) vs. hybrid. Match complexity: simple linear flows -> no-code; branching logic -> code.\n4. **Design for failure.**\n   For each step ask: what if the API is down? What if data is malformed? What if it runs twice? Build retries, validation, and dedup in.\n5. **Build the happy path.**\n   Get the core flow working end-to-end before edge cases. Test with real data in a sandbox.\n6. **Add observability.**\n   Logging, failure alerts (to a channel you actually watch), run dashboards. Test the alerting by breaking something deliberately.\n7. **Document and hand off.**\n   What it does, how to pause\u002Fretry, who owns it. Automations outlive their builders — document like you'll forget.\n8. **Review periodically.**\n   APIs change, processes evolve. Quarterly: still needed? Still working? Still the right tool? Prune dead automations.\n\n## Common pitfalls\n\n- **Automating a broken process.**\n  Automating chaos produces faster chaos. Fix the process manually first, then automate the stable version.\n- **No idempotency.**\n  Double-running creates duplicate orders, emails, tickets. Design every action safe-on-retry from the start.\n- **Silent failures.**\n  Automation breaks, nobody notices for weeks. Alerts on failure are not optional — they're the product.\n- **Polling everything.**\n  5-minute polling across 20 integrations burns quota and lags. Webhooks where available; sensible intervals elsewhere.\n- **Hardcoded secrets.**\n  API keys in flow definitions, shared screenshots, repos. Vaults + rotation, always.\n- **No pause button.**\n  Runaway automation spamming customers with no kill switch. Every flow needs an off switch you can hit in seconds.\n- **Over-automation.**\n  Automating rare, judgment-heavy tasks because you can. Some work should stay human — automate the rote, not the judgment.\n- **Orphaned automations.**\n  Builder leaves, automation breaks, nobody knows it exists. Ownership + documentation + monitoring, or delete it.\n","# Workflow Automation\n\n## Overview\n\nWorkflow automation connects triggers to actions: when X happens, do Y — across apps, APIs, and systems.\n\nReliable automation is a design discipline: idempotent actions, explicit error handling, retries with backoff, and observability from day one.\n\nThis skill is platform-agnostic: the principles apply whether you use n8n, Zapier, Make, code, or cron jobs.\n\nThe question is never 'can I automate this?' but 'should I — and how will I know when it breaks?'\n\n## When to use\n\n- Repetitive multi-step processes done manually\n- Connecting apps that don't integrate natively\n- Evaluating automation platforms for a team\n- Automations that keep breaking silently\n- Deciding what to automate vs. leave manual\n\n## Core concepts\n\n- **Triggers.**\n  Events that start the flow: webhooks (instant), polling (scheduled checks), schedules (cron), manual. Prefer webhooks over polling where available — faster and cheaper.\n- **Actions and branching.**\n  Steps that do things, with conditional branches and loops. Keep flows linear where possible; deep branching becomes untestable.\n- **Idempotency.**\n  Running the same flow twice shouldn't duplicate effects. Design actions to be safe on retry: check-before-create, upsert instead of insert, dedupe keys.\n- **Error handling.**\n  Every external call can fail. Retry with exponential backoff, dead-letter queues for poison messages, and alerts — not silent drops.\n- **State and dedup.**\n  Track processed items (IDs, timestamps) to avoid reprocessing. Polling triggers especially need high-water marks.\n- **Observability.**\n  Log runs, alert on failures, dashboard key metrics. An automation you can't monitor is a liability with a timer.\n- **Secrets management.**\n  API keys in vaults\u002Fsecrets managers, never hardcoded. Rotate credentials; scope them to least privilege.\n- **Manual escape hatches.**\n  Every automation needs a pause button, a manual retry, and a way to run steps by hand. You'll need them at 2am.\n\n## Practical workflow\n\n1. **Map the process manually.**\n   Document the current manual process step by step. Automate the stable version — automating a messy process cements the mess.\n2. **Score candidates.**\n   Frequency x time-cost x error-cost. Automate high-frequency, error-prone drudgery first. Leave rare, judgment-heavy work manual.\n3. **Choose the platform.**\n   No-code (fast, limited) vs. code (flexible, maintained) vs. hybrid. Match complexity: simple linear flows -> no-code; branching logic -> code.\n4. **Design for failure.**\n   For each step ask: what if the API is down? What if data is malformed? What if it runs twice? Build retries, validation, and dedup in.\n5. **Build the happy path.**\n   Get the core flow working end-to-end before edge cases. Test with real data in a sandbox.\n6. **Add observability.**\n   Logging, failure alerts (to a channel you actually watch), run dashboards. Test the alerting by breaking something deliberately.\n7. **Document and hand off.**\n   What it does, how to pause\u002Fretry, who owns it. Automations outlive their builders — document like you'll forget.\n8. **Review periodically.**\n   APIs change, processes evolve. Quarterly: still needed? Still working? Still the right tool? Prune dead automations.\n\n## Common pitfalls\n\n- **Automating a broken process.**\n  Automating chaos produces faster chaos. Fix the process manually first, then automate the stable version.\n- **No idempotency.**\n  Double-running creates duplicate orders, emails, tickets. Design every action safe-on-retry from the start.\n- **Silent failures.**\n  Automation breaks, nobody notices for weeks. Alerts on failure are not optional — they're the product.\n- **Polling everything.**\n  5-minute polling across 20 integrations burns quota and lags. Webhooks where available; sensible intervals elsewhere.\n- **Hardcoded secrets.**\n  API keys in flow definitions, shared screenshots, repos. Vaults + rotation, always.\n- **No pause button.**\n  Runaway automation spamming customers with no kill switch. Every flow needs an off switch you can hit in seconds.\n- **Over-automation.**\n  Automating rare, judgment-heavy tasks because you can. Some work should stay human — automate the rote, not the judgment.\n- **Orphaned automations.**\n  Builder leaves, automation breaks, nobody knows it exists. Ownership + documentation + monitoring, or delete it.\n",{},"main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-workflow-automation",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill ams-workflow-automation",{"tool":37,"command":38},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill ams-workflow-automation",{"tool":40,"command":41},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill ams-workflow-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-workflow-automation\u002FSKILL.md",true,[],[46,53,61,68,75,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"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":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":57,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"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":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"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",[],[]]