[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVBWQERP78RC4P7TTAWN3E":3,"skill-same:01M7EVBWQERP78RC4P7TTAWN3E":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},"01M7EVBWQERP78RC4P7TTAWN3E","ams-planning",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-planning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: planning\ndescription: Plan multi-step AI agent work: decompose goals, sequence agents, define handoffs, and handle failure. Use when orchestrating agents through complex tasks that need structure before execution.\ncategory: ai-maestro\n---\n\n# Planning\n\n## Overview\n\nAgents execute well but plan poorly without structure. Planning is the discipline of decomposing a goal into sequenced, assignable steps before any agent acts.\n\nIn the AI Maestro model, planning produces an explicit plan: goal, steps, agent assignments, dependencies, checkpoints, and success criteria.\n\nGood plans make multi-agent work reliable: each agent knows its task, its inputs, its outputs, and when to hand off.\n\nPlan once, execute many: the plan is reviewable, resumable, and reusable.\n\n## When to use\n\n- Complex tasks needing multiple agents or steps\n- Agent work that keeps drifting or duplicating effort\n- Coordinating handoffs between specialized agents\n- Long-running work that must survive interruptions\n- Reviewing agent strategy before burning execution budget\n\n## Core concepts\n\n- **Decomposition.**\n  Break the goal into steps small enough for one agent to complete confidently. Each step: clear input, clear output, verifiable done-ness.\n- **Sequencing and dependencies.**\n  Order steps by dependency: what must finish before what can start? Parallelize independent steps; sequence the dependent ones.\n- **Agent assignment.**\n  Match steps to agent capabilities: researcher for gathering, coder for building, reviewer for checking. Right agent, right step.\n- **Handoff contracts.**\n  Define exactly what passes between steps: file paths, data formats, key facts. Vague handoffs are where multi-agent work dies.\n- **Checkpoints.**\n  Human (or supervisor) review points before irreversible or expensive steps. Plans without checkpoints drift.\n- **Success criteria.**\n  Verifiable conditions for 'done' per step and overall. Without them, agents optimize for activity, not outcomes.\n- **Failure branches.**\n  For each risky step: what if it fails? Retry, fallback step, or escalate? Plans that assume success break on contact with reality.\n- **Plan as artifact.**\n  The plan lives in a file: readable, reviewable, resumable. Execution updates it; it never lives only in chat.\n\n## Practical workflow\n\n1. **State the goal.**\n   One paragraph: outcome, constraints, non-goals. The plan serves the goal — get it crisp first.\n2. **Decompose into steps.**\n   Break down until each step is agent-sized: clear inputs, outputs, and done criteria. Number them; note dependencies.\n3. **Assign agents.**\n   Match each step to the best-suited agent type. Note required context each agent needs at handoff.\n4. **Define handoffs.**\n   For each boundary: what artifact passes, in what format, where. Write the contracts explicitly.\n5. **Add checkpoints and criteria.**\n   Review points before big steps; success criteria per step and overall. Make 'done' verifiable.\n6. **Review the plan.**\n   Human reviews before execution: are steps right-sized? Dependencies correct? Risks covered? Fix now, cheaply.\n7. **Execute with tracking.**\n   Run steps in order; update plan status as you go. Blocked steps get noted with cause, not silently skipped.\n8. **Close out and learn.**\n   Verify success criteria; record what the plan got right\u002Fwrong. Feed lessons into the next plan.\n\n## Common pitfalls\n\n- **Skipping planning.**\n  Throwing agents at a complex goal with no decomposition. Activity without architecture wastes budget and time.\n- **Oversized steps.**\n  'Research the market' as one step. Steps must be completable in one focused agent run with verifiable output.\n- **Vague handoffs.**\n  'Pass the results to the next agent.' What results, in what format, where? Handoff vagueness compounds across steps.\n- **No checkpoints.**\n  Long agent runs with no review. Drift compounds silently; checkpoints catch it while it's cheap.\n- **Planning forever.**\n  Analysis paralysis: planning the plan. Timebox planning; a good-enough plan executed beats a perfect plan drafted.\n- **Ignoring dependencies.**\n  Parallelizing steps that actually depend on each other. Dependency errors surface as rework — map them upfront.\n- **No failure branches.**\n  Assuming every step succeeds. One failed step with no fallback stalls the whole plan.\n- **Plan in chat only.**\n  Plans in scrollback can't be tracked, resumed, or reviewed. The plan is a file, always.\n","# Planning\n\n## Overview\n\nAgents execute well but plan poorly without structure. Planning is the discipline of decomposing a goal into sequenced, assignable steps before any agent acts.\n\nIn the AI Maestro model, planning produces an explicit plan: goal, steps, agent assignments, dependencies, checkpoints, and success criteria.\n\nGood plans make multi-agent work reliable: each agent knows its task, its inputs, its outputs, and when to hand off.\n\nPlan once, execute many: the plan is reviewable, resumable, and reusable.\n\n## When to use\n\n- Complex tasks needing multiple agents or steps\n- Agent work that keeps drifting or duplicating effort\n- Coordinating handoffs between specialized agents\n- Long-running work that must survive interruptions\n- Reviewing agent strategy before burning execution budget\n\n## Core concepts\n\n- **Decomposition.**\n  Break the goal into steps small enough for one agent to complete confidently. Each step: clear input, clear output, verifiable done-ness.\n- **Sequencing and dependencies.**\n  Order steps by dependency: what must finish before what can start? Parallelize independent steps; sequence the dependent ones.\n- **Agent assignment.**\n  Match steps to agent capabilities: researcher for gathering, coder for building, reviewer for checking. Right agent, right step.\n- **Handoff contracts.**\n  Define exactly what passes between steps: file paths, data formats, key facts. Vague handoffs are where multi-agent work dies.\n- **Checkpoints.**\n  Human (or supervisor) review points before irreversible or expensive steps. Plans without checkpoints drift.\n- **Success criteria.**\n  Verifiable conditions for 'done' per step and overall. Without them, agents optimize for activity, not outcomes.\n- **Failure branches.**\n  For each risky step: what if it fails? Retry, fallback step, or escalate? Plans that assume success break on contact with reality.\n- **Plan as artifact.**\n  The plan lives in a file: readable, reviewable, resumable. Execution updates it; it never lives only in chat.\n\n## Practical workflow\n\n1. **State the goal.**\n   One paragraph: outcome, constraints, non-goals. The plan serves the goal — get it crisp first.\n2. **Decompose into steps.**\n   Break down until each step is agent-sized: clear inputs, outputs, and done criteria. Number them; note dependencies.\n3. **Assign agents.**\n   Match each step to the best-suited agent type. Note required context each agent needs at handoff.\n4. **Define handoffs.**\n   For each boundary: what artifact passes, in what format, where. Write the contracts explicitly.\n5. **Add checkpoints and criteria.**\n   Review points before big steps; success criteria per step and overall. Make 'done' verifiable.\n6. **Review the plan.**\n   Human reviews before execution: are steps right-sized? Dependencies correct? Risks covered? Fix now, cheaply.\n7. **Execute with tracking.**\n   Run steps in order; update plan status as you go. Blocked steps get noted with cause, not silently skipped.\n8. **Close out and learn.**\n   Verify success criteria; record what the plan got right\u002Fwrong. Feed lessons into the next plan.\n\n## Common pitfalls\n\n- **Skipping planning.**\n  Throwing agents at a complex goal with no decomposition. Activity without architecture wastes budget and time.\n- **Oversized steps.**\n  'Research the market' as one step. Steps must be completable in one focused agent run with verifiable output.\n- **Vague handoffs.**\n  'Pass the results to the next agent.' What results, in what format, where? Handoff vagueness compounds across steps.\n- **No checkpoints.**\n  Long agent runs with no review. Drift compounds silently; checkpoints catch it while it's cheap.\n- **Planning forever.**\n  Analysis paralysis: planning the plan. Timebox planning; a good-enough plan executed beats a perfect plan drafted.\n- **Ignoring dependencies.**\n  Parallelizing steps that actually depend on each other. Dependency errors surface as rework — map them upfront.\n- **No failure branches.**\n  Assuming every step succeeds. One failed step with no fallback stalls the whole plan.\n- **Plan in chat only.**\n  Plans in scrollback can't be tracked, resumed, or reviewed. The plan is a file, always.\n",{},"main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-planning",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-planning",{"tool":37,"command":38},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill ams-planning",{"tool":40,"command":41},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill ams-planning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-planning\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",[],[]]