[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DENV7HHZ290D9DTA8EF23V":3,"skill-same:01M6DENV7HHZ290D9DTA8EF23V":92},{"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":23,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6DENV7HHZ290D9DTA8EF23V","agent-guidelines",null,"Discovers project stack, researches breaking changes, consults on recommendations, generates path-scoped rules and reference docs.","iamsteveholmes\u002Fmomentum","iamsteveholmes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92353?v=4","01M6DENK56DRSF72CJ6FJQ4RT1","Steve Holmes","01M6DENK9KCZRYFFEB0M689F7D",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fagent-guidelines\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35],"guidelines","agent guidelines","docs","stack","Rules","reference","project","recommendations","high","path","changes","scoped","2026-11-10 10:12:30",false,"---\nname: replica-recon\ndescription: >-\n  Reverse-engineers any app into a recon map: screen inventory, user flows,\n  component list, inferred data model and a feature matrix, from public pages,\n  screenshots, app store listings, help docs and the user's own account. The\n  first step of the Replica pack. Use when the user says \"clone this app\",\n  \"reverse engineer X\", \"how does X work\", \"map out X\", \"what screens does X\n  have\", \"I want to build my own version of X\", \"copy this app\", or pastes an\n  app's URL or App Store link and wants to rebuild it.\n---\n\n# replica-recon\n\nEverything else in the pack builds from what this skill writes. A bad recon\nmap means a bad clone, so take the time here.\n\nOutput goes in the user's project:\n\n```\nreplica\u002Frecon.md        the recon map (template: recon-map.md in this folder)\nreplica\u002Ffeatures.csv    the feature matrix (template: features.csv in this folder)\nreplica\u002Fscreens\u002F        reference screenshots of the original. Never shipped.\n```\n\n## The rules, before anything else\n\nThis skill rebuilds **functionality and UX patterns**, clean-room style. It\nstudies what the app does and how a user moves through it. It does not take\nanything the app owns.\n\n- **Public sources and the user's own account only.** Never log into an\n  account that is not the user's, never ask for a password, never get past a\n  paywall or a login by any trick.\n- **Reading, not scraping.** No crawlers, no bulk downloads, no loops. If a\n  browser tool is connected to the user's own browser, read pages at human\n  speed with the user present.\n- **No source code, no private APIs.** Do not read or save the app's\n  JavaScript bundles, decompile its binary, or log its network calls to copy\n  endpoints. Public API docs are fine to read.\n- **Check the terms.** Some products' terms forbid using an account to build a\n  competing product. If the user's account is under terms like that, say so\n  and work from public sources only.\n- **Screenshots are reference.** They live in `replica\u002Fscreens\u002F`, are used to\n  compare layouts, and never go into the clone.\n\n## Step 1: scope\n\nAsk three things, or propose answers and get a yes:\n\n1. **Which app, which platform.** Web, iOS, Android, desktop.\n2. **Which slice.** \"All of Notion\" is not a project. \"Notion's pages, blocks\n   and sharing\" is. Default to the core loop: the one flow users pay for.\n3. **Who it is for.** The user's own business, a niche, a product to sell.\n\n## Step 2: list the sources\n\nBuild a sources table first, with a URL on every row. In order of value:\n\n| source | what it gives you |\n| --- | --- |\n| help center \u002F docs | the most complete feature list there is, and the settings |\n| pricing page | which features matter (they gate them) |\n| changelog | what was added recently, what the team thinks is important |\n| app store listing | screenshots of every key screen, the pitch, ratings |\n| public walkthrough videos | real flows, click by click |\n| marketing site | positioning, the core loop in their words |\n| the user's own account | the real thing, every state, driven by the user |\n| public API docs | the data model, almost for free |\n\n## Step 3: screen inventory\n\nOne row per screen. IDs are stable: S01, S02... Every other file refers to them.\n\n`ID | screen | route or how you get there | purpose | key components | states seen`\n\nStates matter: empty, loading, filled, error, permission denied, mobile. An\nempty state you did not record is an empty state you will not build.\n\n## Step 4: user flows\n\nF01, F02... Each one is a goal and the screens it passes through:\n\n```\nF01 Guest books a meeting\n    S07 booking page -> S08 pick a time -> S09 details form -> S10 confirmed\n    edge: no slots this week, time zone differs, slot taken while filling the form\n```\n\nCount the clicks on the happy path. It becomes the number to beat.\n\n## Step 5: components\n\nEvery repeated UI part: buttons, inputs, date pickers, modals, tables, toasts,\nnav. Name, variants, states, which screens use it. This becomes\nreplica-design's component list.\n\n## Step 6: inferred data model\n\nEntities, fields and relationships, each with its evidence and a confidence:\n\n```\nBooking  id, event_type_id, start_at, end_at, guest_name, guest_email,\n         status (confirmed | cancelled | rescheduled), answers (json)\n         evidence: S09 form fields, S10 confirmation, help article \"Cancel a booking\"\n         confidence: high\n```\n\nMark guesses as guesses. replica-architect turns this into a real schema.\n\n## Step 7: feature matrix\n\nWrite `replica\u002Ffeatures.csv` (columns: feature, area, priority, original,\nclone, notes). Priority is must \u002F should \u002F could. `clone` starts at `no` for\nevery row and gets filled in during the build. replica-diff scores it.\n\n## Step 8: what cannot be cloned\n\nList it honestly, as `skip` rows with a reason: licensed content (a music\ncatalogue, a stock library), the network and its users, data the app owns,\npartner deals, hardware, regulated licences (banking, health). \"Clone any\napp\" means the features and the flow, not what the app owns.\n\n## Step 9: size it\n\nScreens, flows, entities, and the hard parts (realtime, sync, payments,\ncalendar or email integrations, offline). Give a size: S (a weekend), M (a\nfew weeks), L (a quarter), XL (rescope it). No promises of a perfect clone.\n\n## Output\n\n`replica\u002Frecon.md` and `replica\u002Ffeatures.csv`, then a five-line summary: the\ncore loop, screen and flow counts, the three hardest parts, what is out of\nscope, and the next step: `\u002Freplica-architect`.\n","# replica-recon\n\nEverything else in the pack builds from what this skill writes. A bad recon\nmap means a bad clone, so take the time here.\n\nOutput goes in the user's project:\n\n```\nreplica\u002Frecon.md        the recon map (template: recon-map.md in this folder)\nreplica\u002Ffeatures.csv    the feature matrix (template: features.csv in this folder)\nreplica\u002Fscreens\u002F        reference screenshots of the original. Never shipped.\n```\n\n## The rules, before anything else\n\nThis skill rebuilds **functionality and UX patterns**, clean-room style. It\nstudies what the app does and how a user moves through it. It does not take\nanything the app owns.\n\n- **Public sources and the user's own account only.** Never log into an\n  account that is not the user's, never ask for a password, never get past a\n  paywall or a login by any trick.\n- **Reading, not scraping.** No crawlers, no bulk downloads, no loops. If a\n  browser tool is connected to the user's own browser, read pages at human\n  speed with the user present.\n- **No source code, no private APIs.** Do not read or save the app's\n  JavaScript bundles, decompile its binary, or log its network calls to copy\n  endpoints. Public API docs are fine to read.\n- **Check the terms.** Some products' terms forbid using an account to build a\n  competing product. If the user's account is under terms like that, say so\n  and work from public sources only.\n- **Screenshots are reference.** They live in `replica\u002Fscreens\u002F`, are used to\n  compare layouts, and never go into the clone.\n\n## Step 1: scope\n\nAsk three things, or propose answers and get a yes:\n\n1. **Which app, which platform.** Web, iOS, Android, desktop.\n2. **Which slice.** \"All of Notion\" is not a project. \"Notion's pages, blocks\n   and sharing\" is. Default to the core loop: the one flow users pay for.\n3. **Who it is for.** The user's own business, a niche, a product to sell.\n\n## Step 2: list the sources\n\nBuild a sources table first, with a URL on every row. In order of value:\n\n| source | what it gives you |\n| --- | --- |\n| help center \u002F docs | the most complete feature list there is, and the settings |\n| pricing page | which features matter (they gate them) |\n| changelog | what was added recently, what the team thinks is important |\n| app store listing | screenshots of every key screen, the pitch, ratings |\n| public walkthrough videos | real flows, click by click |\n| marketing site | positioning, the core loop in their words |\n| the user's own account | the real thing, every state, driven by the user |\n| public API docs | the data model, almost for free |\n\n## Step 3: screen inventory\n\nOne row per screen. IDs are stable: S01, S02... Every other file refers to them.\n\n`ID | screen | route or how you get there | purpose | key components | states seen`\n\nStates matter: empty, loading, filled, error, permission denied, mobile. An\nempty state you did not record is an empty state you will not build.\n\n## Step 4: user flows\n\nF01, F02... Each one is a goal and the screens it passes through:\n\n```\nF01 Guest books a meeting\n    S07 booking page -> S08 pick a time -> S09 details form -> S10 confirmed\n    edge: no slots this week, time zone differs, slot taken while filling the form\n```\n\nCount the clicks on the happy path. It becomes the number to beat.\n\n## Step 5: components\n\nEvery repeated UI part: buttons, inputs, date pickers, modals, tables, toasts,\nnav. Name, variants, states, which screens use it. This becomes\nreplica-design's component list.\n\n## Step 6: inferred data model\n\nEntities, fields and relationships, each with its evidence and a confidence:\n\n```\nBooking  id, event_type_id, start_at, end_at, guest_name, guest_email,\n         status (confirmed | cancelled | rescheduled), answers (json)\n         evidence: S09 form fields, S10 confirmation, help article \"Cancel a booking\"\n         confidence: high\n```\n\nMark guesses as guesses. replica-architect turns this into a real schema.\n\n## Step 7: feature matrix\n\nWrite `replica\u002Ffeatures.csv` (columns: feature, area, priority, original,\nclone, notes). Priority is must \u002F should \u002F could. `clone` starts at `no` for\nevery row and gets filled in during the build. replica-diff scores it.\n\n## Step 8: what cannot be cloned\n\nList it honestly, as `skip` rows with a reason: licensed content (a music\ncatalogue, a stock library), the network and its users, data the app owns,\npartner deals, hardware, regulated licences (banking, health). \"Clone any\napp\" means the features and the flow, not what the app owns.\n\n## Step 9: size it\n\nScreens, flows, entities, and the hard parts (realtime, sync, payments,\ncalendar or email integrations, offline). Give a size: S (a weekend), M (a\nfew weeks), L (a quarter), XL (rescope it). No promises of a perfect clone.\n\n## Output\n\n`replica\u002Frecon.md` and `replica\u002Ffeatures.csv`, then a five-line summary: the\ncore loop, screen and flow counts, the three hardest parts, what is out of\nscope, and the next step: `\u002Freplica-architect`.\n",{"name":41,"description":42},"replica-recon","Reverse-engineers any app into a recon map: screen inventory, user flows, component list, inferred data model and a feature matrix, from public pages, screenshots, app store listings, help docs and the user's own account. The first step of the Replica pack. Use when the user says \"clone this app\", \"reverse engineer X\", \"how does X work\", \"map out X\", \"what screens does X have\", \"I want to build my own version of X\", \"copy this app\", or pastes an app's URL or App Store link and wants to rebuild it.","main","d32244fd815eaa4d6bb54fa1751c70f44528fa42","skills\u002Fmomentum\u002Fskills\u002Fagent-guidelines","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes","http:\u002F\u002Fcapitalcodemonkey.blogspot.com","2026-11-09 05:58:39",{"source":8,"skillName":41,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add iamsteveholmes\u002Fmomentum --skill replica-recon",{"tool":56,"command":57},"bunx","bunx skills add iamsteveholmes\u002Fmomentum --skill replica-recon",{"tool":59,"command":60},"pnpm","pnpm dlx skills add iamsteveholmes\u002Fmomentum --skill replica-recon","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fagent-guidelines\u002FSKILL.md",true,[64,70,76,80,84,88],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"features.csv","ASSET","资产文件",1169,"https:\u002F\u002Fgithub.com\u002FWhiteChronos\u002FChatGPT\u002Fblob\u002Fmain\u002Fplugins\u002Freplica-controller\u002Fskills\u002Freplica-recon\u002Ffeatures.csv",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"recon-map.md","REFERENCE","参考文档",1245,"https:\u002F\u002Fgithub.com\u002FWhiteChronos\u002FChatGPT\u002Fblob\u002Fmain\u002Fplugins\u002Freplica-controller\u002Fskills\u002Freplica-recon\u002Frecon-map.md",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fdetection-heuristics.md",3960,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fagent-guidelines\u002Freferences\u002Fdetection-heuristics.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Freference-doc-template.md",2022,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fagent-guidelines\u002Freferences\u002Freference-doc-template.md",{"path":85,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Frule-template.md",2137,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fagent-guidelines\u002Freferences\u002Frule-template.md",{"path":89,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":90,"sourceHtmlUrl":91},"workflow.md",16674,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fagent-guidelines\u002Fworkflow.md",[93,113,131,153,170,188],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":36},"01M6DES6J0HGT27SEJJWF316FV","upstream-fix","Traces quality failures upstream to spec, rule, or workflow root cause. Proposes fixes at the right level.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fupstream-fix\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,32,108,109,110,111,112],"upstream","upstream fix","fix","to spec","root cause","traces","fixes","at","root","rule","quality","workflow","spec",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":36},"01M6DES4A08NFWQM0AJBR2RRX5","triage","Dedup gate + batch-classify observations into five classes, enrich ARTIFACTs, batch-approve, delegate to intake\u002Fdecision or queue.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Ftriage\u002FSKILL.md",[],[115,120,121,122,123,124,125,126,32,127,128,129,130],"batch","intake","artifacts","decision","queue","delegate","approve","observations","enrich","classify","gate",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":36},"01M6DERYX8W6Z9Z4RM5V6E9HED","sprint-planning","Sprint planning — story selection, team composition, Gherkin specs, and visual companion plan gate for developer sign-off.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-planning\u002FSKILL.md",[],[138,139,140,32,141,142,143,144,145,146,147,148,149,150,151,152,130],"planning","sprint","sprint planning","visual companion","plan gate","for","companion","sign","visual","selection","Composition","Story","plan","team","developer",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":36},"01M6DERWCP7Y0WDY5KG6109RQB","sprint-manager","Sole writer of stories\u002Findex.json and sprints\u002Findex.json — validates state transitions, activates sprints, manages epic membership.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-manager\u002FSKILL.md",[],[160,139,161,162,163,164,165,166,167,168,169],"sprint manager","manager","writer","stories","sprints","EPIC","transitions","json","index","state",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":36},"01M6DERS7B4QHAH5GZHHBA4AHB","sprint-dev","Sprint execution — dependency-driven story development, post-merge AVFL, and team review.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-dev\u002FSKILL.md",[],[177,178,139,151,179,180,181,182,183,184,32,185,186,187,149],"dev","sprint dev","execution","team review","development","merge","review","dependency","post","avfl","driven",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":36},"01M6DERP0A271FYSAXCV85GF04","retro","Sprint retrospective — transcript audit engine (dynamic Workflow), story verification, findings document, and sprint closure.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fretro\u002FSKILL.md",[],[190,195,196,32,197,139,198,149,199,200,201,202,203,111],"sprint retrospective","closure","dynamic workflow","document","engine","audit","verification","transcript","retrospective"]