[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"creator:01M6C67T2SPVP033M7REAAHYHX":3,"creator-list:01M6C67T2SPVP033M7REAAHYHX:stars:1:":19},{"accountNo":4,"login":5,"displayName":5,"avatarUrl":6,"accountType":7,"accountTypeDesc":8,"profileDescription":9,"skillCount":10,"repoCount":11,"professionCount":12,"scenarioCount":13,"totalStars":11,"updatedAt":14,"htmlUrl":15,"blogUrl":16,"company":17,"location":17,"followersCount":18,"publicReposCount":13},"01M6C67T2SPVP033M7REAAHYHX","Allternit","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F250397232?v=4","ORGANIZATION","组织","Allternit builds AI agents that work on your computer, in the cloud, and from your phone. Home of Allternit Desktop and Gizzi Code.",122,1,11,7,"2026-11-12 03:40:39","https:\u002F\u002Fgithub.com\u002FAllternit","https:\u002F\u002Fallternit.com",null,2,{"records":20,"total":10,"current":11,"size":429},[21,52,71,94,118,148,181,206,231,262,268,288,295,301,321,332,365,391],{"skillNo":22,"name":23,"nameZh":17,"description":24,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":28,"categories":29,"keywords":30,"publishedAt":51},"01M6C6GBWRCJNWQP5S16PKXB77","jev","Ask typed System One judgments (noul \u002F choice \u002F score) against Allternit's LOCAL System One server instead of prompting a chat model to \"return JSON\". Use when classifying, routing, scoring, or screening something and code needs a probability it can branch on, or when the user runs \u002Fjev. Official TypeSafe Jev is an optional, explicit remote lane.","Allternit\u002Fallternit-platform","01M6C67T7CXM1DKVQY8DFAFRB2","Apache-2.0","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Ftools\u002Fsystem-one-local\u002Fskills\u002Fjev\u002FSKILL.md",[],[23,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"official","routing","code","server","lane","system","json","model","choice","branch","ask","user","use","scoring","chat","local","probability","remote","can","when","2026-11-10 10:12:30",{"skillNo":53,"name":54,"nameZh":17,"description":55,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":51},"01M6C6G9CGB9MX47NSQ31QNNB7","jev-route","Route with local System One answers — map Choice + confidence to act \u002F confirm \u002F human lanes, or pick a model tier by Choice label. Also documents the separate `route-model` helper for OpenRouter's typesafe\u002Fjev-router (a chat-model router, NOT System One). Use for confidence routing, model-tier routing, or when the user runs \u002Fjev-route.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Ftools\u002Fsystem-one-local\u002Fskills\u002Fjev-route\u002FSKILL.md",[],[23,59,60,61,32,36,38,62,39,63,42,43,64,65,45,66,46,67,68,69,70,50],"jev route","route","documents","pick","openrouter","router","model router","map","helper","with","for","model-tier",{"skillNo":72,"name":73,"nameZh":17,"description":74,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":51},"01M6C6G6JZE0RC50QWWE6HG320","jev-guardrail","Screen text or agent tool calls with a battery of local System One Noul hazards plus a Score, with policy in code — and the Claude Code PreToolUse guard (hooks\u002Fpretooluse-guard) that puts deterministic hard rules first and lets Jev only raise friction. Use for injection\u002Fsecret\u002Fdestructive-action screening or when the user runs \u002Fjev-guardrail.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Ftools\u002Fsystem-one-local\u002Fskills\u002Fjev-guardrail\u002FSKILL.md",[],[23,78,79,80,33,81,82,83,36,84,85,86,42,43,87,88,89,90,46,91,92,69,93,50],"jev guardrail","guardrail","policy","injection","first","guard","tool","text","Rules","friction","only","hooks","deterministic","battery","calls","agent tool",{"skillNo":95,"name":96,"nameZh":17,"description":97,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":98,"categories":99,"keywords":105,"publishedAt":51},"01M6C6G426P7Q5J3F98HVYDCB2","jev-fanout","Ask every independent System One question over the same state in ONE POST \u002Fv1\u002Fsystemone to the local server (speculative fan-out). Use for parallel judgments, compound commands, one-call turn assessment, or when the user runs \u002Fjev-fanout. Do not fire one HTTP call per question.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Ftools\u002Fsystem-one-local\u002Fskills\u002Fjev-fanout\u002FSKILL.md",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[23,106,107,108,109,110,34,36,111,41,112,42,43,113,114,46,115,116,69,117,50],"fanout","jev fanout","http","assessment","state","parallel","question","do","call","post","v1","local server",{"skillNo":119,"name":120,"nameZh":17,"description":121,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":51},"01M6C6G13D7JK869Q3DHMQ9542","memory-drive","Read and write the user's Allternit Memory Drive, a git repo of markdown memories in the open Agent Memory Repo format. Use at the start of a session to load what the user's agents remember (MEMORY.md), when the user says \"remember this\", when you learn a durable fact about the user or their work, and before answering questions that depend on past sessions.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Ftools\u002Fmemory-drive-plugin\u002Fskills\u002Fmemory-drive\u002FSKILL.md",[],[125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,42,141,43,142,143,144,145,146,147,50],"memory","drive","memory drive","sessions","remember","learn","git","agent memory","start","open","markdown","format","work","repo","read","write","session","what the","memories","about","questions","you","load",{"skillNo":149,"name":150,"nameZh":17,"description":151,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":51},"01M6C6FX778N1047QAJ39Y582H","agent-orchestrator","Orchestrate external CLI agents (kimi, codex, agy, claude, grok, gizzi) through the Allternit Factory (gizzi agents \u002F orchestration \u002F workspace \u002F workflows). Use when the user asks to delegate, offload, or farm out implementation work to another CLI agent \u002F terminal session, or to run work outside this session to save tokens. Part of Allternit Agents \u002F Bot Agents — not a separate product.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Ftools\u002Fagent-orchestrator\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000023","Skill与智能体开发",[158,159,160,161,162,163,164,165,166,167,168,169,170,137,171,172,141,43,173,174,175,176,177,178,179,180,50],"orchestrator","agent orchestrator","bot","cli","terminal","codex","orchestration","workflows","run","product","orchestrate","save","workspace","delegate","factory","grok","kimi","implementation","offload","tokens","cli agents","farm","terminal session",{"skillNo":182,"name":183,"nameZh":17,"description":184,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":185,"categories":186,"keywords":188,"publishedAt":51},"01M6C6FT301NEFTT5RSJK874N7","webobsidian","Read, write, search, and manage notes in a WebObsidian vault through its Agent REST API (\u002Fapi\u002Fv1). Use whenever the user asks to find, read, create, update, append to, or delete notes in their WebObsidian \u002F Obsidian vault, list tags, get backlinks, or run a vault search. Credentials (base URL + API key) are stored in ~\u002F.webobsidian\u002Fcredentials.json; if missing, ask the user for them and save them before making requests.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fservices\u002Fvault-viewer\u002Fdocs\u002Fagent-skill\u002Fwebobsidian\u002FSKILL.md",[187],{"categoryNo":155,"categoryName":156,"taxonomyType":103,"taxonomyTypeDesc":104},[183,189,190,191,192,166,193,194,195,196,197,198,169,199,37,200,41,139,140,201,202,43,203,204,205],"obsidian","notes","create","delete","update","search","REST","vault","credentials","api","obsidian vault","find","list","append","get","backlinks","URL",{"skillNo":207,"name":208,"nameZh":17,"description":209,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":210,"categories":211,"keywords":212,"publishedAt":51},"01M6C6FQEB1W6A3CWNYP5SW5MZ","add-provider","Add or extend an open-source OOMOL Connect provider under src\u002Fproviders\u002F\u003Cservice>, including provider definition, action schemas, local executors, credential validation, examples, and generated catalog updates.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fservices\u002Fopen-connector\u002F.codex\u002Fskills\u002Fadd-provider\u002FSKILL.md",[],[213,214,215,216,217,218,219,134,220,221,222,223,46,224,225,226,227,228,229,230],"add provider","provider","add","connect","validation","examples","Providers","src","generated","catalog","credential","service","open-source","action","updates","source","definition","extend",{"skillNo":232,"name":233,"nameZh":17,"description":234,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":235,"categories":236,"keywords":238,"publishedAt":51},"01M6C6FKVK1ECTJ5T9BKJ2SEZA","allternit-phones","Drive real phones, phone numbers and mailboxes through Allternit's MCP server. Use when the task is to operate an Android phone or iPhone (take a screenshot, tap, type, open an app, run a goal on the phone, replay a saved phone skill, run the same job on several phones), test a mobile app on a real device, give an agent its own phone number and mailbox, send or read an SMS, read a one-time code (OTP) or verification email, or share a live view link of a phone screen. Triggers on: phone, device, Android, iPhone, app on my phone, SMS, text message, OTP, verification code, 2FA code, agent number, agent mailbox, Allternit phones.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fplugins\u002Fallternit-phones\u002Fskills\u002Fallternit-phones\u002FSKILL.md",[237],{"categoryNo":155,"categoryName":156,"taxonomyType":103,"taxonomyTypeDesc":104},[239,240,241,242,243,166,33,244,245,34,246,134,85,139,247,43,248,249,250,251,252,253,254,255,256,257,258,259,260,261,50],"allternit phones","MCP","android","mcp server","test","share","verification","email","view","goal","mobile app","take","mobile","tap","message","time","iphone","app","otp","operate","number","take a screenshot","send",{"skillNo":263,"name":233,"nameZh":17,"description":234,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":264,"categories":265,"keywords":267,"publishedAt":51},"01M6C6FGMD5NFCPJM8AX1J6TTR","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fplugins\u002Fallternit-phones\u002Fcodex\u002Fallternit-phones\u002FSKILL.md",[266],{"categoryNo":155,"categoryName":156,"taxonomyType":103,"taxonomyTypeDesc":104},[239,240,241,242,243,166,33,244,245,34,246,134,85,139,247,43,248,249,250,251,252,253,254,255,256,257,258,259,260,261,50],{"skillNo":269,"name":270,"nameZh":17,"description":271,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":272,"categories":273,"keywords":274,"publishedAt":51},"01M6C6FDYTWQ5PHSF5TTCQ0R5G","ao","Control ao, the Allternit agent orchestrator (terminal workspace manager for AI coding agents). Use only when the user explicitly mentions ao or asks to use ao to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Ffactory\u002Fpane\u002Fskills\u002Fherdr\u002FSKILL.md",[],[270,162,275,276,277,278,279,280,111,170,137,42,281,158,43,159,88,282,283,113,284,285,286,287,69,50],"coding agents","ai coding agents","delegation","herdr","panes","coding","workspace manager","ai coding","workspaces","task","control","env","inspect",{"skillNo":289,"name":290,"nameZh":17,"description":17,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":291,"categories":292,"keywords":293,"publishedAt":51},"01M6C6FC3NGGMN8WGC8JR1Y4DX","_template","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fdomains\u002Fagent\u002Ftemplates\u002Fallternit_workspace\u002Flayer4_skills\u002F_template\u002FSKILL.md",[],[294],"template",{"skillNo":296,"name":297,"nameZh":17,"description":17,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":298,"categories":299,"keywords":300,"publishedAt":51},"01M6C6FAY4R7G6XSWXN550BAT5","github","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fdomains\u002Fagent\u002Fgizziclaw\u002Fsrc\u002Fskills\u002Fexamples\u002Fgithub\u002FSKILL.md",[],[297],{"skillNo":302,"name":303,"nameZh":17,"description":304,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":305,"licenseFileUrl":17,"sourceHtmlUrl":306,"categories":307,"keywords":311,"publishedAt":51},"01M6C6F93DQKRVVQQ4F2M7F877","Canvas","Canvas LMS integration for course management","MIT","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fdomains\u002Fagent\u002Fgizziclaw\u002Fsrc\u002Fskills\u002Fexamples\u002Fcanvas\u002FSKILL.md",[308],{"categoryNo":309,"categoryName":310,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000015","视觉设计",[312,313,198,314,201,315,316,203,317,318,319,69,320],"canvas","integration","team","management","canvas lms","courses","submit","course","lms",{"skillNo":322,"name":323,"nameZh":17,"description":324,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":305,"licenseFileUrl":17,"sourceHtmlUrl":325,"categories":326,"keywords":327,"publishedAt":51},"01M6C6F7EZA1BRQ41CT753R99Y","Apple Notes","Read and write Apple Notes","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fdomains\u002Fagent\u002Fgizziclaw\u002Fsrc\u002Fskills\u002Fexamples\u002Fapple-notes\u002FSKILL.md",[],[328,190,329,194,314,139,140,330,331],"apple notes","apple","script","apple-notes",{"skillNo":333,"name":334,"nameZh":17,"description":335,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":336,"categories":337,"keywords":343,"publishedAt":51},"01M6C6F4ABEG2DJM20ZNWV3JHV","cloudflare","Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fcmd\u002Fgizzi-code\u002Ftest\u002Ffixture\u002Fskills\u002Fcloudflare\u002FSKILL.md",[338],{"categoryNo":339,"categoryName":340,"taxonomyType":341,"taxonomyTypeDesc":342},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[334,344,345,346,347,348,349,33,350,351,352,353,354,43,355,356,357,358,359,360,361,362,69,363,364],"agents sdk","sdk","security","storage","infrastructure","development","networking","terraform","waf","infrastructure-as-code","ddos","workers","objects","platform","tunnel","as","infrastructure-as","pulumi","r2","d1","cloudflare development",{"skillNo":366,"name":367,"nameZh":17,"description":368,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":369,"categories":370,"keywords":375,"publishedAt":51},"01M6C6F1AV9JKS1W8WX9Y74GXP","agents-sdk","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fcmd\u002Fgizzi-code\u002Ftest\u002Ffixture\u002Fskills\u002Fagents-sdk\u002FSKILL.md",[371,374],{"categoryNo":372,"categoryName":373,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":155,"categoryName":156,"taxonomyType":103,"taxonomyTypeDesc":104},[344,345,240,376,165,377,378,379,110,380,334,381,313,382,383,384,315,89,385,355,254,386,387,388,147,389,390,50],"ai agents","react","tasks","state management","mcp servers","rpc","websocket","real-time","applications","cloudflare workers","apps","react hooks","scheduled","stateful","scheduled tasks",{"skillNo":392,"name":393,"nameZh":17,"description":394,"descriptionZh":17,"repositoryFullName":25,"ownerLogin":5,"ownerAvatarUrl":6,"ownerAccountNo":4,"ownerDisplayName":5,"repositoryNo":26,"starsCount":11,"licenseSpdxId":27,"licenseFileUrl":17,"sourceHtmlUrl":395,"categories":396,"keywords":401,"publishedAt":51},"01M6C6EXFQ8YE5VA3VPDQZM4G6","visual-design","Make web and app UI look deliberate and finished instead of templated. Covers choosing an aesthetic direction before writing code, type scale and font pairing, a spacing system, colour as tokens with dark mode, layout and hierarchy, detail density, imagery, empty\u002Floading\u002Ferror states, contrast, and phone-width layout, then a screenshot review loop (desktop + phone, light + dark) where you critique the render and fix the three worst problems. Use when building or redesigning a page, landing page, marketing site, dashboard, settings screen or component styling, or when asked to \"make it look better\", \"polish this\", \"make it premium\u002Fmodern\u002Fcleaner\", or \"it looks generic\". Respects an existing design system when the project has one.","https:\u002F\u002Fgithub.com\u002FAllternit\u002Fallternit-platform\u002Fblob\u002Fmain\u002Fcmd\u002Fgizzi-code\u002Fsrc\u002Fruntime\u002Fskills\u002Fbundled\u002Fcraft\u002Fvisual-design\u002FSKILL.md",[397,398],{"categoryNo":309,"categoryName":310,"taxonomyType":103,"taxonomyTypeDesc":104},{"categoryNo":399,"categoryName":400,"taxonomyType":341,"taxonomyTypeDesc":342},"01JBSEEDCAT000000000000032","设计师",[402,403,404,405,406,407,408,409,410,33,411,412,413,36,414,415,416,417,418,43,419,420,256,421,422,423,424,425,146,426,427,428,50],"design","visual design","visual","writing","review","dashboard","web","component","desktop","critique","loop","polish","site","page","settings","fix","landing","aesthetic","project","direction","error","render","states","loading","spacing system","mode","hierarchy",18]