[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BY9GNVBPFHMVFRDKY02JSX":3,"skill-same:01M7BY9GNVBPFHMVFRDKY02JSX":43},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M7BY9GNVBPFHMVFRDKY02JSX","gk-base-critique-affordance",null,"Critique a screen's interactive affordances — what looks clickable, state visibility, CTA clarity, and action discoverability.","makeyzhang-cpu\u002Fgeekclaw","makeyzhang-cpu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F282184316?v=4","01M7BY92NE8R5TAVDAV2CTBGHV","01M7BY92P6TYAA1XX1E7XCX7GS",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fcrates\u002Fbackend\u002Fnomifun-app\u002Fassets\u002Fbuiltin-skills\u002Fgk-base-critique-affordance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gk-base-critique-affordance\ndescription: \"Critique a screen's interactive affordances — what looks clickable, state visibility, CTA clarity, and action discoverability.\"\n---\n\n# critique-affordance\n\n# Critique Affordance\nYou are an expert in interaction design and the visual communication of interactivity.\n## What You Do\nYou analyse a screen to identify whether interactive elements are visually distinguishable, whether states are communicated clearly, and whether the primary action is obvious. You flag affordance failures and propose specific fixes.\n## Critique Dimensions\n### Clickability Signals\nEvaluate whether interactive elements look interactive.\n- Do buttons, links, and controls look distinct from static content through colour, shape, underline, or elevation?\n- Are there elements that look interactive but are not (false affordances)?\n- Are there elements that are interactive but look static (missing affordances)?\n- Is the interactive area large enough — touch targets should be at least 44×44px on mobile.\n### State Visibility\nEvaluate whether element states are visually communicated.\n- Are default, hover, active, focus, disabled, and selected states visually distinct?\n- Is the focus state visible and high-contrast (not just the browser default ring on a coloured background)?\n- Are loading and skeleton states present where async content is expected?\n- Are disabled states clearly communicated without relying on colour alone?\n### CTA Clarity\nEvaluate whether the primary action on screen is immediately obvious.\n- Is there a single dominant CTA per view, or are multiple actions competing at the same visual weight?\n- Does the primary CTA use filled\u002Fsolid style while secondary actions use ghost or text variants?\n- Is the CTA label specific and action-oriented (\"Save changes\", not \"OK\")?\n- Is the CTA positioned where users expect it — bottom-right on forms, inline after content blocks?\n### Action Discoverability\nEvaluate whether all available actions can be found without instruction.\n- Are actions hidden behind hover states or tooltips that mobile users can't access?\n- Are contextual actions (edit, delete, share) visible or indicated — not completely hidden until hover?\n- Are empty states actionable — do they tell the user what to do next?\n- Are destructive actions (delete, remove) visually distinguished from constructive ones?\n## Output Format\nFor each dimension — Clickability Signals, State Visibility, CTA Clarity, Action Discoverability — provide:\n1. **Observation** — what you see (neutral, factual)\n2. **Problem** — what is broken and why it matters\n3. **Fix** — a specific, actionable change\nRate each dimension: `pass` \u002F `minor issue` \u002F `major issue`.\n## Common Failure Patterns\n- Ghost buttons in low-contrast contexts where the border becomes invisible\n- Focus rings suppressed with `outline: none` and no replacement state\n- Multiple filled CTAs on one screen, leaving users unsure which to press\n- Edit and delete actions hidden behind hover — inaccessible on touch and invisible until discovered by accident\n- Empty states that explain nothing and offer no path forward\n","# critique-affordance\n\n# Critique Affordance\nYou are an expert in interaction design and the visual communication of interactivity.\n## What You Do\nYou analyse a screen to identify whether interactive elements are visually distinguishable, whether states are communicated clearly, and whether the primary action is obvious. You flag affordance failures and propose specific fixes.\n## Critique Dimensions\n### Clickability Signals\nEvaluate whether interactive elements look interactive.\n- Do buttons, links, and controls look distinct from static content through colour, shape, underline, or elevation?\n- Are there elements that look interactive but are not (false affordances)?\n- Are there elements that are interactive but look static (missing affordances)?\n- Is the interactive area large enough — touch targets should be at least 44×44px on mobile.\n### State Visibility\nEvaluate whether element states are visually communicated.\n- Are default, hover, active, focus, disabled, and selected states visually distinct?\n- Is the focus state visible and high-contrast (not just the browser default ring on a coloured background)?\n- Are loading and skeleton states present where async content is expected?\n- Are disabled states clearly communicated without relying on colour alone?\n### CTA Clarity\nEvaluate whether the primary action on screen is immediately obvious.\n- Is there a single dominant CTA per view, or are multiple actions competing at the same visual weight?\n- Does the primary CTA use filled\u002Fsolid style while secondary actions use ghost or text variants?\n- Is the CTA label specific and action-oriented (\"Save changes\", not \"OK\")?\n- Is the CTA positioned where users expect it — bottom-right on forms, inline after content blocks?\n### Action Discoverability\nEvaluate whether all available actions can be found without instruction.\n- Are actions hidden behind hover states or tooltips that mobile users can't access?\n- Are contextual actions (edit, delete, share) visible or indicated — not completely hidden until hover?\n- Are empty states actionable — do they tell the user what to do next?\n- Are destructive actions (delete, remove) visually distinguished from constructive ones?\n## Output Format\nFor each dimension — Clickability Signals, State Visibility, CTA Clarity, Action Discoverability — provide:\n1. **Observation** — what you see (neutral, factual)\n2. **Problem** — what is broken and why it matters\n3. **Fix** — a specific, actionable change\nRate each dimension: `pass` \u002F `minor issue` \u002F `major issue`.\n## Common Failure Patterns\n- Ghost buttons in low-contrast contexts where the border becomes invisible\n- Focus rings suppressed with `outline: none` and no replacement state\n- Multiple filled CTAs on one screen, leaving users unsure which to press\n- Edit and delete actions hidden behind hover — inaccessible on touch and invisible until discovered by accident\n- Empty states that explain nothing and offer no path forward\n",{"name":5,"description":7},"main","1f321f8966b6741235f35f79c97c0ffdcffb11ba","crates\u002Fbackend\u002Fnomifun-app\u002Fassets\u002Fbuiltin-skills\u002Fgk-base-critique-affordance","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu","2026-11-08 16:23:21",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add makeyzhang-cpu\u002Fgeekclaw --skill gk-base-critique-affordance",{"tool":35,"command":36},"bunx","bunx skills add makeyzhang-cpu\u002Fgeekclaw --skill gk-base-critique-affordance",{"tool":38,"command":39},"pnpm","pnpm dlx skills add makeyzhang-cpu\u002Fgeekclaw --skill gk-base-critique-affordance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fcrates\u002Fbackend\u002Fnomifun-app\u002Fassets\u002Fbuiltin-skills\u002Fgk-base-critique-affordance\u002FSKILL.md",true,[],[44,51,58,65,72,79],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":48,"categories":49,"keywords":50,"publishedAt":18},"01M7BYJ19XV75TDGRGXBFJN1T4","drive-geekclaw","Use to connect to and drive a GeekClaw instance from an external agent (Claude Code \u002F Cursor \u002F any MCP client). Drive its browser \u002F computer \u002F knowledge base \u002F files and manage the platform over MCP or REST, with a per-companion access token (you run AS the bound companion). Use this whenever the user asks to control, automate, or hand work off to \"GeekClaw\", \"their GeekClaw\", \"the desktop companion\", or a running GeekClaw server.","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fdocs\u002Fskills\u002Fdrive-nomifun\u002FSKILL.md",[],[],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M7BYHZBZNHHBX8M87JZ6Y031","example-skill","Fixture skill used by startup_materialize integration tests.","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fcrates\u002Fbackend\u002Fnomifun-extension\u002Ftests\u002Ffixtures\u002Fbuiltin-skills-fixture\u002Fexample-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7BYHWFXC17GE9SXDK1X3GTD","ui-ux-pro-max","Professional UI\u002FUX design research skill with a bundled searchable database for product patterns, visual styles, color palettes, typography, landing-page structure, dashboard charts, UX practices, and stack guidance. Use when designing, building, reviewing, or improving interfaces.","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fcrates\u002Fbackend\u002Fnomifun-app\u002Fassets\u002Fbuiltin-skills\u002Fui-ux-pro-max\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7BYHR24XK92Z2YYQHK2732Y","planning-with-files","Maintain durable task plans, findings, and progress logs in workspace files for long-running or research-heavy work. Use when a task spans many steps or sessions, needs an auditable evidence trail, or risks losing important decisions to context limits. Do not use for short tasks that fit comfortably in the active conversation.","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fcrates\u002Fbackend\u002Fnomifun-app\u002Fassets\u002Fbuiltin-skills\u002Fplanning-with-files\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7BYHKQ6A4CNTQB0JXRJ5AXX","officecli","Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fcrates\u002Fbackend\u002Fnomifun-app\u002Fassets\u002Fbuiltin-skills\u002Fofficecli\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7BYHD30974T2E9FBTJZN3R2","officecli-xlsx","Use this skill any time a .xlsx file is involved -- as input, output, or both. This includes: creating spreadsheets, financial models, dashboards, or trackers; reading, parsing, or extracting data from any .xlsx file; editing, modifying, or updating existing workbooks; working with formulas, charts, pivot tables, or templates; importing CSV\u002FTSV data into Excel format. Trigger whenever the user mentions 'spreadsheet', 'workbook', 'Excel', 'financial model', 'tracker', 'dashboard', or references a .xlsx\u002F.csv filename.","https:\u002F\u002Fgithub.com\u002Fmakeyzhang-cpu\u002Fgeekclaw\u002Fblob\u002Fmain\u002Fcrates\u002Fbackend\u002Fnomifun-app\u002Fassets\u002Fbuiltin-skills\u002Fofficecli-xlsx\u002FSKILL.md",[],[]]