[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CXZ9T2ABTZAKAC4S90CXKY":3,"skill-same:01M6CXZ9T2ABTZAKAC4S90CXKY":104},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6CXZ9T2ABTZAKAC4S90CXKY","oiloil-ui-ux-guide",null,"Modern, clean UI\u002FUX guidance + review skill. Use when you need actionable UX\u002FUI recommendations, design principles, or a design review checklist for new features or existing systems (web\u002Fapp). Focus on CRAP (Contrast\u002FRepetition\u002FAlignment\u002FProximity) plus task-first UX, information architecture, feedback & system status, consistency, affordances, error prevention\u002Frecovery, and cognitive load. Enforce a modern minimal style (clean, spacious, typography-led), reduce unnecessary copy, forbid emoji as icons, and recommend intuitive refined icons from a consistent icon set.","eric861129\u002FSKILLS_All-in-one","eric861129","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74950944?v=4","01M6CXHDYEYRPFGGV4EFXCSYCF","ChiYu-Huang","01M6CXHE2J5CN1EBTY0FKV3ZKW",52,"MIT","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"oiloil ui ux guide","ux","ui","guide","feedback","recommendations","focus","enforce","clean","design principles","alignment","typography","design","system","prevention","SET","review checklist","status","architecture","review","2026-11-10 10:12:30",false,"---\nname: oiloil-ui-ux-guide\ndescription: Modern, clean UI\u002FUX guidance + review skill. Use when you need actionable UX\u002FUI recommendations, design principles, or a design review checklist for new features or existing systems (web\u002Fapp). Focus on CRAP (Contrast\u002FRepetition\u002FAlignment\u002FProximity) plus task-first UX, information architecture, feedback & system status, consistency, affordances, error prevention\u002Frecovery, and cognitive load. Enforce a modern minimal style (clean, spacious, typography-led), reduce unnecessary copy, forbid emoji as icons, and recommend intuitive refined icons from a consistent icon set.\n---\n\n# OilOil UI\u002FUX Guide (Modern Minimal)\n\nUse this skill in two modes:\n\n- `guide`: Provide compact principles and concrete do\u002Fdon't rules for modern clean UI\u002FUX.\n- `review`: Review an existing UI (screenshot \u002F mock \u002F HTML \u002F PR) and output prioritized, actionable fixes.\n\nKeep outputs concise. Prefer bullets, not long paragraphs.\n\n## Workflow (pick one)\n\n### 1) `guide` workflow\n1. Identify the surface: marketing page \u002F dashboard \u002F settings \u002F creation flow \u002F list-detail \u002F form.\n2. Identify the primary user task and primary CTA.\n3. Apply the system-level guiding principles first (mental model and interaction logic).\n4. Then apply the core principles below (start from UX, then refine with CRAP).\n5. If icons are involved: apply `references\u002Ficons.md`.\n\n### 2) `review` workflow\n1. State assumptions (platform, target user, primary task).\n2. List findings as `P0\u002FP1\u002FP2` (blocker \u002F important \u002F polish) with short evidence.\n3. For each major issue, label the diagnosis: execution vs evaluation gulf; slip vs mistake (see `references\u002Fdesign-psych.md`).\n4. Propose fixes that are implementable (layout, hierarchy, components, copy, states).\n5. End with a short checklist to verify changes.\n\nUse `references\u002Freview-template.md` when you need a stable output format.\n\n## Non-negotiables (hard rules)\n- No emoji used as icons (or as UI decoration). If an emoji appears, replace it with a proper icon.\n- Icons must be intuitive and refined. Use a single consistent icon set for the product (avoid mixing styles).\n- Minimize copy by default. Add explanatory text only when it prevents errors, reduces ambiguity, or improves trust.\n\n## System-Level Guiding Principles\n\nApply these as first-order constraints before choosing components or page patterns.\nFull definitions and review questions: `references\u002Fsystem-principles.md`.\n\nKey principles: concept constancy · primary task focus · UI copy source discipline · state perceptibility · help text layering (L0–L3) · feedback loop closure · prevention + recoverability · progressive complexity · action perceptibility · cognitive load budget · evolution with semantic continuity.\n\n## Core Principles (minimal set)\n\n### A) Task-first UX\n- Make the primary task obvious in \u003C3 seconds.\n- Allow exactly one primary CTA per screen\u002Fsection.\n- Optimize the happy path; hide advanced controls behind progressive disclosure.\n\n### B) Information architecture (grouping & findability)\n- Group by user mental model (goal\u002Fobject\u002Ftime\u002Fstatus), not by backend fields.\n- Use clear section titles; keep navigation patterns stable across similar screens.\n- When item count grows: add search\u002Ffilter\u002Fsort early, not late.\n\n### C) Feedback & system status\n- Cover all states: loading, empty, error, success, permission. Details in `references\u002Fchecklists.md`.\n- After any action, answer: \"did it work?\" + \"what changed?\" + \"what can I do next?\"\n- Prefer inline, contextual feedback over global toasts (except for cross-page actions).\n\n### D) Consistency & predictability\n- Same interaction = same component + same wording + same placement.\n- Use a small, stable set of component variants; avoid one-off styles.\n\n### E) Affordance + Signifiers (make actions obvious)\n- Clickable things must look clickable (button\u002Flink styling + hover\u002Ffocus + cursor). On web, custom clickable elements need `cursor: pointer` and focus styles.\n- Primary actions need a label; icon-only is reserved for universally-known actions.\n- Show constraints before submit (format, units, required), not only after errors.\n- For deeper theory (affordances, signifiers, mapping, constraints): see `references\u002Fdesign-psych.md`.\n\n### F) Error prevention & recovery\n- Prevent errors with constraints, defaults, and inline validation.\n- Make destructive actions reversible when possible; otherwise require deliberate confirmation.\n- Error messages must be actionable (what happened + how to fix).\n\n### G) Cognitive load control\n- Reduce choices: sensible defaults, presets, and progressive disclosure.\n- Break long tasks into steps only when it reduces thinking (not just to look \"enterprise\").\n- Keep visual noise low: fewer borders, fewer colors, fewer competing highlights.\n\n### H) CRAP (visual hierarchy & layout)\n- Contrast: emphasize the few things that matter (CTA, current state, key numbers).\n- Repetition: tokens\u002Fcomponents\u002Fspacing follow a scale; avoid “almost the same” styles.\n- Alignment: align to a clear grid; fix 2px drift; align baselines where text matters.\n- Proximity: tight within a group, loose between groups; spacing is the primary grouping tool.\n\n## Spacing & layout discipline (compact rule set)\n\nUse this when implementing or reviewing layouts. Keep it short, but enforce it strictly.\n\n- Rule 1 - One spacing scale:\n  - Base unit: 4px.\n  - Allowed spacing set (recommended): 4 \u002F 8 \u002F 12 \u002F 16 \u002F 24 \u002F 32 \u002F 40 \u002F 48.\n  - New gaps\u002Fpadding should use this set; off-scale values need a clear reason.\n- Rule 2 - Repetition first:\n  - Same component type keeps the same internal spacing (cards, list rows, form groups, section blocks).\n  - Components with the same visual role should not have different spacing patterns.\n- Rule 3 - Alignment + grouping:\n  - Align to one grid and fix 1-2px drift.\n  - Tight spacing within a group, looser spacing between groups.\n- Rule 4 - No decorative nesting:\n  - Extra wrappers must add real function (grouping, state, scroll, affordance).\n  - If a wrapper only adds border\u002Fbackground, remove it and group with spacing instead.\n- Quick review pass:\n  - Any off-scale spacing values?\n  - Any baseline\u002Fedge misalignment?\n  - Any wrapper layer removable without losing meaning?\n\n## Modern minimal style guidance (taste with rules)\n- Use whitespace + typography to create hierarchy; avoid decoration-first design.\n- Prefer subtle surfaces (light elevation, low-contrast borders). Avoid heavy shadows.\n- Keep color palette small; use one accent color for primary actions and key states.\n- Copy: short, direct labels; add helper text only when it reduces mistakes or increases trust.\n\n## Motion (animation) guidance (content\u002Fcreator-friendly, not flashy)\n- Motion explains **hierarchy** (what is a layer\u002Fpanel) and **state change** (what just happened). Avoid motion as decoration.\n- Default motion vocabulary: fade; then small translate+fade; allow tiny scale+fade for overlays. Avoid big bouncy motion.\n- Keep the canvas\u002Fcontent area stable. Panels\u002Foverlays can move; the work surface should not “float.”\n- Prefer consistency over variety: same component type uses the same motion pattern.\n- Avoid layout jumps. Use placeholders\u002Fskeletons to keep layout stable while loading.\n\n## Anti-AI Self-Check (run after generating UI)\n\nBefore finalizing any generated UI, verify these items. Violating any one is a mandatory fix.\n\n- **Gradient restraint** — Gradients must convey meaning (progress, depth, state distinction). Purely decorative gradients: at most one per page. If background, buttons, and borders all use gradients simultaneously, that is overuse — pick one and flatten the rest.\n- **No emoji as UI** — Already a non-negotiable. Re-check: no emoji slipped in as section icons, status indicators, or button labels.\n- **Copy necessity** — For every piece of text, ask: if I remove this, can the user still understand through layout, icons, and position alone? If yes, remove it. Text is the last resort, not the default.\n- **Decoration justification** — Every purely visual effect (blur, glow, animated entrance, layered shadows) must answer: \"what does this help the user understand?\" No answer → remove.\n\n## References\n- System-level guiding principles (concept constancy, copy discipline, state perceptibility, etc.): `references\u002Fsystem-principles.md`\n- Interaction psychology (Fitts\u002FHick\u002FMiller, cognitive biases, flow, attention): `references\u002Finteraction-psychology.md`\n- Design psychology (affordances, signifiers, mapping, constraints, gulfs, slips vs mistakes): `references\u002Fdesign-psych.md`\n- Icon rules and \"intuitive refined\" guidance: `references\u002Ficons.md`\n- Review output template and scoring: `references\u002Freview-template.md`\n- Expanded checklists (states, affordance, lists, forms, settings, motion, dashboards, copy): `references\u002Fchecklists.md`\n","# OilOil UI\u002FUX Guide (Modern Minimal)\n\nUse this skill in two modes:\n\n- `guide`: Provide compact principles and concrete do\u002Fdon't rules for modern clean UI\u002FUX.\n- `review`: Review an existing UI (screenshot \u002F mock \u002F HTML \u002F PR) and output prioritized, actionable fixes.\n\nKeep outputs concise. Prefer bullets, not long paragraphs.\n\n## Workflow (pick one)\n\n### 1) `guide` workflow\n1. Identify the surface: marketing page \u002F dashboard \u002F settings \u002F creation flow \u002F list-detail \u002F form.\n2. Identify the primary user task and primary CTA.\n3. Apply the system-level guiding principles first (mental model and interaction logic).\n4. Then apply the core principles below (start from UX, then refine with CRAP).\n5. If icons are involved: apply `references\u002Ficons.md`.\n\n### 2) `review` workflow\n1. State assumptions (platform, target user, primary task).\n2. List findings as `P0\u002FP1\u002FP2` (blocker \u002F important \u002F polish) with short evidence.\n3. For each major issue, label the diagnosis: execution vs evaluation gulf; slip vs mistake (see `references\u002Fdesign-psych.md`).\n4. Propose fixes that are implementable (layout, hierarchy, components, copy, states).\n5. End with a short checklist to verify changes.\n\nUse `references\u002Freview-template.md` when you need a stable output format.\n\n## Non-negotiables (hard rules)\n- No emoji used as icons (or as UI decoration). If an emoji appears, replace it with a proper icon.\n- Icons must be intuitive and refined. Use a single consistent icon set for the product (avoid mixing styles).\n- Minimize copy by default. Add explanatory text only when it prevents errors, reduces ambiguity, or improves trust.\n\n## System-Level Guiding Principles\n\nApply these as first-order constraints before choosing components or page patterns.\nFull definitions and review questions: `references\u002Fsystem-principles.md`.\n\nKey principles: concept constancy · primary task focus · UI copy source discipline · state perceptibility · help text layering (L0–L3) · feedback loop closure · prevention + recoverability · progressive complexity · action perceptibility · cognitive load budget · evolution with semantic continuity.\n\n## Core Principles (minimal set)\n\n### A) Task-first UX\n- Make the primary task obvious in \u003C3 seconds.\n- Allow exactly one primary CTA per screen\u002Fsection.\n- Optimize the happy path; hide advanced controls behind progressive disclosure.\n\n### B) Information architecture (grouping & findability)\n- Group by user mental model (goal\u002Fobject\u002Ftime\u002Fstatus), not by backend fields.\n- Use clear section titles; keep navigation patterns stable across similar screens.\n- When item count grows: add search\u002Ffilter\u002Fsort early, not late.\n\n### C) Feedback & system status\n- Cover all states: loading, empty, error, success, permission. Details in `references\u002Fchecklists.md`.\n- After any action, answer: \"did it work?\" + \"what changed?\" + \"what can I do next?\"\n- Prefer inline, contextual feedback over global toasts (except for cross-page actions).\n\n### D) Consistency & predictability\n- Same interaction = same component + same wording + same placement.\n- Use a small, stable set of component variants; avoid one-off styles.\n\n### E) Affordance + Signifiers (make actions obvious)\n- Clickable things must look clickable (button\u002Flink styling + hover\u002Ffocus + cursor). On web, custom clickable elements need `cursor: pointer` and focus styles.\n- Primary actions need a label; icon-only is reserved for universally-known actions.\n- Show constraints before submit (format, units, required), not only after errors.\n- For deeper theory (affordances, signifiers, mapping, constraints): see `references\u002Fdesign-psych.md`.\n\n### F) Error prevention & recovery\n- Prevent errors with constraints, defaults, and inline validation.\n- Make destructive actions reversible when possible; otherwise require deliberate confirmation.\n- Error messages must be actionable (what happened + how to fix).\n\n### G) Cognitive load control\n- Reduce choices: sensible defaults, presets, and progressive disclosure.\n- Break long tasks into steps only when it reduces thinking (not just to look \"enterprise\").\n- Keep visual noise low: fewer borders, fewer colors, fewer competing highlights.\n\n### H) CRAP (visual hierarchy & layout)\n- Contrast: emphasize the few things that matter (CTA, current state, key numbers).\n- Repetition: tokens\u002Fcomponents\u002Fspacing follow a scale; avoid “almost the same” styles.\n- Alignment: align to a clear grid; fix 2px drift; align baselines where text matters.\n- Proximity: tight within a group, loose between groups; spacing is the primary grouping tool.\n\n## Spacing & layout discipline (compact rule set)\n\nUse this when implementing or reviewing layouts. Keep it short, but enforce it strictly.\n\n- Rule 1 - One spacing scale:\n  - Base unit: 4px.\n  - Allowed spacing set (recommended): 4 \u002F 8 \u002F 12 \u002F 16 \u002F 24 \u002F 32 \u002F 40 \u002F 48.\n  - New gaps\u002Fpadding should use this set; off-scale values need a clear reason.\n- Rule 2 - Repetition first:\n  - Same component type keeps the same internal spacing (cards, list rows, form groups, section blocks).\n  - Components with the same visual role should not have different spacing patterns.\n- Rule 3 - Alignment + grouping:\n  - Align to one grid and fix 1-2px drift.\n  - Tight spacing within a group, looser spacing between groups.\n- Rule 4 - No decorative nesting:\n  - Extra wrappers must add real function (grouping, state, scroll, affordance).\n  - If a wrapper only adds border\u002Fbackground, remove it and group with spacing instead.\n- Quick review pass:\n  - Any off-scale spacing values?\n  - Any baseline\u002Fedge misalignment?\n  - Any wrapper layer removable without losing meaning?\n\n## Modern minimal style guidance (taste with rules)\n- Use whitespace + typography to create hierarchy; avoid decoration-first design.\n- Prefer subtle surfaces (light elevation, low-contrast borders). Avoid heavy shadows.\n- Keep color palette small; use one accent color for primary actions and key states.\n- Copy: short, direct labels; add helper text only when it reduces mistakes or increases trust.\n\n## Motion (animation) guidance (content\u002Fcreator-friendly, not flashy)\n- Motion explains **hierarchy** (what is a layer\u002Fpanel) and **state change** (what just happened). Avoid motion as decoration.\n- Default motion vocabulary: fade; then small translate+fade; allow tiny scale+fade for overlays. Avoid big bouncy motion.\n- Keep the canvas\u002Fcontent area stable. Panels\u002Foverlays can move; the work surface should not “float.”\n- Prefer consistency over variety: same component type uses the same motion pattern.\n- Avoid layout jumps. Use placeholders\u002Fskeletons to keep layout stable while loading.\n\n## Anti-AI Self-Check (run after generating UI)\n\nBefore finalizing any generated UI, verify these items. Violating any one is a mandatory fix.\n\n- **Gradient restraint** — Gradients must convey meaning (progress, depth, state distinction). Purely decorative gradients: at most one per page. If background, buttons, and borders all use gradients simultaneously, that is overuse — pick one and flatten the rest.\n- **No emoji as UI** — Already a non-negotiable. Re-check: no emoji slipped in as section icons, status indicators, or button labels.\n- **Copy necessity** — For every piece of text, ask: if I remove this, can the user still understand through layout, icons, and position alone? If yes, remove it. Text is the last resort, not the default.\n- **Decoration justification** — Every purely visual effect (blur, glow, animated entrance, layered shadows) must answer: \"what does this help the user understand?\" No answer → remove.\n\n## References\n- System-level guiding principles (concept constancy, copy discipline, state perceptibility, etc.): `references\u002Fsystem-principles.md`\n- Interaction psychology (Fitts\u002FHick\u002FMiller, cognitive biases, flow, attention): `references\u002Finteraction-psychology.md`\n- Design psychology (affordances, signifiers, mapping, constraints, gulfs, slips vs mistakes): `references\u002Fdesign-psych.md`\n- Icon rules and \"intuitive refined\" guidance: `references\u002Ficons.md`\n- Review output template and scoring: `references\u002Freview-template.md`\n- Expanded checklists (states, affordance, lists, forms, settings, motion, dashboards, copy): `references\u002Fchecklists.md`\n",{"name":5,"description":7},"main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide",13,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one","http:\u002F\u002Fhuangchiyu.com\u002FSKILLS_All-in-one\u002F","https:\u002F\u002Fgithub.com\u002Feric861129","https:\u002F\u002Fhuangchiyu.com\u002FChiYu-Blog\u002F","開發工程師，專注於 C#／.NET 系統現代化、AI-assisted engineering、開源工具與技術寫作。","2026-04-16 14:28:14",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill oiloil-ui-ux-guide",{"tool":70,"command":71},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill oiloil-ui-ux-guide",{"tool":73,"command":74},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill oiloil-ui-ux-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002FSKILL.md",true,[78,84,88,92,96,100],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fchecklists.md","REFERENCE","参考文档",4638,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002Freferences\u002Fchecklists.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fdesign-psych.md",3716,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002Freferences\u002Fdesign-psych.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Ficons.md",1630,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002Freferences\u002Ficons.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Finteraction-psychology.md",7811,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002Freferences\u002Finteraction-psychology.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Freview-template.md",1855,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002Freferences\u002Freview-template.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fsystem-principles.md",5332,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FDevelopment & Code Tools\u002Foiloil-ui-ux-guide\u002Freferences\u002Fsystem-principles.md",[105,132,163,189,214,234],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":112,"publishedAt":49},"01M6CZ1WR3KNVTKSWH4GNWT646","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fwhat-if-oracle\u002FSKILL.md",[111],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[113,114,115,116,117,30,118,119,120,121,122,123,124,125,126,127,128,129,130,131],"oracle","what if oracle","go","run","planning","futures","risk","analysis","explore","decision","branch","question","read","write","idea","exploration","options","stress-test","strategies",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":148,"publishedAt":49},"01M6CZ1QHGJE91A95MSN5EK5Q9","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fvenue-templates\u002FSKILL.md",[138,141,144,145],{"categoryNo":139,"categoryName":140,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":142,"categoryName":143,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":146,"categoryName":147,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[149,150,151,152,153,154,155,156,157,158,125,126,159,160,161,162],"templates","venue templates","research","guidelines","NeurIPS","ICML","LaTeX","science","Bash","access","edit","proposals","Academic","requirements",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":173,"publishedAt":49},"01M6CZ1KBQD2E5RTFB3BGVX7CD","the-fool","Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fthe-fool\u002FSKILL.md",[169,170],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":171,"categoryName":172,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[174,48,115,175,47,116,176,177,178,179,180,181,182,183,160,184,185,186,187,188],"the fool","workflow","code","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","expert","poke","ideas",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":198,"publishedAt":49},"01M6CZ1ES826S7P1X3333E40TA","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-writing\u002FSKILL.md",[195,196,197],{"categoryNo":139,"categoryName":140,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":146,"categoryName":147,"taxonomyType":26,"taxonomyTypeDesc":27},[199,200,152,201,202,203,204,205,157,206,125,126,159,207,208,209,210,211,212,213],"writing","scientific writing","core","reporting","deep research","Citations","Outlines","tool","use","never","structure","deep","full","stage","prisma",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":221,"publishedAt":49},"01M6CZ1B2JGJTB9FRD0TW4RXXE","scientific-brainstorming","Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-brainstorming\u002FSKILL.md",[220],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[222,223,151,224,117,225,226,227,207,228,229,230,128,231,232,212,233],"brainstorming","scientific brainstorming","sessions","data","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":246,"publishedAt":49},"01M6CZ16JG8N7A2ZX04BGE8J2Y","research-lookup","Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fresearch-lookup\u002FSKILL.md",[240,243,244,245],{"categoryNo":241,"categoryName":242,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":142,"categoryName":143,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":171,"categoryName":172,"taxonomyType":26,"taxonomyTypeDesc":27},[151,247,248,249,225,250,251,157,252,253,125,126,159,207,254,255,256,257,258,161],"lookup","research lookup","search","perplexity","api","parallel","openrouter","backend","up","look","queries","chat"]