[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JZM3EBPSD3HCCM23W3NR7":3,"skill-same:01M71JZM3EBPSD3HCCM23W3NR7":83},{"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":59,"commitSha":60,"skillDirectory":61,"forksCount":62,"repositoryHtmlUrl":63,"repositoryHomepageUrl":64,"ownerHtmlUrl":65,"ownerBlogUrl":66,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M71JZM3EBPSD3HCCM23W3NR7","ultra-think",null,"Use when facing architectural decisions, complex trade-offs, strategic technology choices, or scaling and migration questions that deserve more than a quick answer. Lays out options with trade-offs, then a recommendation.","coco-research\u002Fcoco","coco-research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F68911604?v=4","01M71JRE9C4NM4NSZM4JD0BJTB","Coco Research","01M71JREA0ZMR0PMH3CKA99SN1",631,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fultra-think\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},"01JBSEEDCAT000000000000030","开发工程师","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],"ultra think","think","ultra","strategic","when","generic","trade-offs","more","answer","quick","with","codex","recommendation","scaling","trade","technology","options","use","decisions","code","2026-11-10 10:12:30",false,"---\nname: ultra-think\ndescription: \"Use when facing architectural decisions, complex trade-offs, strategic technology choices, or scaling and migration questions that deserve more than a quick answer. Lays out options with trade-offs, then a recommendation.\"\ndomain: foundational\nsupports: [claude-code, cursor, codex, generic]\nversion: 0.1.0\n---\n\n# Ultra Think — Deep Analysis Mode\n\nDeep, multi-dimensional analysis and problem solving. Activates systematic reasoning across technical, business, user, and system perspectives. Generates multiple solutions with trade-offs, then synthesizes into a clear recommendation.\n\n**Use when**: facing architectural decisions, complex trade-offs, strategic technology choices, system design problems, scaling challenges, migration decisions, or any question that deserves more than a quick answer. Attach this skill when you want rigorous, first-principles thinking.\n\n---\n\n## When This Skill Is Activated\n\nDo NOT jump to a solution. Follow every step below in order. Think deeply at each stage before moving on.\n\n---\n\n## Step 1: Parse the Problem\n\nBefore analyzing, make sure you understand what's actually being asked.\n\n- Extract the core challenge from the user's message\n- Identify all stakeholders and constraints (stated and implied)\n- Surface hidden complexities and implicit requirements\n- Question assumptions — what is the user taking for granted?\n- Name the unknowns explicitly\n\n---\n\n## Step 2: Multi-Dimensional Analysis\n\nAnalyze the problem from four perspectives. Do not skip any.\n\n### Technical Perspective\n- Feasibility and constraints\n- Scalability, performance, maintainability\n- Security implications\n- Technical debt and future-proofing\n- Integration complexity\n\n### Business Perspective\n- Business value and ROI\n- Time-to-market pressure\n- Competitive advantage\n- Risk vs. reward trade-offs\n- Cost (development, operational, opportunity)\n\n### User Perspective\n- User needs and pain points\n- Usability and accessibility\n- Edge cases and failure states from the user's point of view\n- User journeys affected\n\n### System Perspective\n- System-wide impacts and ripple effects\n- Integration points and coupling\n- Dependencies (upstream and downstream)\n- Emergent behaviors and unintended interactions\n\n---\n\n## Step 3: Generate Multiple Solutions\n\nBrainstorm **at least 3 distinct approaches** — not variations of the same idea.\n\nFor each approach, evaluate:\n- Pros and cons\n- Implementation complexity (T-shirt size: S\u002FM\u002FL\u002FXL)\n- Resource requirements (people, time, money)\n- Key risks\n- Long-term implications (what does this look like in 2 years?)\n\nInclude at least one unconventional or creative solution. Consider hybrid approaches that combine strengths of different options.\n\n---\n\n## Step 4: Deep Dive on Top Candidates\n\nFor the 1–2 most promising solutions:\n\n- Sketch a detailed implementation plan (phases, milestones)\n- Identify pitfalls and mitigation strategies\n- Consider a phased approach or MVP path\n- Analyze **second-order effects** — what changes because of this change?\n- Think through failure modes — what happens when this breaks?\n- Estimate reversibility — how hard is it to undo if wrong?\n\n---\n\n## Step 5: Cross-Domain Thinking\n\nLook beyond the immediate domain for insight:\n\n- Are there parallels from other industries? (e.g., how did logistics solve this? Healthcare? Finance?)\n- Do design patterns from other contexts apply? (e.g., circuit breakers from electrical engineering → software resilience)\n- Are there natural system analogies? (e.g., biological redundancy, evolutionary pressure)\n- Can existing solutions be combined in a novel way?\n\n---\n\n## Step 6: Challenge and Stress-Test\n\nPlay devil's advocate against every solution, including the one you favor.\n\n- What's the strongest argument against each option?\n- What blind spots might you have?\n- Run \"what if\" scenarios (what if traffic is 10x? what if the team halves? what if requirements change?)\n- Stress-test assumptions — which ones, if wrong, would invalidate the whole approach?\n- Look for unintended consequences\n\n---\n\n## Step 7: Synthesize and Recommend\n\nCombine all insights into a structured deliverable. Use this exact format:\n\n```\n## Problem Analysis\n- **Core challenge**: [one sentence]\n- **Key constraints**: [list]\n- **Critical success factors**: [what must be true for any solution to work]\n- **Assumptions**: [what we're taking as given]\n\n## Solution Options\n\n### Option 1: [Name]\n- **Description**: [2-3 sentences]\n- **Pros**: [list]\n- **Cons**: [list]\n- **Complexity**: [S\u002FM\u002FL\u002FXL]\n- **Risk level**: [Low\u002FMedium\u002FHigh]\n- **Best when**: [conditions that make this the right choice]\n\n### Option 2: [Name]\n[Same structure]\n\n### Option 3: [Name]\n[Same structure]\n\n## Recommendation\n- **Recommended approach**: [which option and why]\n- **Rationale**: [the decisive factors]\n- **Implementation roadmap**: [phases with rough timelines]\n- **Success metrics**: [how we'll know it's working]\n- **Risk mitigation**: [top 3 risks and their mitigations]\n- **Reversibility**: [how hard to undo if wrong]\n\n## Contrarian View\n- **The case against this recommendation**: [strongest counterargument]\n- **What would change our mind**: [signals that we chose wrong]\n- **Areas of uncertainty**: [what we don't know yet]\n\n## Confidence Assessment\n- **Overall confidence**: [High\u002FMedium\u002FLow] — [why]\n- **What would increase confidence**: [additional research, prototyping, data needed]\n```\n\n---\n\n## Step 8: Meta-Reflection\n\nEnd with a brief reflection:\n\n- Where is the analysis weakest?\n- What biases might be influencing the recommendation?\n- What additional expertise or data would improve the analysis?\n- What's the one thing most likely to be wrong?\n\n---\n\n## Thinking Principles\n\nApply these mental models throughout the analysis:\n\n| Principle | Application |\n|-----------|-------------|\n| **First Principles** | Break down to fundamental truths, don't reason by analogy alone |\n| **Systems Thinking** | Consider interconnections, feedback loops, emergent behavior |\n| **Probabilistic Thinking** | Work with ranges and likelihoods, not certainties |\n| **Inversion** | Ask \"what should we avoid?\" not just \"what should we do?\" |\n| **Second-Order Effects** | Consider the consequences of consequences |\n| **Reversibility** | Prefer reversible decisions; be extra careful with irreversible ones |\n| **Occam's Razor** | Among equally valid solutions, prefer the simpler one |\n\n---\n\n## Output Expectations\n\n- Comprehensive analysis (typically 2–4 pages of insight)\n- Multiple viable solutions with honest trade-offs\n- Clear reasoning chains — show your work\n- Explicit acknowledgment of uncertainties\n- Actionable recommendation with next steps\n- At least one novel insight or non-obvious perspective\n","# Ultra Think — Deep Analysis Mode\n\nDeep, multi-dimensional analysis and problem solving. Activates systematic reasoning across technical, business, user, and system perspectives. Generates multiple solutions with trade-offs, then synthesizes into a clear recommendation.\n\n**Use when**: facing architectural decisions, complex trade-offs, strategic technology choices, system design problems, scaling challenges, migration decisions, or any question that deserves more than a quick answer. Attach this skill when you want rigorous, first-principles thinking.\n\n---\n\n## When This Skill Is Activated\n\nDo NOT jump to a solution. Follow every step below in order. Think deeply at each stage before moving on.\n\n---\n\n## Step 1: Parse the Problem\n\nBefore analyzing, make sure you understand what's actually being asked.\n\n- Extract the core challenge from the user's message\n- Identify all stakeholders and constraints (stated and implied)\n- Surface hidden complexities and implicit requirements\n- Question assumptions — what is the user taking for granted?\n- Name the unknowns explicitly\n\n---\n\n## Step 2: Multi-Dimensional Analysis\n\nAnalyze the problem from four perspectives. Do not skip any.\n\n### Technical Perspective\n- Feasibility and constraints\n- Scalability, performance, maintainability\n- Security implications\n- Technical debt and future-proofing\n- Integration complexity\n\n### Business Perspective\n- Business value and ROI\n- Time-to-market pressure\n- Competitive advantage\n- Risk vs. reward trade-offs\n- Cost (development, operational, opportunity)\n\n### User Perspective\n- User needs and pain points\n- Usability and accessibility\n- Edge cases and failure states from the user's point of view\n- User journeys affected\n\n### System Perspective\n- System-wide impacts and ripple effects\n- Integration points and coupling\n- Dependencies (upstream and downstream)\n- Emergent behaviors and unintended interactions\n\n---\n\n## Step 3: Generate Multiple Solutions\n\nBrainstorm **at least 3 distinct approaches** — not variations of the same idea.\n\nFor each approach, evaluate:\n- Pros and cons\n- Implementation complexity (T-shirt size: S\u002FM\u002FL\u002FXL)\n- Resource requirements (people, time, money)\n- Key risks\n- Long-term implications (what does this look like in 2 years?)\n\nInclude at least one unconventional or creative solution. Consider hybrid approaches that combine strengths of different options.\n\n---\n\n## Step 4: Deep Dive on Top Candidates\n\nFor the 1–2 most promising solutions:\n\n- Sketch a detailed implementation plan (phases, milestones)\n- Identify pitfalls and mitigation strategies\n- Consider a phased approach or MVP path\n- Analyze **second-order effects** — what changes because of this change?\n- Think through failure modes — what happens when this breaks?\n- Estimate reversibility — how hard is it to undo if wrong?\n\n---\n\n## Step 5: Cross-Domain Thinking\n\nLook beyond the immediate domain for insight:\n\n- Are there parallels from other industries? (e.g., how did logistics solve this? Healthcare? Finance?)\n- Do design patterns from other contexts apply? (e.g., circuit breakers from electrical engineering → software resilience)\n- Are there natural system analogies? (e.g., biological redundancy, evolutionary pressure)\n- Can existing solutions be combined in a novel way?\n\n---\n\n## Step 6: Challenge and Stress-Test\n\nPlay devil's advocate against every solution, including the one you favor.\n\n- What's the strongest argument against each option?\n- What blind spots might you have?\n- Run \"what if\" scenarios (what if traffic is 10x? what if the team halves? what if requirements change?)\n- Stress-test assumptions — which ones, if wrong, would invalidate the whole approach?\n- Look for unintended consequences\n\n---\n\n## Step 7: Synthesize and Recommend\n\nCombine all insights into a structured deliverable. Use this exact format:\n\n```\n## Problem Analysis\n- **Core challenge**: [one sentence]\n- **Key constraints**: [list]\n- **Critical success factors**: [what must be true for any solution to work]\n- **Assumptions**: [what we're taking as given]\n\n## Solution Options\n\n### Option 1: [Name]\n- **Description**: [2-3 sentences]\n- **Pros**: [list]\n- **Cons**: [list]\n- **Complexity**: [S\u002FM\u002FL\u002FXL]\n- **Risk level**: [Low\u002FMedium\u002FHigh]\n- **Best when**: [conditions that make this the right choice]\n\n### Option 2: [Name]\n[Same structure]\n\n### Option 3: [Name]\n[Same structure]\n\n## Recommendation\n- **Recommended approach**: [which option and why]\n- **Rationale**: [the decisive factors]\n- **Implementation roadmap**: [phases with rough timelines]\n- **Success metrics**: [how we'll know it's working]\n- **Risk mitigation**: [top 3 risks and their mitigations]\n- **Reversibility**: [how hard to undo if wrong]\n\n## Contrarian View\n- **The case against this recommendation**: [strongest counterargument]\n- **What would change our mind**: [signals that we chose wrong]\n- **Areas of uncertainty**: [what we don't know yet]\n\n## Confidence Assessment\n- **Overall confidence**: [High\u002FMedium\u002FLow] — [why]\n- **What would increase confidence**: [additional research, prototyping, data needed]\n```\n\n---\n\n## Step 8: Meta-Reflection\n\nEnd with a brief reflection:\n\n- Where is the analysis weakest?\n- What biases might be influencing the recommendation?\n- What additional expertise or data would improve the analysis?\n- What's the one thing most likely to be wrong?\n\n---\n\n## Thinking Principles\n\nApply these mental models throughout the analysis:\n\n| Principle | Application |\n|-----------|-------------|\n| **First Principles** | Break down to fundamental truths, don't reason by analogy alone |\n| **Systems Thinking** | Consider interconnections, feedback loops, emergent behavior |\n| **Probabilistic Thinking** | Work with ranges and likelihoods, not certainties |\n| **Inversion** | Ask \"what should we avoid?\" not just \"what should we do?\" |\n| **Second-Order Effects** | Consider the consequences of consequences |\n| **Reversibility** | Prefer reversible decisions; be extra careful with irreversible ones |\n| **Occam's Razor** | Among equally valid solutions, prefer the simpler one |\n\n---\n\n## Output Expectations\n\n- Comprehensive analysis (typically 2–4 pages of insight)\n- Multiple viable solutions with honest trade-offs\n- Clear reasoning chains — show your work\n- Explicit acknowledgment of uncertainties\n- Actionable recommendation with next steps\n- At least one novel insight or non-obvious perspective\n",{"name":5,"domain":54,"version":55,"supports":56,"description":7},"foundational","0.1.0",[57,58,40,34],"claude-code","cursor","main","cd89f013b617f7eea982a9bbc60e992974fda2aa","skills\u002Fultra-think",15,"https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco","https:\u002F\u002Fcocoresearch.org\u002Fcoco\u002F","https:\u002F\u002Fgithub.com\u002Fcoco-research","https:\u002F\u002Fcocoresearch.org","Local-first, open-source tools for people who work with AI agents: governed memory, agents that check their own work, and data that stays on your machine.","2026-11-11 12:18:13",{"source":8,"skillName":5,"commands":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add coco-research\u002Fcoco --skill ultra-think",{"tool":75,"command":76},"bunx","bunx skills add coco-research\u002Fcoco --skill ultra-think",{"tool":78,"command":79},"pnpm","pnpm dlx skills add coco-research\u002Fcoco --skill ultra-think","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fskills\u002Fultra-think\u002FSKILL.md",true,[],[84,109,119,135,170,189],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":91,"publishedAt":49},"01M71KEJXF9KMT0BWCMRSRFA4M","trading-super-intelligence","Trading Super Intelligence Team. Named real-world personas across 8 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Ftrading\u002FSKILL.md",[90],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"super","trading super intelligence","intelligence","trading","validator","personas","local","composites","studio","team","across","world","first","gated","2026","lm studio","local-first",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":116,"publishedAt":49},"01M71KEFWS3CMAP7DF1P0FWTDE","strategy-super-intelligence","Strategy Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fstrategy\u002FSKILL.md",[115],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[117,92,118,94,96,97,98,99,100,101,102,103,104,105,106,107,108],"strategy","strategy super intelligence",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":129,"publishedAt":49},"01M71KED56ZEPK2QE84QSQPMT0","risk-compliance-super-intelligence","Risk & Compliance (GRC) Super Intelligence Team. Named real-world personas across 7 cells. Built local-first (LM Studio) and validator-gated. Illustrative composites; see DISCLAIMER.md.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Frisk-compliance\u002FSKILL.md",[125,126],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":127,"categoryName":128,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000037","律师与法务",[130,92,131,132,133,94,96,97,98,99,134,100,101,102,103,104,105,106,107,108],"risk","risk compliance super intelligence","compliance","risk compliance","grc",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":154,"publishedAt":49},"01M71KE9A2FWSC74VA96W1EZSN","product-design-super-intelligence","Your product + design brain trust and decision partner. Named personas across 8 cells spanning product strategy, discovery\u002Fresearch, growth\u002Fmetrics, design foundations\u002Fusability, design leadership\u002Fcraft, UX\u002Fcontent, design systems, and a…","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fproduct-design\u002FSKILL.md",[141,144,147,148,151],{"categoryNo":142,"categoryName":143,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":149,"categoryName":150,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理",{"categoryNo":152,"categoryName":153,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师",[155,156,94,157,92,158,159,160,161,162,163,101,102,164,165,106,166,167,168,169],"design","product","product design","product design super intelligence","foundations","product-design","decision","design systems","usability","leadership","ux","brain","craft","metrics","trust",{"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":178,"publishedAt":49},"01M71KE6H9FPSD9TECYFBPXZ8Y","legal-ip-super-intelligence","Your legal, IP, and regulatory brain trust. 31 named personas across 7 cells covering patent strategy, tech licensing, regulatory litigation, AI governance, open-source compliance, privacy law, and antitrust.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Flegal-ip\u002FSKILL.md",[176,177],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":127,"categoryName":128,"taxonomyType":26,"taxonomyTypeDesc":27},[179,92,180,94,181,182,169,183,97,184,185,186,117,101,102,187,132,188,106,166],"ip","legal ip super intelligence","legal","sep","tech","litigation","ai governance","open","open-source","governance",{"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":196,"publishedAt":49},"01M71KE36QRY610V6YVB9JWRND","healthcare-life-sciences-super-intelligence","Your healthcare and life sciences brain trust. 25 named personas across 7 cells covering drug discovery, medtech, biotech strategy, health policy, genomics, clinical trials, and healthcare economics.","https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco\u002Fblob\u002Fmain\u002Fsystems\u002Fsuperintelligence\u002Fhealthcare-life-sciences\u002FSKILL.md",[195],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[197,92,198,199,94,182,169,200,201,97,202,203,117,101,102,204,205,206,207,106],"healthcare","healthcare life sciences super intelligence","life","economics","discovery","policy","clinical","clinical trials","health","trials","genomics"]