[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DDHSNVYAF3A2F9R4GQDFG2":3,"skill-same:01M7DDHSNVYAF3A2F9R4GQDFG2":86},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":70,"ownerHtmlUrl":71,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":72,"install":73,"resources":85},"01M7DDHSNVYAF3A2F9R4GQDFG2","research-decision-room",null,"Turn messy user research notes, interviews, support tickets, surveys, and product\ncontext into an evidence-backed decision room: a single HTML artifact with an\nevidence ledger, theme map, confidence heatmap, opportunity matrix, decision\nmemo, and experiment queue. Use when teams need to move from qualitative\nsignals to product or design decisions without fabricating certainty.","feimacode\u002Fopen-design-agent-kit","feimacode","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F264390570?v=4","01M7D3HQSP5EP4Z4JECTSQ7EBD","Feima Code","01M7D3HQT72Q4EVQJP89MR9WP1",1129,"MIT","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fresearch-decision-room\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: research-decision-room\ndescription: |\n  Turn messy user research notes, interviews, support tickets, surveys, and product\n  context into an evidence-backed decision room: a single HTML artifact with an\n  evidence ledger, theme map, confidence heatmap, opportunity matrix, decision\n  memo, and experiment queue. Use when teams need to move from qualitative\n  signals to product or design decisions without fabricating certainty.\ntriggers:\n  - \"research decision room\"\n  - \"user research synthesis\"\n  - \"research synthesis dashboard\"\n  - \"evidence-backed product decision\"\n  - \"interview synthesis\"\n  - \"opportunity solution tree\"\n  - \"usability findings dashboard\"\n  - \"qualitative research board\"\nod:\n  mode: prototype\n  platform: desktop\n  scenario: research\n  preview:\n    type: html\n    entry: index.html\n    reload: debounce-100\n  design_system:\n    requires: true\n    sections: [color, typography, layout, components]\n  craft:\n    requires: [typography, color, accessibility-baseline, anti-ai-slop]\n  inputs:\n    - name: research_material\n      type: string\n      required: true\n      description: \"Interview notes, tickets, survey excerpts, analytics notes, or a product decision brief\"\n    - name: decision_scope\n      type: string\n      required: false\n      description: \"The product\u002Fdesign decision the team needs to make\"\n  outputs:\n    primary: index.html\n  example_prompt: \"Synthesize 8 interview notes, 24 support tickets, and recent activation metrics into a research decision room for whether a project-management app should add an onboarding checklist or contextual inline tips.\"\n  capabilities_required:\n    - file_write\n---\n\n# Research Decision Room Skill\n\nCreate a single-page HTML decision artifact that helps a product or design team\nturn messy evidence into a clear next move. The output is not a decorative\nresearch deck. It is a working room for debate: evidence, themes, confidence,\ntradeoffs, and recommended experiments stay visible together.\n\n## Resource map\n\n```text\nresearch-decision-room\u002F\n├── SKILL.md\n├── example.html\n└── references\u002F\n    ├── checklist.md\n    └── evidence-model.md\n```\n\nRead `references\u002Fevidence-model.md` before synthesis and run\n`references\u002Fchecklist.md` before emitting the artifact.\n\n## When to use this skill\n\nUse this skill when the user has any mix of:\n\n- Interview notes, usability-test observations, support tickets, sales call notes,\n  app-store reviews, NPS comments, survey open text, analytics snippets, or\n  product-decision context.\n- A decision that needs evidence: \"Should we build X?\", \"Which onboarding path\n  should we try?\", \"Why are users dropping off?\", \"What do customers actually\n  mean by slow?\"\n- A need to share findings with stakeholders who will not read a long research\n  report.\n\nDo not use it for pure visual inspiration, campaign ideation, or brand moodboards.\n\n## Workflow\n\n### Step 1 - Establish the decision frame\n\nIdentify the decision scope from the user's prompt. If the user did not give a\ndecision, derive one from the evidence and label it as inferred.\n\nWrite a short frame with:\n\n- Decision question.\n- Audience or segment.\n- Time horizon.\n- Known constraints.\n- What this artifact will not decide.\n\nIf key context is missing and the task is not blocked, proceed with labelled\nassumptions instead of asking a broad question.\n\n### Step 2 - Build the evidence ledger\n\nNormalize every useful signal into ledger rows using the model in\n`references\u002Fevidence-model.md`.\n\nEach ledger row must include:\n\n- `id`: short stable id, such as `I-03`, `T-14`, `M-02`.\n- `source_type`: interview, usability, support, survey, analytics, sales, field\n  note, or stakeholder.\n- `segment`: user type or \"unknown\".\n- `signal`: one-sentence observation.\n- `quote_or_metric`: direct quote, metric, or \"not provided\".\n- `strength`: strong, medium, or weak.\n- `limitations`: why this evidence may be biased or incomplete.\n\nNever invent quotes, participant counts, dates, revenue impact, or metrics. If\nthe user did not provide a number, use \"not provided\" and explain what evidence\nwould increase confidence.\n\n### Step 3 - Synthesize themes and tensions\n\nCluster evidence into 4 to 6 themes. For each theme:\n\n- Name the theme in plain human language.\n- List the evidence ids that support it.\n- Explain the behavior behind it, not just the UI complaint.\n- Mark confidence as high, medium, or low.\n- Note contradictions or segment differences.\n\nPrefer verbs over nouns: \"Teams abandon setup when the first blank state asks\nfor too much\" is better than \"Onboarding problem\".\n\n### Step 4 - Score opportunities\n\nCreate an opportunity matrix with 3 to 5 options. Score each option on a 1 to 5\nscale:\n\n- Evidence strength.\n- User pain.\n- Business leverage.\n- Implementation risk, where 5 means low risk and 1 means high risk.\n\nShow the total score, but do not let the score replace judgment. Add one sentence\non why the top recommendation wins.\n\n### Step 5 - Draft the decision memo\n\nWrite a decision memo with:\n\n1. Recommended move.\n2. Why now.\n3. What evidence supports it.\n4. What could be wrong.\n5. What to measure next.\n6. Reversible next step.\n\nKeep the memo short enough to read in under one minute.\n\n### Step 6 - Create the HTML artifact\n\nProduce a self-contained `index.html`. Use the active `DESIGN.md` for typography,\nspacing, color roles, and component tone, but keep the information architecture\nstable:\n\n1. Header with decision question, confidence, and last-updated label.\n2. Executive readout with recommendation, risk, and next experiment.\n3. Evidence ledger with filter chips.\n4. Theme map with evidence ids and confidence.\n5. Opportunity matrix.\n6. Decision memo.\n7. Experiment queue with owner, metric, and success threshold.\n8. Assumptions and limitations.\n\nThe artifact should be interactive but durable. Simple vanilla JavaScript is\nallowed for filtering evidence, switching views, or highlighting related ids.\nNo framework dependency is required.\n\n### Step 7 - Self-check and emit\n\nRun the checklist. Then emit one concise orientation sentence and one HTML\nartifact:\n\n```xml\n\u003Cartifact identifier=\"research-decision-room\" type=\"text\u002Fhtml\" title=\"Research Decision Room\">\n\u003C!doctype html>\n\u003Chtml>...\u003C\u002Fhtml>\n\u003C\u002Fartifact>\n```\n\nNothing after the closing `\u003C\u002Fartifact>`.\n","# Research Decision Room Skill\n\nCreate a single-page HTML decision artifact that helps a product or design team\nturn messy evidence into a clear next move. The output is not a decorative\nresearch deck. It is a working room for debate: evidence, themes, confidence,\ntradeoffs, and recommended experiments stay visible together.\n\n## Resource map\n\n```text\nresearch-decision-room\u002F\n├── SKILL.md\n├── example.html\n└── references\u002F\n    ├── checklist.md\n    └── evidence-model.md\n```\n\nRead `references\u002Fevidence-model.md` before synthesis and run\n`references\u002Fchecklist.md` before emitting the artifact.\n\n## When to use this skill\n\nUse this skill when the user has any mix of:\n\n- Interview notes, usability-test observations, support tickets, sales call notes,\n  app-store reviews, NPS comments, survey open text, analytics snippets, or\n  product-decision context.\n- A decision that needs evidence: \"Should we build X?\", \"Which onboarding path\n  should we try?\", \"Why are users dropping off?\", \"What do customers actually\n  mean by slow?\"\n- A need to share findings with stakeholders who will not read a long research\n  report.\n\nDo not use it for pure visual inspiration, campaign ideation, or brand moodboards.\n\n## Workflow\n\n### Step 1 - Establish the decision frame\n\nIdentify the decision scope from the user's prompt. If the user did not give a\ndecision, derive one from the evidence and label it as inferred.\n\nWrite a short frame with:\n\n- Decision question.\n- Audience or segment.\n- Time horizon.\n- Known constraints.\n- What this artifact will not decide.\n\nIf key context is missing and the task is not blocked, proceed with labelled\nassumptions instead of asking a broad question.\n\n### Step 2 - Build the evidence ledger\n\nNormalize every useful signal into ledger rows using the model in\n`references\u002Fevidence-model.md`.\n\nEach ledger row must include:\n\n- `id`: short stable id, such as `I-03`, `T-14`, `M-02`.\n- `source_type`: interview, usability, support, survey, analytics, sales, field\n  note, or stakeholder.\n- `segment`: user type or \"unknown\".\n- `signal`: one-sentence observation.\n- `quote_or_metric`: direct quote, metric, or \"not provided\".\n- `strength`: strong, medium, or weak.\n- `limitations`: why this evidence may be biased or incomplete.\n\nNever invent quotes, participant counts, dates, revenue impact, or metrics. If\nthe user did not provide a number, use \"not provided\" and explain what evidence\nwould increase confidence.\n\n### Step 3 - Synthesize themes and tensions\n\nCluster evidence into 4 to 6 themes. For each theme:\n\n- Name the theme in plain human language.\n- List the evidence ids that support it.\n- Explain the behavior behind it, not just the UI complaint.\n- Mark confidence as high, medium, or low.\n- Note contradictions or segment differences.\n\nPrefer verbs over nouns: \"Teams abandon setup when the first blank state asks\nfor too much\" is better than \"Onboarding problem\".\n\n### Step 4 - Score opportunities\n\nCreate an opportunity matrix with 3 to 5 options. Score each option on a 1 to 5\nscale:\n\n- Evidence strength.\n- User pain.\n- Business leverage.\n- Implementation risk, where 5 means low risk and 1 means high risk.\n\nShow the total score, but do not let the score replace judgment. Add one sentence\non why the top recommendation wins.\n\n### Step 5 - Draft the decision memo\n\nWrite a decision memo with:\n\n1. Recommended move.\n2. Why now.\n3. What evidence supports it.\n4. What could be wrong.\n5. What to measure next.\n6. Reversible next step.\n\nKeep the memo short enough to read in under one minute.\n\n### Step 6 - Create the HTML artifact\n\nProduce a self-contained `index.html`. Use the active `DESIGN.md` for typography,\nspacing, color roles, and component tone, but keep the information architecture\nstable:\n\n1. Header with decision question, confidence, and last-updated label.\n2. Executive readout with recommendation, risk, and next experiment.\n3. Evidence ledger with filter chips.\n4. Theme map with evidence ids and confidence.\n5. Opportunity matrix.\n6. Decision memo.\n7. Experiment queue with owner, metric, and success threshold.\n8. Assumptions and limitations.\n\nThe artifact should be interactive but durable. Simple vanilla JavaScript is\nallowed for filtering evidence, switching views, or highlighting related ids.\nNo framework dependency is required.\n\n### Step 7 - Self-check and emit\n\nRun the checklist. Then emit one concise orientation sentence and one HTML\nartifact:\n\n```xml\n\u003Cartifact identifier=\"research-decision-room\" type=\"text\u002Fhtml\" title=\"Research Decision Room\">\n\u003C!doctype html>\n\u003Chtml>...\u003C\u002Fhtml>\n\u003C\u002Fartifact>\n```\n\nNothing after the closing `\u003C\u002Fartifact>`.\n",{"od":24,"name":5,"triggers":55,"description":64},{"mode":25,"craft":26,"inputs":32,"outputs":41,"preview":43,"platform":46,"scenario":47,"design_system":48,"example_prompt":52,"capabilities_required":53},"prototype",{"requires":27},[28,29,30,31],"typography","color","accessibility-baseline","anti-ai-slop",[33,38],{"name":34,"type":35,"required":36,"description":37},"research_material","string",true,"Interview notes, tickets, survey excerpts, analytics notes, or a product decision brief",{"name":39,"type":35,"required":20,"description":40},"decision_scope","The product\u002Fdesign decision the team needs to make",{"primary":42},"index.html",{"type":44,"entry":42,"reload":45},"html","debounce-100","desktop","research",{"requires":36,"sections":49},[29,28,50,51],"layout","components","Synthesize 8 interview notes, 24 support tickets, and recent activation metrics into a research decision room for whether a project-management app should add an onboarding checklist or contextual inline tips.",[54],"file_write",[56,57,58,59,60,61,62,63],"research decision room","user research synthesis","research synthesis dashboard","evidence-backed product decision","interview synthesis","opportunity solution tree","usability findings dashboard","qualitative research board","Turn messy user research notes, interviews, support tickets, surveys, and product\ncontext into an evidence-backed decision room: a single HTML artifact with an\nevidence ledger, theme map, confidence heatmap, opportunity matrix, decision\nmemo, and experiment queue. Use when teams need to move from qualitative\nsignals to product or design decisions without fabricating certainty.\n","main","e38061066b92c298798dbddc1decbae8c026464f","packages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fresearch-decision-room",104,"https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit","https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=feima.open-design-agent-kit","https:\u002F\u002Fgithub.com\u002Ffeimacode","2026-11-14 17:32:48",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":36},[75,78,81],{"tool":76,"command":77},"npx","npx skills add feimacode\u002Fopen-design-agent-kit --skill research-decision-room",{"tool":79,"command":80},"bunx","bunx skills add feimacode\u002Fopen-design-agent-kit --skill research-decision-room",{"tool":82,"command":83},"pnpm","pnpm dlx skills add feimacode\u002Fopen-design-agent-kit --skill research-decision-room","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fresearch-decision-room\u002FSKILL.md",[],[87,94,101,108,115,122],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7DDR9C4RR6E8F46YBJ8MW64","youtube-clipper","YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7DDR57XHXAFBGKX3SYTGSJB","writing-guidelines","Review docs\u002Fprose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fwriting-guidelines\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7DDR2RM4F3FM5642JZBGJSF","wpds","WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fwpds\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7DDQX3G9QDCBV5GGZGQ1NZN","weread-year-in-review-video-template","WeRead-inspired HyperFrames video template for vertical annual reading reports,\npersonal reading dashboards, book-note recaps, and shareable year-in-review\nstories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper\ntexture, editorial Chinese typography, book-page metaphors, data highlights,\nand deterministic motion.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fweread-year-in-review-video-template\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7DDQRGJEHQST6TXDH6ZAV5G","web-design-guidelines","Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M7DDQKADVPZW1Z1HTVKXY542","web-clone","网站复刻 \u002F 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互\u002FWebGL\u002FCanvas\u002FThree.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 \u002F React-Vue-Next 内容站 \u002F WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fweb-clone\u002FSKILL.md",[],[]]