[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBGVT2CFZNEMJSBXWYX751":3,"skill-same:01M7EBGVT2CFZNEMJSBXWYX751":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EBGVT2CFZNEMJSBXWYX751","research-problem-scout",null,"Use at the beginning of scientific idea discovery to find real, important, falsifiable research failures from actual sources; reject weak motivations before architectures and novelty-hunting. Includes low-cost problem-evidence scouting and a hard Motivation-First Gate.","zms618\u002Fno-heartburn-academic-skills","zms618","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F105599679?v=4","01M7EBA1W5DCCS8A3KMY0A0R28","Cheng He","01M7EBA1XAKYE8NVWVS162527D",0,"MIT","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-problem-scout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: research-problem-scout\ndescription: Use at the beginning of scientific idea discovery to find real, important, falsifiable research failures from actual sources; reject weak motivations before architectures and novelty-hunting. Includes low-cost problem-evidence scouting and a hard Motivation-First Gate.\n---\n\n## v3.4 portfolio discovery extension\n\nFor `CVPR_BEST_PAPER_ASPIRATION` or multi-motivation discovery, call `research-motivation-portfolio` first. Build a broad, source-grounded **portfolio of different questions** (default 5–8 honest motives) then explain why 2–3 have more important, defensible shortcomings, and research nearest prior work for every shortlist member. Only after this can you turn a surviving motivation into a technical Idea. See `..\u002Fresearch-idea-discovery\u002Freferences\u002Fmotivation-portfolio-and-cvpr.md`. A strong single-problem analysis alone is not a completed portfolio-first discovery.\n\n# Research Problem Scout — 先找真问题，再考虑 Idea\n\nRead `..\u002Fresearch-idea-discovery\u002Freferences\u002Fmotivation-first-gate.md`, `..\u002Fresearch-idea-discovery\u002Freferences\u002Fmotivation-and-story-protocol.md`, and `..\u002Fresearch-idea-discovery\u002Freferences\u002Fsearch-connectors.md`.\n\nPerform bounded, neutral reading of actual benchmarks, strongest simple baselines, counterexamples, negative results and matched-condition comparisons. Produce up to three **problem cards**, not method proposals. Seek adverse data as actively as supportive data. Cite each Table\u002FFigure\u002Fsetting or prove evidence is unavailable. Never claim the root cause was discovered from one comparison.\n\nRank by **problem evidence quality and scientific importance**, NOT how easily three innovations can be invented. Explicitly test the null explanation: “Would fair tuning, a different metric or a matched backbone make this disappear?” Check dataset and regime scope to avoid overgeneralizing from one condition. This cheap scan may precede resource-intensive dataset feasibility; do not impose downstream G0 before deciding which problem merits further work.\n\nFor each problem call the structural `scripts\u002Fmotivation_gate.py` when local commands are available, but also critically read its sources. The script cannot independently verify citations or scientific importance. Output PASS_FOR_IDEATION \u002F PROBE_ONLY \u002F REJECT_OR_REFRAME \u002F RESEARCH_MORE; only PASS may trigger the Hypothesis Lab to generate IDEA_SEED and the costly D0\u002FG0\u002FN\u002FL\u002FM2\u002Fmethod design workflow. For PROBE_ONLY, offer one bounded fairness\u002Freplication check and a stop condition, with no method architecture. If all fail, report why and one targeted neutral Deep Research prompt. Label any role-playing review `ROLE_SIMULATED`.\n\n## v3.5 paper-anchored probe\nUse `research-paper-anchor-scout` for quick-start research: ask counterfactual questions at each real Figure\u002FTable, replicate failures, investigate why successful methods work, and reconcile paper disagreements fairly. All still require M0; manuscript limitations or a method's popularity alone are not established failures.\n","## v3.4 portfolio discovery extension\n\nFor `CVPR_BEST_PAPER_ASPIRATION` or multi-motivation discovery, call `research-motivation-portfolio` first. Build a broad, source-grounded **portfolio of different questions** (default 5–8 honest motives) then explain why 2–3 have more important, defensible shortcomings, and research nearest prior work for every shortlist member. Only after this can you turn a surviving motivation into a technical Idea. See `..\u002Fresearch-idea-discovery\u002Freferences\u002Fmotivation-portfolio-and-cvpr.md`. A strong single-problem analysis alone is not a completed portfolio-first discovery.\n\n# Research Problem Scout — 先找真问题，再考虑 Idea\n\nRead `..\u002Fresearch-idea-discovery\u002Freferences\u002Fmotivation-first-gate.md`, `..\u002Fresearch-idea-discovery\u002Freferences\u002Fmotivation-and-story-protocol.md`, and `..\u002Fresearch-idea-discovery\u002Freferences\u002Fsearch-connectors.md`.\n\nPerform bounded, neutral reading of actual benchmarks, strongest simple baselines, counterexamples, negative results and matched-condition comparisons. Produce up to three **problem cards**, not method proposals. Seek adverse data as actively as supportive data. Cite each Table\u002FFigure\u002Fsetting or prove evidence is unavailable. Never claim the root cause was discovered from one comparison.\n\nRank by **problem evidence quality and scientific importance**, NOT how easily three innovations can be invented. Explicitly test the null explanation: “Would fair tuning, a different metric or a matched backbone make this disappear?” Check dataset and regime scope to avoid overgeneralizing from one condition. This cheap scan may precede resource-intensive dataset feasibility; do not impose downstream G0 before deciding which problem merits further work.\n\nFor each problem call the structural `scripts\u002Fmotivation_gate.py` when local commands are available, but also critically read its sources. The script cannot independently verify citations or scientific importance. Output PASS_FOR_IDEATION \u002F PROBE_ONLY \u002F REJECT_OR_REFRAME \u002F RESEARCH_MORE; only PASS may trigger the Hypothesis Lab to generate IDEA_SEED and the costly D0\u002FG0\u002FN\u002FL\u002FM2\u002Fmethod design workflow. For PROBE_ONLY, offer one bounded fairness\u002Freplication check and a stop condition, with no method architecture. If all fail, report why and one targeted neutral Deep Research prompt. Label any role-playing review `ROLE_SIMULATED`.\n\n## v3.5 paper-anchored probe\nUse `research-paper-anchor-scout` for quick-start research: ask counterfactual questions at each real Figure\u002FTable, replicate failures, investigate why successful methods work, and reconcile paper disagreements fairly. All still require M0; manuscript limitations or a method's popularity alone are not established failures.\n",{"name":5,"description":7},"main","e6390f546a3cc4731cf8bd03a19a20ca8334553b","skills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-problem-scout","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills","https:\u002F\u002Fgithub.com\u002Fzms618","https:\u002F\u002Fzms618.github.io\u002F","M.S. Student @ Fuzhou University | Computational Pathology & Medical Vision","2026-10-13 13:38:55",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add zms618\u002Fno-heartburn-academic-skills --skill research-problem-scout",{"tool":38,"command":39},"bunx","bunx skills add zms618\u002Fno-heartburn-academic-skills --skill research-problem-scout",{"tool":41,"command":42},"pnpm","pnpm dlx skills add zms618\u002Fno-heartburn-academic-skills --skill research-problem-scout","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-problem-scout\u002FSKILL.md",true,[],[47,53,59,66,73,80],{"skillNo":48,"name":49,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7EBH8ZAKH92EA8GG2A4Z8B4","research-review-board","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-review-board\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7EBH5BYYHV4EVM1YDP0JXWW","research-proposal-generator","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-proposal-generator\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7EBH1PX2Q7R48QY45Q94D3T","research-problem-validation","Validate research problems before generating ideas.","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-problem-validation\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7EBGQ1WQ7ZQ8DCDYXVBT1W9","research-pilot-designer","Use when user requests falsification pilot experiment design hypothesis testing research planning. Works within the general Research Idea Discovery plugin and any user-selected field.","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-pilot-designer\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7EBGH5KFCBRGNQXS0TYHXE4","research-paper-anchor-scout","Critically read a small adversarial group of anchor papers to discover real, falsifiable research problems from failures, successful-method mechanisms, contradictions and deployment assumptions; reuse verified assets without blindly modifying the previous network.","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-paper-anchor-scout\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7EBGCDZ32S1M34HJGXH42RA","research-novelty-auditor","Use when user requests prior art novelty scooping collision auditing scientific research papers. Works within the general Research Idea Discovery plugin and any user-selected field.","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-novelty-auditor\u002FSKILL.md",[],[]]