[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EBAV7MWGDDCNTKRTJQCT0N":3,"skill-same:01M7EBAV7MWGDDCNTKRTJQCT0N":68},{"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},"01M7EBAV7MWGDDCNTKRTJQCT0N","figure-designer",null,"Advises on the design of the three core figures in a technical paper: the Motivated Example (Figure 1), the Solution Overview (Methodology), and the Experimental Results figures. Recommends the right design paradigm, layout, labelling, and tool for each figure type, then runs a quality-control audit. Use when the user asks to 'design a figure', 'draw Figure 1', 'plot experiment results', 'choose the right chart type', 'which figure tool to use', or 'figure looks unprofessional'.","zms618\u002Fno-heartburn-academic-skills","zms618","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F105599679?v=4","01M7EBA1W5DCCS8A3KMY0A0R28","Cheng He","01M7EBA1XAKYE8NVWVS162527D",0,"CC-BY-4.0","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fai-mentor\u002Fskills\u002Ffigure-designer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: figure-designer\ndescription: >-\n  Advises on the design of the three core figures in a technical paper:\n  the Motivated Example (Figure 1), the Solution Overview\n  (Methodology), and the Experimental Results figures. Recommends the\n  right design paradigm, layout, labelling, and tool for each figure\n  type, then runs a quality-control audit. Use when the user asks to\n  'design a figure', 'draw Figure 1', 'plot experiment results',\n  'choose the right chart type', 'which figure tool to use', or\n  'figure looks unprofessional'.\nlicense: CC-BY-4.0\n---\n\n# Figure Designer\n\n## Overview\n\nA top-venue paper typically carries six to eight figures, with three\ncarrying almost all the storytelling weight: the Motivated Example\n(Figure 1, on page 1 or the top of page 2), the Solution Overview\n(inside the Methodology section), and the Experimental Results\nfigures (inside the Experiments section). Reviewers scan these three\nin under a minute to decide whether the paper is worth reading in\ndetail; weak figures sink otherwise-strong papers.\n\nThis skill takes the user's intent (what they want to communicate)\nplus context (research area, method name, target venue) and returns\nthe recommended paradigm, a layout sketch, labelling guidance,\ntool suggestion, and a quality-control audit against a universal\nrule set (vector format, font size, colour-blind-safe encoding,\nself-contained caption, honest axis ranges).\n\n## When to use this skill\n\n- Before drawing any figure in a paper.\n- The user asks to 'design a figure', 'draw Figure 1', 'plot\n  experiment results', 'choose the right chart type'.\n- The user has drawn a figure and wants a design audit.\n- The user is unsure which figure type or paradigm to choose.\n- Preparing camera-ready figures before submission.\n\n## When NOT to use this skill\n\n- The user only wants generic plotting help (bar chart, line chart)\n  outside a paper. Regular assistance suffices.\n- The paper is not yet structured; use `intro-drafter` or\n  `tech-paper-template` first to decide what figures the paper\n  needs.\n- The user wants a review of an already-finished paper. Use\n  `pre-submission-reviewer`.\n\n## Core procedure\n\n### Step 1: Figure-type identification\n\nDecide which of the three core types the figure is. If the user's\nrequest does not match any, either it is a supporting figure (use\nthe experimental-results guidance as a base) or it does not belong\nin the paper.\n\nIf the mode is `figure-audit` and the user has provided an image\npath, load the image with the Read tool **before** proceeding to\nStep 2. Vision-based inspection enables the universal rule audit\nin Step 6 to check font legibility, colour palette, raster-vs-\nvector tells, and chartjunk directly rather than relying on user\ndescription. If no image is provided, continue in text-only mode\nand mark vision-only rules (font size, raster detection, colour\npalette) as \"user must verify\" in the final audit report.\n\n### Step 2: Paradigm recommendation\n\nSee: references\u002Fmotivated-example.md, references\u002Fsolution-overview.md,\nor references\u002Fexperimental-results.md depending on figure type.\n\nEach figure type has two to three canonical paradigms. Pick the one\nthat fits the user's storytelling need, and explain why the other\nparadigms fit less well.\n\n### Step 3: Layout sketch\n\nProduce a text description of the layout: panel positions, element\nplacement, arrows, colour assignments. The goal is that the user\ncould draw the first draft from the sketch alone.\n\n### Step 4: Labelling and annotation guidance\n\n- Name every visible element concretely (no \"Module A\", \"X\", \"Y\").\n- Annotate critical points (failure highlight, success highlight,\n  comparison emphasis).\n- Specify font sizes and colour palette. Default colour palette:\n  ColorBrewer Qualitative or Viridis for sequential.\n\n### Step 5: Tool suggestion\n\nSee: references\u002Ftools.md for the tool matrix and the decision\nheuristic.\n\nDefault recommendations:\n\n- Motivated Example and Solution Overview: PowerPoint (draft),\n  Figma (polish).\n- Experimental Results: Matplotlib or Seaborn in a reusable\n  `plot_utils.py` script.\n- LaTeX-integrated figures: TikZ or PGFPlots.\n\n### Step 6: Universal rule audit\n\nSee: references\u002Fdesign-rules.md for the full universal rule set.\n\nVerify every proposed or existing figure against:\n\n- Vector format (PDF, EPS, SVG) for export.\n- Font size at least 8pt post-scaling.\n- Small canvas (not large canvas with small fonts).\n- Colour-blind-safe palette; no colour-only encoding.\n- Self-contained caption whose first sentence states the core\n  finding.\n- Honest axis ranges.\n- No 3D effects, no chartjunk.\n\nFlag every violation with severity.\n\n### Step 7: Integrity gate\n\nRun the checks in the Integrity gate section below.\n\n### Step 8: Output\n\nEmit the full design in the Output format below.\n\n## Integrity gate\n\nBullets tagged [inspection] are checked by the LLM from its own\noutput. Bullets tagged [user-verify] require the user to confirm\nbecause the check depends on either the drawn figure or knowledge\nthe skill does not have (paper context, prior Introduction).\n\nBefore returning the design:\n\n1. **[inspection]** Paradigm matches figure type (motivated example\n   is not a pipeline; overview is not a bar chart).\n2. **[inspection]** Layout sketch is concrete enough that the user\n   could draw from it.\n3. **[inspection]** Labels are real entity names, not placeholders.\n4. **[inspection]** Tool suggestion matches the figure's complexity\n   (not Matplotlib for a multi-icon motivated example, not\n   PowerPoint for a 20-method bar chart).\n5. **[inspection] when image provided, [user-verify] text-only**\n   Universal rule audit has been run; no CRITICAL violation is\n   left unaddressed. Vision-only rules (raster-vs-vector, font\n   size, colour palette) are only checkable when the user supplies\n   an image.\n6. **[user-verify]** For motivated examples, the example is the\n   same running example referenced by the Introduction (no new\n   example introduced in Figure 1). The skill does not see the\n   Introduction; the user confirms.\n7. **[inspection]** For experimental results, the chart type\n   matches the data type (time-series uses line, multi-method\n   comparison uses grouped bar, trade-off uses scatter).\n\nIf any [inspection] check fails, mark the design as \"needs user\nattention\". For [user-verify] items, surface them to the user as\nitems they must confirm before submission.\n\n## Output format\n\n### 1. Figure type\n- Type: \u003Cmotivated-example or solution-overview or experimental-results>\n- Reason: \u003Cone sentence>\n\n### 2. Paradigm recommendation\n- Paradigm: \u003Cname>\n- Why this paradigm: \u003Crationale>\n- Alternatives considered and rejected: \u003Clist>\n\n### 3. Layout sketch\n- Canvas: \u003Csize>\n- Panels: \u003Clist with positions and contents>\n- Arrows and connections: \u003Clist>\n- Colour assignment: \u003Cmapping>\n\n### 4. Labelling and annotations\n- Element names: \u003Clist>\n- Critical highlights: \u003Clist>\n- Font sizes: \u003Ctarget>\n- Colour palette: \u003Cname>\n\n### 5. Tool suggestion\n- Primary: \u003Ctool>\n- Alternative: \u003Ctool>\n- Reason: \u003Crationale>\n\n### 6. Universal rule audit\n- [ ] Vector format: \u003Cpass or fail>\n- [ ] Font size: \u003Cpass or fail>\n- [ ] Colour-blind safe: \u003Cpass or fail>\n- [ ] Self-contained caption: \u003Cpass or fail>\n- [ ] Honest axis range (if applicable): \u003Cpass or fail>\n- [ ] No chartjunk: \u003Cpass or fail>\n\n### 7. Integrity gate result\n- Gate 1-7: \u003Cpass or fail>\n\n### 8. Severity summary\n- \u003Cn> CRITICAL, \u003Cm> MAJOR, \u003Ck> MINOR\n- Top three actions first: ...\n","# Figure Designer\n\n## Overview\n\nA top-venue paper typically carries six to eight figures, with three\ncarrying almost all the storytelling weight: the Motivated Example\n(Figure 1, on page 1 or the top of page 2), the Solution Overview\n(inside the Methodology section), and the Experimental Results\nfigures (inside the Experiments section). Reviewers scan these three\nin under a minute to decide whether the paper is worth reading in\ndetail; weak figures sink otherwise-strong papers.\n\nThis skill takes the user's intent (what they want to communicate)\nplus context (research area, method name, target venue) and returns\nthe recommended paradigm, a layout sketch, labelling guidance,\ntool suggestion, and a quality-control audit against a universal\nrule set (vector format, font size, colour-blind-safe encoding,\nself-contained caption, honest axis ranges).\n\n## When to use this skill\n\n- Before drawing any figure in a paper.\n- The user asks to 'design a figure', 'draw Figure 1', 'plot\n  experiment results', 'choose the right chart type'.\n- The user has drawn a figure and wants a design audit.\n- The user is unsure which figure type or paradigm to choose.\n- Preparing camera-ready figures before submission.\n\n## When NOT to use this skill\n\n- The user only wants generic plotting help (bar chart, line chart)\n  outside a paper. Regular assistance suffices.\n- The paper is not yet structured; use `intro-drafter` or\n  `tech-paper-template` first to decide what figures the paper\n  needs.\n- The user wants a review of an already-finished paper. Use\n  `pre-submission-reviewer`.\n\n## Core procedure\n\n### Step 1: Figure-type identification\n\nDecide which of the three core types the figure is. If the user's\nrequest does not match any, either it is a supporting figure (use\nthe experimental-results guidance as a base) or it does not belong\nin the paper.\n\nIf the mode is `figure-audit` and the user has provided an image\npath, load the image with the Read tool **before** proceeding to\nStep 2. Vision-based inspection enables the universal rule audit\nin Step 6 to check font legibility, colour palette, raster-vs-\nvector tells, and chartjunk directly rather than relying on user\ndescription. If no image is provided, continue in text-only mode\nand mark vision-only rules (font size, raster detection, colour\npalette) as \"user must verify\" in the final audit report.\n\n### Step 2: Paradigm recommendation\n\nSee: references\u002Fmotivated-example.md, references\u002Fsolution-overview.md,\nor references\u002Fexperimental-results.md depending on figure type.\n\nEach figure type has two to three canonical paradigms. Pick the one\nthat fits the user's storytelling need, and explain why the other\nparadigms fit less well.\n\n### Step 3: Layout sketch\n\nProduce a text description of the layout: panel positions, element\nplacement, arrows, colour assignments. The goal is that the user\ncould draw the first draft from the sketch alone.\n\n### Step 4: Labelling and annotation guidance\n\n- Name every visible element concretely (no \"Module A\", \"X\", \"Y\").\n- Annotate critical points (failure highlight, success highlight,\n  comparison emphasis).\n- Specify font sizes and colour palette. Default colour palette:\n  ColorBrewer Qualitative or Viridis for sequential.\n\n### Step 5: Tool suggestion\n\nSee: references\u002Ftools.md for the tool matrix and the decision\nheuristic.\n\nDefault recommendations:\n\n- Motivated Example and Solution Overview: PowerPoint (draft),\n  Figma (polish).\n- Experimental Results: Matplotlib or Seaborn in a reusable\n  `plot_utils.py` script.\n- LaTeX-integrated figures: TikZ or PGFPlots.\n\n### Step 6: Universal rule audit\n\nSee: references\u002Fdesign-rules.md for the full universal rule set.\n\nVerify every proposed or existing figure against:\n\n- Vector format (PDF, EPS, SVG) for export.\n- Font size at least 8pt post-scaling.\n- Small canvas (not large canvas with small fonts).\n- Colour-blind-safe palette; no colour-only encoding.\n- Self-contained caption whose first sentence states the core\n  finding.\n- Honest axis ranges.\n- No 3D effects, no chartjunk.\n\nFlag every violation with severity.\n\n### Step 7: Integrity gate\n\nRun the checks in the Integrity gate section below.\n\n### Step 8: Output\n\nEmit the full design in the Output format below.\n\n## Integrity gate\n\nBullets tagged [inspection] are checked by the LLM from its own\noutput. Bullets tagged [user-verify] require the user to confirm\nbecause the check depends on either the drawn figure or knowledge\nthe skill does not have (paper context, prior Introduction).\n\nBefore returning the design:\n\n1. **[inspection]** Paradigm matches figure type (motivated example\n   is not a pipeline; overview is not a bar chart).\n2. **[inspection]** Layout sketch is concrete enough that the user\n   could draw from it.\n3. **[inspection]** Labels are real entity names, not placeholders.\n4. **[inspection]** Tool suggestion matches the figure's complexity\n   (not Matplotlib for a multi-icon motivated example, not\n   PowerPoint for a 20-method bar chart).\n5. **[inspection] when image provided, [user-verify] text-only**\n   Universal rule audit has been run; no CRITICAL violation is\n   left unaddressed. Vision-only rules (raster-vs-vector, font\n   size, colour palette) are only checkable when the user supplies\n   an image.\n6. **[user-verify]** For motivated examples, the example is the\n   same running example referenced by the Introduction (no new\n   example introduced in Figure 1). The skill does not see the\n   Introduction; the user confirms.\n7. **[inspection]** For experimental results, the chart type\n   matches the data type (time-series uses line, multi-method\n   comparison uses grouped bar, trade-off uses scatter).\n\nIf any [inspection] check fails, mark the design as \"needs user\nattention\". For [user-verify] items, surface them to the user as\nitems they must confirm before submission.\n\n## Output format\n\n### 1. Figure type\n- Type: \u003Cmotivated-example or solution-overview or experimental-results>\n- Reason: \u003Cone sentence>\n\n### 2. Paradigm recommendation\n- Paradigm: \u003Cname>\n- Why this paradigm: \u003Crationale>\n- Alternatives considered and rejected: \u003Clist>\n\n### 3. Layout sketch\n- Canvas: \u003Csize>\n- Panels: \u003Clist with positions and contents>\n- Arrows and connections: \u003Clist>\n- Colour assignment: \u003Cmapping>\n\n### 4. Labelling and annotations\n- Element names: \u003Clist>\n- Critical highlights: \u003Clist>\n- Font sizes: \u003Ctarget>\n- Colour palette: \u003Cname>\n\n### 5. Tool suggestion\n- Primary: \u003Ctool>\n- Alternative: \u003Ctool>\n- Reason: \u003Crationale>\n\n### 6. Universal rule audit\n- [ ] Vector format: \u003Cpass or fail>\n- [ ] Font size: \u003Cpass or fail>\n- [ ] Colour-blind safe: \u003Cpass or fail>\n- [ ] Self-contained caption: \u003Cpass or fail>\n- [ ] Honest axis range (if applicable): \u003Cpass or fail>\n- [ ] No chartjunk: \u003Cpass or fail>\n\n### 7. Integrity gate result\n- Gate 1-7: \u003Cpass or fail>\n\n### 8. Severity summary\n- \u003Cn> CRITICAL, \u003Cm> MAJOR, \u003Ck> MINOR\n- Top three actions first: ...\n",{"name":5,"license":15,"description":7},"main","e6390f546a3cc4731cf8bd03a19a20ca8334553b","skills\u002Fai-mentor\u002Fskills\u002Ffigure-designer","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 figure-designer",{"tool":38,"command":39},"bunx","bunx skills add zms618\u002Fno-heartburn-academic-skills --skill figure-designer",{"tool":41,"command":42},"pnpm","pnpm dlx skills add zms618\u002Fno-heartburn-academic-skills --skill figure-designer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fai-mentor\u002Fskills\u002Ffigure-designer\u002FSKILL.md",true,[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdesign-rules.md","REFERENCE","参考文档",3979,"https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fai-mentor\u002Fskills\u002Ffigure-designer\u002Freferences\u002Fdesign-rules.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fexperimental-results.md",5117,"https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fai-mentor\u002Fskills\u002Ffigure-designer\u002Freferences\u002Fexperimental-results.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fmotivated-example.md",4618,"https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fai-mentor\u002Fskills\u002Ffigure-designer\u002Freferences\u002Fmotivated-example.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsolution-overview.md",4893,"https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fai-mentor\u002Fskills\u002Ffigure-designer\u002Freferences\u002Fsolution-overview.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftools.md",3957,"https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fai-mentor\u002Fskills\u002Ffigure-designer\u002Freferences\u002Ftools.md",[69,76,82,89,96,103],{"skillNo":70,"name":71,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7EBH8ZAKH92EA8GG2A4Z8B4","research-review-board","MIT","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-review-board\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7EBGVT2CFZNEMJSBXWYX751","research-problem-scout","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.","https:\u002F\u002Fgithub.com\u002Fzms618\u002Fno-heartburn-academic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-idea-discovery\u002Fskills\u002Fresearch-problem-scout\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]