[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76ZKM97B2SY0PP5GDWS9XZS":3,"skill-same:01M76ZKM97B2SY0PP5GDWS9XZS":47},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M76ZKM97B2SY0PP5GDWS9XZS","auto-paper-writer",null,"自动撰写科研论文的完整 AI pipeline。当用户说\"撰写[方向]论文\"、\"自动写论文\"、\"生成论文\"时触发。功能包括：(1) 搜索 ArXiv 最新论文并下载原始 PDF；(2) 总结现有工作局限性；(3) 设计创新模型框架；(4) 撰写双栏 LaTeX 论文（IEEEtran格式）；(5) 生成科研级 matplotlib 配图；(6) 编译 PDF 并保存到桌面。此技能仅生成学术论文框架和创新点思路，不保证内容创新性和实验真实性，用户需自行在 Overleaf\u002F本地 LaTeX 中补充实验结果和细节调整。","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Fauto-paper-writer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: auto-paper-writer\ndescription: 自动撰写科研论文的完整 AI pipeline。当用户说\"撰写[方向]论文\"、\"自动写论文\"、\"生成论文\"时触发。功能包括：(1) 搜索 ArXiv 最新论文并下载原始 PDF；(2) 总结现有工作局限性；(3) 设计创新模型框架；(4) 撰写双栏 LaTeX 论文（IEEEtran格式）；(5) 生成科研级 matplotlib 配图；(6) 编译 PDF 并保存到桌面。此技能仅生成学术论文框架和创新点思路，不保证内容创新性和实验真实性，用户需自行在 Overleaf\u002F本地 LaTeX 中补充实验结果和细节调整。\n---\n\n# Auto Paper Writer\n\n自动撰写科研论文的完整 pipeline。从文献调研到 PDF 输出的端到端自动化。\n\n## 工作流程\n\n### Step 1: 搜索最新论文\n使用 ArXiv API 搜索相关方向的最新论文：\n\n```powershell\n# PowerShell 调用 ArXiv API\n$query = \"your search terms\"\n$url = \"https:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?search_query=all:$query&start=0&max_results=10&sortBy=submittedDate&sortOrder=descending\"\n```\n\n优先搜索 ICLR\u002FNeurIPS\u002FAAAI\u002FICML 等顶会论文，以及与用户方向相关的高引用工作。\n\n### Step 1.5: 保存搜索论文\n将搜索到的论文信息保存到文献文件夹：\n\n```powershell\n# 创建文献文件夹\n$ref_dir = \"$paper_dir\\references\"\nNew-Item -ItemType Directory -Path $ref_dir -Force\n\n# 保存论文列表（Markdown 格式）\n$ref_content = @\"\n# 文献调研\n\n## 搜索时间：$(Get-Date -Format \"yyyy-MM-dd HH:mm\")\n## 搜索方向：$direction\n## 搜索关键词：$keywords\n\n---\n\n### 论文列表\n\n| # | 论文标题 | 作者 | 日期 | arXiv ID |\n|---|---------|------|------|----------|\n\"@\n\nforeach ($entry in $xml.feed.entry) {\n    $title = $entry.title -replace '\\s+', ' '\n    $authors = ($entry.author | ForEach-Object { $_.name }) -join ', '\n    $published = $entry.published.Substring(0,10)\n    $arxiv_id = $entry.id.Split('\u002F')[-1]\n    $ref_content += \"`n| - | $title | $authors | $published | [$arxiv_id](https:\u002F\u002Farxiv.org\u002Fabs\u002F$arxiv_id) |\"\n}\n\n$ref_content += \"@\"\n$ref_content | Out-File -FilePath \"$ref_dir\\paper_references.md\" -Encoding UTF8\n```\n\n保存内容：\n- `references\u002Fpaper_references.md` — 论文列表（标题\u002F作者\u002F日期\u002F链接）\n- `references\u002F*.pdf` — 原始论文 PDF 文件\n\n### Step 1.5: 下载论文原文 PDF\n从 ArXiv 下载每篇论文的原始 PDF，**文件用论文标题命名**：\n\n```powershell\n# ArXiv PDF 下载地址格式\n# https:\u002F\u002Farxiv.org\u002Fpdf\u002F{arxiv_id}.pdf\n\nforeach ($entry in $xml.feed.entry) {\n    $arxiv_id = $entry.id.Split('\u002F')[-1] -replace 'v\\d+$', ''\n    $title = $entry.title -replace '\\s+', ' ' -replace '[^\\w\\s-]', '' -replace '\\s', '_'\n    $pdf_url = \"https:\u002F\u002Farxiv.org\u002Fpdf\u002F$arxiv_id.pdf\"\n    $pdf_path = \"$ref_dir\\$title.pdf\"\n\n    # 截断过长文件名，保留前 50 字符\n    if ($title.Length -gt 50) {\n        $title = $title.Substring(0, 50)\n        $pdf_path = \"$ref_dir\\$title.pdf\"\n    }\n\n    try {\n        Invoke-WebRequest -Uri $pdf_url -OutFile $pdf_path -UseBasicParsing\n        Write-Host \"Downloaded: $title.pdf\"\n    } catch {\n        Write-Host \"Failed to download: $arxiv_id\"\n    }\n}\n```\n\n**文件命名规则**：\n- 用论文标题命名，不是 arXiv ID\n- 空格替换为下划线\n- 特殊字符清理\n- 过长截断前 50 字符\n\n下载结果示例：\n- `references\u002FBidirectional_Cross-Modal_Prompting_for_Event-Frame.pdf`\n- `references\u002FMM-WebAgent_A_Hierarchical_Multimodal_Web_Agent.pdf`\n- ...\n\n**重要**：此步骤是标准工作流程的必要环节，必须执行！\n\n### Step 2: 分析局限性\n阅读摘要和核心方法，总结现有工作的**局限性**：\n- 计算开销大 \u002F 参数量过大\n- 需要海量标注数据\n- 模态对齐\u002F融合不完善\n- 泛化能力有限\n- 推理速度慢\n\n### Step 3: 设计创新模型框架\n- 起一个简洁有力的模型名字\n- 提出 **3-5 个核心创新点**\n- 画整体架构框图（模块化设计）\n\n### Step 4: 撰写论文\n按标准科研论文结构，使用 **IEEEtran 双栏格式**：\n\n```latex\n\\documentclass[conference]{IEEEtran}\n```\n\n论文结构：\n1. **Abstract** - 简明扼要，150-250 词\n2. **Introduction** - 研究背景、动机、贡献（列出 3-5 条贡献）\n3. **Related Work** - 梳理相关工作，对比分析\n4. **Proposed Method** - 详细介绍方法\n5. **Experiments** - 实验设置、基线对比\n6. **Conclusion** - 总结与未来工作\n7. **References** - 格式规范的参考文献\n\n使用标准 LaTeX 公式、表格、`\\ref{}` 交叉引用。\n\n### Step 5: 生成科研级配图\n使用 matplotlib 生成 300dpi 高质量图片：\n\n```python\nimport matplotlib.pyplot as plt\nplt.rcParams['font.size'] = 10\nplt.rcParams['figure.dpi'] = 300\n\n# 图1: 模型框架图 - 整体架构，模块化，箭头标注\n# 图2: 方法细节图 - 核心创新机制\n# 图3: 实验结果图 - 对比曲线、柱状图\n```\n\n### Step 6: 编译 PDF\n使用 **TeX Live**（不是 Tectonic）编译：\n\n```powershell\n$texlive = \"D:\\texlive\\2026\\bin\\windows\\pdflatex.exe\"\n$paper_dir = \"C:\\Users\\29064\\Desktop\\PaperName\"\n\n# 必须运行两次！第一次生成 .aux，第二次解析交叉引用\n& $texlive \"$paper_dir\\paper.tex\" -interaction=nonstopmode -output-directory=\"$paper_dir\"\n& $texlive \"$paper_dir\\paper.tex\" -interaction=nonstopmode -output-directory=\"$paper_dir\"\n```\n\n**关键规则**：\n- 编译失败时**绝不简化 .tex 内容**，保留完整让用户在 Overleaf 自行处理\n- 编译时**必须在 tex 文件所在目录运行**（否则图片相对路径找不到）\n- **不要用 Tectonic**（与 IEEEtran 不兼容）\n\n### Step 7: 保存到桌面\n输出路径：`C:\\Users\\29064\\Desktop\\[论文名字]\\`\n包含文件：\n- `paper.tex` - 主论文文件\n- `paper.pdf` - 编译后的 PDF\n- `figure1.png` \u002F `figure2.png` \u002F `figure3.png` - 配图\n- `references\u002Fpaper_references.md` - 文献调研列表\n- `references\u002F*.pdf` - 原始论文 PDF\n\n### Step 8: 清理临时文件\n论文撰写完成后，**删除所有临时脚本文件**：\n- 搜索脚本（`search_*.ps1`）\n- 下载脚本（`download_*.ps1`）\n- 配图生成脚本（`generate_*.py`）\n- 其他中间文件\n\n```powershell\nRemove-Item \"$env:USERPROFILE\\Desktop\\*.ps1\" -Force\nRemove-Item \"$env:USERPROFILE\\Desktop\\*.py\" -Force\nRemove-Item \"$env:USERPROFILE\\Desktop\\*_v*.pptx\" -Force\n```\n\n## 核心原则\n\n1. **生成后立即编译**：.tex 完成后立刻用 TeX Live 编译\n2. **保留完整性**：不简化内容，编译失败时输出完整 .tex\n3. **双栏 IEEEtran**：标准学术论文格式\n4. **科研级配图**：300dpi，清晰标注\n\n## 参考文件\n\n- **论文模板**：[references\u002Fieee_template.md](references\u002Fieee_template.md)\n- **LaTeX 写作指南**：[references\u002Flatex_guide.md](references\u002Flatex_guide.md)\n- **配图规范**：[references\u002Ffigure_guide.md](references\u002Ffigure_guide.md)\n","# Auto Paper Writer\n\n自动撰写科研论文的完整 pipeline。从文献调研到 PDF 输出的端到端自动化。\n\n## 工作流程\n\n### Step 1: 搜索最新论文\n使用 ArXiv API 搜索相关方向的最新论文：\n\n```powershell\n# PowerShell 调用 ArXiv API\n$query = \"your search terms\"\n$url = \"https:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?search_query=all:$query&start=0&max_results=10&sortBy=submittedDate&sortOrder=descending\"\n```\n\n优先搜索 ICLR\u002FNeurIPS\u002FAAAI\u002FICML 等顶会论文，以及与用户方向相关的高引用工作。\n\n### Step 1.5: 保存搜索论文\n将搜索到的论文信息保存到文献文件夹：\n\n```powershell\n# 创建文献文件夹\n$ref_dir = \"$paper_dir\\references\"\nNew-Item -ItemType Directory -Path $ref_dir -Force\n\n# 保存论文列表（Markdown 格式）\n$ref_content = @\"\n# 文献调研\n\n## 搜索时间：$(Get-Date -Format \"yyyy-MM-dd HH:mm\")\n## 搜索方向：$direction\n## 搜索关键词：$keywords\n\n---\n\n### 论文列表\n\n| # | 论文标题 | 作者 | 日期 | arXiv ID |\n|---|---------|------|------|----------|\n\"@\n\nforeach ($entry in $xml.feed.entry) {\n    $title = $entry.title -replace '\\s+', ' '\n    $authors = ($entry.author | ForEach-Object { $_.name }) -join ', '\n    $published = $entry.published.Substring(0,10)\n    $arxiv_id = $entry.id.Split('\u002F')[-1]\n    $ref_content += \"`n| - | $title | $authors | $published | [$arxiv_id](https:\u002F\u002Farxiv.org\u002Fabs\u002F$arxiv_id) |\"\n}\n\n$ref_content += \"@\"\n$ref_content | Out-File -FilePath \"$ref_dir\\paper_references.md\" -Encoding UTF8\n```\n\n保存内容：\n- `references\u002Fpaper_references.md` — 论文列表（标题\u002F作者\u002F日期\u002F链接）\n- `references\u002F*.pdf` — 原始论文 PDF 文件\n\n### Step 1.5: 下载论文原文 PDF\n从 ArXiv 下载每篇论文的原始 PDF，**文件用论文标题命名**：\n\n```powershell\n# ArXiv PDF 下载地址格式\n# https:\u002F\u002Farxiv.org\u002Fpdf\u002F{arxiv_id}.pdf\n\nforeach ($entry in $xml.feed.entry) {\n    $arxiv_id = $entry.id.Split('\u002F')[-1] -replace 'v\\d+$', ''\n    $title = $entry.title -replace '\\s+', ' ' -replace '[^\\w\\s-]', '' -replace '\\s', '_'\n    $pdf_url = \"https:\u002F\u002Farxiv.org\u002Fpdf\u002F$arxiv_id.pdf\"\n    $pdf_path = \"$ref_dir\\$title.pdf\"\n\n    # 截断过长文件名，保留前 50 字符\n    if ($title.Length -gt 50) {\n        $title = $title.Substring(0, 50)\n        $pdf_path = \"$ref_dir\\$title.pdf\"\n    }\n\n    try {\n        Invoke-WebRequest -Uri $pdf_url -OutFile $pdf_path -UseBasicParsing\n        Write-Host \"Downloaded: $title.pdf\"\n    } catch {\n        Write-Host \"Failed to download: $arxiv_id\"\n    }\n}\n```\n\n**文件命名规则**：\n- 用论文标题命名，不是 arXiv ID\n- 空格替换为下划线\n- 特殊字符清理\n- 过长截断前 50 字符\n\n下载结果示例：\n- `references\u002FBidirectional_Cross-Modal_Prompting_for_Event-Frame.pdf`\n- `references\u002FMM-WebAgent_A_Hierarchical_Multimodal_Web_Agent.pdf`\n- ...\n\n**重要**：此步骤是标准工作流程的必要环节，必须执行！\n\n### Step 2: 分析局限性\n阅读摘要和核心方法，总结现有工作的**局限性**：\n- 计算开销大 \u002F 参数量过大\n- 需要海量标注数据\n- 模态对齐\u002F融合不完善\n- 泛化能力有限\n- 推理速度慢\n\n### Step 3: 设计创新模型框架\n- 起一个简洁有力的模型名字\n- 提出 **3-5 个核心创新点**\n- 画整体架构框图（模块化设计）\n\n### Step 4: 撰写论文\n按标准科研论文结构，使用 **IEEEtran 双栏格式**：\n\n```latex\n\\documentclass[conference]{IEEEtran}\n```\n\n论文结构：\n1. **Abstract** - 简明扼要，150-250 词\n2. **Introduction** - 研究背景、动机、贡献（列出 3-5 条贡献）\n3. **Related Work** - 梳理相关工作，对比分析\n4. **Proposed Method** - 详细介绍方法\n5. **Experiments** - 实验设置、基线对比\n6. **Conclusion** - 总结与未来工作\n7. **References** - 格式规范的参考文献\n\n使用标准 LaTeX 公式、表格、`\\ref{}` 交叉引用。\n\n### Step 5: 生成科研级配图\n使用 matplotlib 生成 300dpi 高质量图片：\n\n```python\nimport matplotlib.pyplot as plt\nplt.rcParams['font.size'] = 10\nplt.rcParams['figure.dpi'] = 300\n\n# 图1: 模型框架图 - 整体架构，模块化，箭头标注\n# 图2: 方法细节图 - 核心创新机制\n# 图3: 实验结果图 - 对比曲线、柱状图\n```\n\n### Step 6: 编译 PDF\n使用 **TeX Live**（不是 Tectonic）编译：\n\n```powershell\n$texlive = \"D:\\texlive\\2026\\bin\\windows\\pdflatex.exe\"\n$paper_dir = \"C:\\Users\\29064\\Desktop\\PaperName\"\n\n# 必须运行两次！第一次生成 .aux，第二次解析交叉引用\n& $texlive \"$paper_dir\\paper.tex\" -interaction=nonstopmode -output-directory=\"$paper_dir\"\n& $texlive \"$paper_dir\\paper.tex\" -interaction=nonstopmode -output-directory=\"$paper_dir\"\n```\n\n**关键规则**：\n- 编译失败时**绝不简化 .tex 内容**，保留完整让用户在 Overleaf 自行处理\n- 编译时**必须在 tex 文件所在目录运行**（否则图片相对路径找不到）\n- **不要用 Tectonic**（与 IEEEtran 不兼容）\n\n### Step 7: 保存到桌面\n输出路径：`C:\\Users\\29064\\Desktop\\[论文名字]\\`\n包含文件：\n- `paper.tex` - 主论文文件\n- `paper.pdf` - 编译后的 PDF\n- `figure1.png` \u002F `figure2.png` \u002F `figure3.png` - 配图\n- `references\u002Fpaper_references.md` - 文献调研列表\n- `references\u002F*.pdf` - 原始论文 PDF\n\n### Step 8: 清理临时文件\n论文撰写完成后，**删除所有临时脚本文件**：\n- 搜索脚本（`search_*.ps1`）\n- 下载脚本（`download_*.ps1`）\n- 配图生成脚本（`generate_*.py`）\n- 其他中间文件\n\n```powershell\nRemove-Item \"$env:USERPROFILE\\Desktop\\*.ps1\" -Force\nRemove-Item \"$env:USERPROFILE\\Desktop\\*.py\" -Force\nRemove-Item \"$env:USERPROFILE\\Desktop\\*_v*.pptx\" -Force\n```\n\n## 核心原则\n\n1. **生成后立即编译**：.tex 完成后立刻用 TeX Live 编译\n2. **保留完整性**：不简化内容，编译失败时输出完整 .tex\n3. **双栏 IEEEtran**：标准学术论文格式\n4. **科研级配图**：300dpi，清晰标注\n\n## 参考文件\n\n- **论文模板**：[references\u002Fieee_template.md](references\u002Fieee_template.md)\n- **LaTeX 写作指南**：[references\u002Flatex_guide.md](references\u002Flatex_guide.md)\n- **配图规范**：[references\u002Ffigure_guide.md](references\u002Ffigure_guide.md)\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fa\u002Fauto-paper-writer",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill auto-paper-writer",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill auto-paper-writer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill auto-paper-writer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fa\u002Fauto-paper-writer\u002FSKILL.md",true,[],[48,56,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":55},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":55},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":55},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":55},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":55},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"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":90,"publishedAt":55},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]