[{"data":1,"prerenderedAt":282},["ShallowReactive",2],{"repo-hugohe3-ppt-master-en":3,"i18n-hugohe3-ppt-master-en":279},{"mirrorPool":4,"detail":13,"relatedProjects":145},[5,9],{"key":6,"label":7,"base":8,"type":6},"github","mirror.github","https:\u002F\u002Fgithub.com\u002F",{"key":10,"label":11,"base":12,"type":10},"auto-proxy","mirror.autoProxy","https:\u002F\u002Fgithub.xxlab.tech\u002F",{"owner":14,"repo":15,"repoId":16,"repoUrl":17,"starCount":18,"language":19,"description":20,"languages":21,"screenshots":26,"homepage":27,"pushedAt":28,"ownerAvatar":29,"ownerName":30,"ownerBio":31,"lastSyncTime":32,"lastReleaseTime":33,"tags":34,"license":45,"category":46,"subgroup":47,"releases":48},"hugohe3","ppt-master",1113573066,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master",75408,"Python","AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He",{"Python":22,"JavaScript":23,"CSS":24,"HTML":25},94.4,4.8,0.6,0.1,[],"https:\u002F\u002Fhugohe3.github.io\u002Fppt-master-examples\u002F","2026-11-09","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F188330578?v=4","HugoHe","CPA · CPV · 14 yrs in investment & financing. Author of ppt-master (70k+★). Turning professional workflows into products.\r\n","2026-11-10T08:05:47.725123+00:00","2026-11-08T10:38:28Z",[35,36,37,38,39,40,41,42,43,44],"ai-agent","aippt","office","powerpoint","powerpoint-generation","ppt","pptx","presentation","slide","slides","MIT","development","AI编程助手",[49,63,75,88,100,111,122,133],{"tag":50,"publishAt":33,"semVer":51,"prerelease":55,"assets":56},"v6.9.0",[52,53,54],6,9,0,false,[57],{"fileName":58,"sizeMb":59,"sha256":60,"downloadCount":61,"originUrl":62},"ppt-master-skill-v6.9.0.zip",21.78,"5ac7bf511b1bbaf3809b9fb3d8465918f79ca39b5451203c9eb9e08763acd873",6946,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.9.0\u002Fppt-master-skill-v6.9.0.zip",{"tag":64,"publishAt":65,"semVer":66,"prerelease":55,"assets":68},"v6.8.0","2026-10-30T06:05:44Z",[52,67,54],8,[69],{"fileName":70,"sizeMb":71,"sha256":72,"downloadCount":73,"originUrl":74},"ppt-master-skill-v6.8.0.zip",21.66,"2819a5b2330fa0dee9819b37395db5da33ae2b159908864225aa60481fe92bdd",41312,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.8.0\u002Fppt-master-skill-v6.8.0.zip",{"tag":76,"publishAt":77,"semVer":78,"prerelease":55,"assets":81},"v6.7.3","2026-10-22T11:43:24Z",[52,79,80],7,3,[82],{"fileName":83,"sizeMb":84,"sha256":85,"downloadCount":86,"originUrl":87},"ppt-master-skill-v6.7.3.zip",21.56,"0f709c0e3fa42671c65e35964bb26acbffad468eec829f00b9db6c418f95db3f",47896,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.7.3\u002Fppt-master-skill-v6.7.3.zip",{"tag":89,"publishAt":90,"semVer":91,"prerelease":55,"assets":93},"v6.7.2","2026-10-17T12:21:54Z",[52,79,92],2,[94],{"fileName":95,"sizeMb":96,"sha256":97,"downloadCount":98,"originUrl":99},"ppt-master-skill-v6.7.2.zip",21.52,"b93c5ef3a52ae1f0d1412aa9b85aae6706b769ed3e8cf5b1682dec1cbbf2860f",15371,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.7.2\u002Fppt-master-skill-v6.7.2.zip",{"tag":101,"publishAt":102,"semVer":103,"prerelease":55,"assets":105},"v6.7.1","2026-10-16T15:50:46Z",[52,79,104],1,[106],{"fileName":107,"sizeMb":96,"sha256":108,"downloadCount":109,"originUrl":110},"ppt-master-skill-v6.7.1.zip","64992f79dff176755032579c6e5437cec3a2296e1cb92a0c8ce031cc7ce3d811",1051,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.7.1\u002Fppt-master-skill-v6.7.1.zip",{"tag":112,"publishAt":113,"semVer":114,"prerelease":55,"assets":115},"v6.7.0","2026-10-08T02:01:38Z",[52,79,54],[116],{"fileName":117,"sizeMb":118,"sha256":119,"downloadCount":120,"originUrl":121},"ppt-master-skill-v6.7.0.zip",21.51,"40424d9784fa25f771da8b312258c3c67a168925122aa6bb7faf6848e77ceee9",10372,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.7.0\u002Fppt-master-skill-v6.7.0.zip",{"tag":123,"publishAt":124,"semVer":125,"prerelease":55,"assets":126},"v6.6.0","2026-09-19T05:06:18Z",[52,52,54],[127],{"fileName":128,"sizeMb":129,"sha256":130,"downloadCount":131,"originUrl":132},"ppt-master-skill-v6.6.0.zip",59.14,"4e239ac3c11036c8c9d3bb987f5ccbd02a176d6832f2404f8a067414d834d2a1",12879,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.6.0\u002Fppt-master-skill-v6.6.0.zip",{"tag":134,"publishAt":135,"semVer":136,"prerelease":55,"assets":138},"v6.5.0","2026-09-16T12:20:17Z",[52,137,54],5,[139],{"fileName":140,"sizeMb":141,"sha256":142,"downloadCount":143,"originUrl":144},"ppt-master-skill-v6.5.0.zip",59.11,"874788c752f47f1a6d775c170ccadb68a4b4f9302ff06b5360b98798503c70ec",2762,"https:\u002F\u002Fgithub.com\u002Fhugohe3\u002Fppt-master\u002Freleases\u002Fdownload\u002Fv6.5.0\u002Fppt-master-skill-v6.5.0.zip",[146,163,195,223,234,260],{"owner":147,"repo":148,"repoId":149,"category":150,"subgroup":47,"language":151,"tags":152,"starCount":153,"ownerUid":154,"latestTag":155,"platforms":156,"lastReleaseTime":160,"downloadCount":161,"description":162},"anomalyco","opencode",975734319,"ai","TypeScript",[],226622,66570915,"v2.3.0",[157,158,159],"windows","mac","linux","2026-11-13T08:55:07Z",7346,"An open-source AI coding agent available as both a CLI and desktop app, with quick installation via script, npm, Homebrew, and other package managers.",{"owner":164,"repo":165,"repoId":166,"category":167,"subgroup":47,"language":168,"tags":169,"starCount":188,"ownerUid":189,"latestTag":190,"platforms":191,"lastReleaseTime":192,"downloadCount":193,"description":194},"farion1231","cc-switch",1031912724,"tools","Rust",[170,171,172,173,174,175,176,177,178,179,180,148,181,182,183,184,185,186,187],"ai-tools","claude-code","codex","deepseek-harness","desktop-app","grok","grokbuild","hermes","kimi-code","mcp","open-source","pi","provider-management","rust","skills","skills-management","tauri","wsl-support",153919,44939412,"v4.0.31",[157,158,159],"2026-11-12T15:59:54Z",3837,"A cross-platform desktop tool to manage multiple AI programming assistants, including Claude Code, Codex, Gemini CLI, Grok Build, and more.",{"owner":196,"repo":197,"repoId":198,"category":150,"subgroup":47,"language":19,"tags":199,"starCount":215,"ownerUid":216,"latestTag":217,"platforms":218,"lastReleaseTime":220,"downloadCount":221,"description":222},"Graphify-Labs","graphify",1200597263,[200,201,202,171,203,204,172,205,206,207,197,208,209,210,211,179,212,213,184,214],"ai-agents","antigravity","ast","code-analysis","code-search","cursor","developer-tools","gemini","graphrag","knowledge-graph","leiden","llm","openclaw","rag","tree-sitter",147160,297659074,"v0.9.108",[219],"other","2026-11-12T21:48:11Z",130,"Graphify is a local tool that turns any codebase — with its docs, SQL schemas, configs, and PDFs — into a queryable knowledge graph, integrating as a \u002Fgraphify skill for Claude Code, Cursor, and other AI coding assistants with deterministic AST parsing instead of vector search.",{"owner":224,"repo":172,"repoId":225,"category":150,"subgroup":47,"language":168,"tags":226,"starCount":227,"ownerUid":228,"latestTag":229,"platforms":230,"lastReleaseTime":231,"downloadCount":232,"description":233},"openai",965415649,[],135171,14957082,"rust-v0.169.0",[157,158,159,219],"2026-11-13T08:37:05Z",74966,"A lightweight coding agent from OpenAI that runs in your terminal, with support for ChatGPT accounts or API keys.",{"owner":235,"repo":236,"repoId":237,"category":46,"subgroup":47,"language":151,"tags":238,"starCount":253,"ownerUid":254,"latestTag":255,"platforms":256,"lastReleaseTime":257,"downloadCount":258,"description":259},"stablyai","orca",1183888342,[239,200,240,241,171,172,242,243,244,245,246,212,148,247,181,248,249,250,251,252],"agent-ide","automation","bot","ghostty","grok-bot","hermes-agent","mobile-app","muse","orchestration","runtime","swarm","terminal","worktrees","yc-backed",124240,127256420,"v1.4.258",[157,158,159,219],"2026-11-13T01:35:38Z",235931,"An AI orchestrator that runs multiple coding agents like Codex and ClaudeCode in parallel, available on desktop, mobile, and VPS.",{"owner":261,"repo":262,"repoId":263,"category":167,"subgroup":47,"language":151,"tags":264,"starCount":271,"ownerUid":272,"latestTag":273,"platforms":274,"lastReleaseTime":276,"downloadCount":277,"description":278},"pingdotgg","t3code",1153130349,[265,266,150,267,268,171,269,270],"agent-orchestration","agents","chatgpt","claude","code","vibe-coding",59345,89191727,"v0.1.10-nightly.20261113.4643",[157,158,159,275,219],"android","2026-11-13T14:47:45Z",4473,"An agent harness control surface that lets you control AI coding agents like Claude Code, Codex, and Cursor on your machine from a mobile, web, or desktop app.",{"description":280,"readmeHtml":281},"PPT Master is a workflow that runs inside agent-capable AI tools and turns PDFs, Word files, web pages or a single topic into natively editable PowerPoint decks on the user's own machine.","\u003Ch2 id=\"project-overview\">Project Overview\u003C\u002Fh2>\u003Cp>PPT Master turns documents, PDFs, web pages, images or a one-line topic into a natively editable \u003Ccode>.pptx\u003C\u002Fcode> file, with the whole pipeline running on your own machine: the AI analyses the content, designs the layout and writes SVG, and the Python scripts in the repository compile that SVG into DrawingML. It is not a standalone app but a skill plus script bundle under \u003Ccode>skills\u002Fppt-master\u003C\u002Fcode>, driven by any AI tool that can read and write files, run commands and hold a multi-turn conversation. The result is a real deck with slide masters, native shapes, charts, tables and OMML formulas rather than flattened images, and every page stays editable in PowerPoint.\u003C\u002Fp>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Item\u003C\u002Fth>\n\u003Cth>Value\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>Form\u003C\u002Ftd>\n\u003Ctd>Skill pack plus Python scripts inside an AI tool\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Output\u003C\u002Ftd>\n\u003Ctd>Natively editable \u003Ccode>.pptx\u003C\u002Fcode>, with \u003Ccode>svg_final\u002F\u003C\u002Fcode> page previews by default\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Runtime\u003C\u002Ftd>\n\u003Ctd>Python 3.10–3.14\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>License\u003C\u002Ftd>\n\u003Ctd>MIT\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Cblockquote>\n\u003Cp>Swap letting the AI draw pictures for letting the AI write real PowerPoint.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch2 id=\"supported-hosts\">Supported Hosts\u003C\u002Fh2>\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Host type\u003C\u002Fth>\n\u003Cth>Examples\u003C\u002Fth>\n\u003Cth>How to use\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>IDE-native agent\u003C\u002Ftd>\n\u003Ctd>VS Code, Cursor, Trae, Windsurf, Zed\u003C\u002Ftd>\n\u003Ctd>Open the project folder and type instructions in the side chat panel\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>IDE plugin\u003C\u002Ftd>\n\u003Ctd>Claude Code extension, GitHub Copilot, Cline\u003C\u002Ftd>\n\u003Ctd>Installed inside VS Code or a JetBrains host\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>CLI agent\u003C\u002Ftd>\n\u003Ctd>Claude Code CLI, Codex CLI, Gemini CLI\u003C\u002Ftd>\n\u003Ctd>Start it in the terminal after entering the project folder\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2 id=\"key-features\">Key Features\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Native PPTX export\u003C\u002Fstrong>: output lands in \u003Ccode>exports\u002Fname_timestamp.pptx\u003C\u002Fcode>, where shapes, text boxes and connectors are real PowerPoint objects you can keep editing\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Document to outline\u003C\u002Fstrong>: reads PDF, DOCX, HTML, EPUB and IPYNB directly, while \u003Ccode>doc\u003C\u002Fcode>, \u003Ccode>odt\u003C\u002Fcode>, \u003Ccode>rtf\u003C\u002Fcode>, \u003Ccode>tex\u003C\u002Fcode>, \u003Ccode>rst\u003C\u002Fcode>, \u003Ccode>org\u003C\u002Fcode> and \u003Ccode>typ\u003C\u002Fcode> need Pandoc installed\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Masters and layouts\u003C\u002Fstrong>: decks inherit real \u003Ccode>p:sldMaster\u003C\u002Fcode> and \u003Ccode>p:sldLayout\u003C\u002Fcode> structures, and an existing company template can be applied\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Native charts and tables\u003C\u002Fstrong>: with \u003Ccode>--native-charts-and-tables\u003C\u002Fcode> the deck gets Chart and Table objects with Edit Data, saved as a separate \u003Ccode>_native_charts_tables.pptx\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Formulas and motion\u003C\u002Fstrong>: formulas compile to OMML for PowerPoint 2010 and later, and native transitions, animations and narration from speaker notes are supported\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Image sourcing\u003C\u002Fstrong>: \u003Ccode>image_gen.py\u003C\u002Fcode> generates images through an AI backend, while \u003Ccode>image_search.py\u003C\u002Fcode> searches the web and adds attribution automatically for CC0 and CC BY style licenses\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Refill an existing deck\u003C\u002Fstrong>: hand the AI a finished \u003Ccode>.pptx\u003C\u002Fcode> and it keeps the design, edits only the pages you pick and leaves untouched pages byte-identical\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Canvas presets\u003C\u002Fstrong>: ships PPT 16:9, Xiaohongshu, WeChat and more than 10 canvas sizes\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"quick-start\">Quick Start\u003C\u002Fh2>\u003Col>\n\u003Cli>Install Python 3.10–3.14, and tick Add to PATH on Windows\u003C\u002Fli>\n\u003Cli>Clone the repository, enter the folder and run \u003Ccode>pip install -r requirements.txt\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Open the \u003Ccode>ppt-master\u003C\u002Fcode> folder in an AI tool, or start a CLI agent inside that folder\u003C\u002Fli>\n\u003Cli>Put your PDF, DOCX or images under \u003Ccode>projects\u002F\u003C\u002Fcode> and name the path in chat, for example make an 8-page deck from \u003Ccode>projects\u002Fq3-report\u002Fsources\u002Freport.pdf\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Confirm the template, aspect ratio and page count the AI proposes, or ask it to quick generate without confirmation\u003C\u002Fli>\n\u003Cli>Collect the file from \u003Ccode>exports\u002F\u003C\u002Fcode>, and find page previews in \u003Ccode>svg_final\u002F\u003C\u002Fcode> for the default flow\u003C\u002Fli>\n\u003Cli>Add \u003Ccode>--native-charts-and-tables\u003C\u002Fcode> when you need data-backed charts, which saves a separate \u003Ccode>_native_charts_tables.pptx\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Copy \u003Ccode>.env.example\u003C\u002Fcode> to \u003Ccode>.env\u003C\u002Fcode> and fill in \u003Ccode>PEXELS_API_KEY\u003C\u002Fcode> or \u003Ccode>PIXABAY_API_KEY\u003C\u002Fcode> for better stock images, while Openverse search works without keys\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Ch2 id=\"target-audience\">Target Audience\u003C\u002Fh2>\u003Cul>\n\u003Cli>People who present often at work\u003C\u002Fli>\n\u003Cli>Teams that reuse a corporate template\u003C\u002Fli>\n\u003Cli>Marketers producing decks in bulk\u003C\u002Fli>\n\u003Cli>Technical users comfortable with AI tools\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"core-advantages\">Core Advantages\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Model cost only\u003C\u002Fstrong>: the software is free and open source, and the only spend is model usage plus the search, image and speech services you choose to enable\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Local data\u003C\u002Fstrong>: the pipeline runs on your machine, so source material is not uploaded to a third-party platform first\u003C\u002Fli>\n\u003Cli>\u003Cstrong>No model lock-in\u003C\u002Fstrong>: Claude, GPT, Gemini and Kimi all drive the same workflow, so switching tools does not mean rebuilding the project\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Close to native\u003C\u002Fstrong>: capabilities are added against the feature-by-feature mapping in \u003Ccode>docs\u002Fpowerpoint-svg-mapping.md\u003C\u002Fcode> instead of pasting page screenshots into slides\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"system-requirements\">System Requirements\u003C\u002Fh2>\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Item\u003C\u002Fth>\n\u003Cth>Requirement\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>OS\u003C\u002Ftd>\n\u003Ctd>Windows 10 and later, macOS, Linux\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Python\u003C\u002Ftd>\n\u003Ctd>3.10–3.14\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Optional dependency\u003C\u002Ftd>\n\u003Ctd>Pandoc, only for legacy formats such as \u003Ccode>doc\u003C\u002Fcode>, \u003Ccode>odt\u003C\u002Fcode>, \u003Ccode>rtf\u003C\u002Fcode>, \u003Ccode>tex\u003C\u002Fcode>, \u003Ccode>rst\u003C\u002Fcode>, \u003Ccode>org\u003C\u002Fcode> and \u003Ccode>typ\u003C\u002Fcode>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>AI tool\u003C\u002Ftd>\n\u003Ctd>An agent with file access, command execution and multi-turn chat\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>Model context\u003C\u002Ftd>\n\u003Ctd>Around 1 million tokens recommended for long documents\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2 id=\"notes\">Notes\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>The model sets the ceiling\u003C\u002Fstrong>: the skill only provides the workflow, so layout quality follows the model's context and taste and weaker models fall short on the same pipeline\u003C\u002Fli>\n\u003Cli>\u003Cstrong>One pass, no resume\u003C\u002Fstrong>: quick mode produces a deck in a single pass and cannot be resumed, and it writes no \u003Ccode>svg_final\u002F\u003C\u002Fcode> preview\u003C\u002Fli>\n\u003Cli>\u003Cstrong>PDF component license differs\u003C\u002Fstrong>: the optional PDF converter relies on PyMuPDF under AGPL-3.0, so redistributing a bundle that includes it must follow those terms\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Bring your own assets\u003C\u002Fstrong>: fonts, brand templates and high-resolution images are not in the repository, so corporate templates must be placed under \u003Ccode>projects\u002F\u003C\u002Fcode> or the template folder\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Output keeps growing\u003C\u002Fstrong>: every run adds a new timestamped file under \u003Ccode>exports\u002F\u003C\u002Fcode>, so long-term use needs manual cleanup\u003C\u002Fli>\n\u003C\u002Ful>\n",1794593696899]