GitHub user
Agent skills by SpaceZephyr
- skills
- 62
- repositories
- 3
Repositories by SpaceZephyr
- creator-buddyCreator Buddy: orchestrated Agent Skills for cross-platform content search, creator analysis, and viral trend research1.6k stars · 31 skills
- design-buddyDesign Buddy: visual production Agent Skills for brand design systems, GPT-image-2 images, diagrams, infographics, logos, slide decks, WeChat layouts and social images174 stars · 16 skills
- career.skill告诉 AI 你的职业，它帮你把工作拆成一套可以用的 Skill 库160 stars · 15 skills
Skills by SpaceZephyr, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Fetches hot WeChat Official Account articles by sector or keywords and produces a data file and an HTML report with rankings, style patterns and writing references. | SpaceZephyr/ | 1.6k | — | ~847 | Automated safety check: Pass | No licence | 1 mo ago |
| 2 | Turns an article, SOP, or tutorial into a self-contained, multi-page 3:4 HTML deck of image cards meant to be screenshotted page by page. | SpaceZephyr/ | 1.6k | — | ~928 | Automated safety check: Pass | No licence | 1 mo ago |
| 3 | Finds recent viral WeChat official account articles for a niche keyword and shows up to ten picks as cards, for topic research and benchmarking. | SpaceZephyr/ | 1.6k | — | ~848 | Automated safety check: Pass | No licence | 1 mo ago |
| 4 | Turns written content into designed slide images from an outline, merges them into PPTX or PDF, and can borrow styles from a registry of brand design systems. | SpaceZephyr/ | 174 | — | ~6.5k | Automated safety check: Pass | No licence | 3 mo ago |
| 5 | Draws chart images such as flowcharts, architecture diagrams, ER diagrams and SWOT boards for WeChat official account articles, in one of six visual styles. | SpaceZephyr/ | 1.6k | — | ~1.7k | Automated safety check: Pass | No licence | 1 mo ago |
| 6 | Turns an article into WeChat Official Account HTML with a local preview, a choice of three visual styles and a button that copies the rich HTML. | SpaceZephyr/ | 174 | — | ~1.2k | Automated safety check: Pass | No licence | 3 mo ago |
| 7 | Creates a 2.35:1 header cover for a WeChat official account article with image generation, keeping the headline inside the area that survives sharing crops. | SpaceZephyr/ | 1.6k | — | ~1.5k | Automated safety check: Pass | No licence | 1 mo ago |
| 8 | 《AI Engineering: Building Applications with Foundation Models》(Chip Huyen, O'Reilly 2025) 方法论。 | SpaceZephyr/ | 160 | — | ~1.2k | Automated safety check: Pass | No licence | 3 mo ago |
| 9 | Adds sound to a finished video: generates narration from a script with TTS, finds royalty-free background music, and mixes everything together with ffmpeg. | SpaceZephyr/ | 1.6k | — | ~615 | Automated safety check: Pass | No licence | 1 mo ago |
| 10 | Splits a Markdown article by heading, drafts an image prompt for each section, then generates diagrams with the Gemini API and embeds them in the note. | SpaceZephyr/ | 174 | — | ~1k | Automated safety check: Pass | No licence | 3 mo ago |
| 11 | 《俞军产品方法论》(俞军等，中信出版社 2019) 方法论。把书中的用户价值公式、交易模型、决策效用理论 改造为 AI 产品经理在 AI 化决策 / 需求评估 / 效用比较场景可直接执行的规则集。 | SpaceZephyr/ | 160 | — | ~1.1k | Automated safety check: Pass | No licence | 3 mo ago |
| 12 | 动效导演 + B-roll 生成器。从一段文字/脚本/视频，一次性产出 30 秒以上的动效 B-roll 视频（HTML→确定性 MP4）。不做 PPT 式翻页，从「视觉隐喻 + 运动」出发；内置多种设计风格（暗色 SaaS 魔术、黑白打字机、暖色编辑、极简白、蓝图网格）；产出一律不用 emoji，用排版/几何/SVG 线性图标。当用户说「做 B-roll」「做个动效视频」「motion… | SpaceZephyr/ | 1.6k | — | ~716 | Automated safety check: Pass | No licence | 1 mo ago |
| 13 | Generates a finished chart image directly with GPT-image-2 from a text description, across ten chart types such as flowcharts, architecture diagrams and SWOT grids in six visual styles. | SpaceZephyr/ | 174 | — | ~1.6k | Automated safety check: Pass | No licence | 3 mo ago |
| 14 | Cleans up a raw talking-head recording by cutting slips, filler and silences after your review, then assembles the cut into a finished MP4 with subtitles and a timeline preview. | SpaceZephyr/ | 1.6k | — | ~484 | Automated safety check: Pass | No licence | 1 mo ago |
| 15 | Walks a non-coder through structured questions about scene, style, color, text rules and consistency, then auto-generates a complete, ready-to-use batch image-generation skill. | SpaceZephyr/ | 174 | — | ~1.3k | Automated safety check: Pass | No licence | 3 mo ago |
| 16 | Extracts subtitles or a full transcript from YouTube, Xiaoyuzhou, Bilibili, Douyin and Xiaohongshu links, using speech recognition when a video has no subtitles. | SpaceZephyr/ | 1.6k | — | ~498 | Automated safety check: Pass | No licence | 1 mo ago |
| 17 | Generates PNG images for four common needs: Xiaohongshu covers, slide illustrations, charts and article logic diagrams, with twelve visual styles and automatic style suggestions. | SpaceZephyr/ | 174 | — | ~2k | Automated safety check: Pass | No licence | 3 mo ago |
| 18 | AI 产品经理顾问团总控。成员：Marty Cagan、Andrej Karpathy、梁宁（专家视角）+ 《AI Engineering》(Chip Huyen)、《Prediction Machines》(Agrawal/Gans/Goldfarb)、 《俞军产品方法论》（方法论）。 | SpaceZephyr/ | 160 | — | ~1.1k | Automated safety check: Pass | No licence | 3 mo ago |
| 19 | Generates a 3:4 Xiaohongshu post cover from a topic, title and optional portrait or product photo, choosing a layout and color style and keeping the subject's likeness intact. | SpaceZephyr/ | 1.6k | — | ~889 | Automated safety check: Pass | No licence | 1 mo ago |
| 20 | Generates ten logo variants in one run from a brand description or an uploaded reference image, with seven style options, using the Gemini image API and saving files to an Obsidian folder. | SpaceZephyr/ | 174 | — | ~870 | Automated safety check: Pass | No licence | 3 mo ago |
| 21 | 投资专家顾问团总控。成员：段永平、查理·芒格、霍华德·马克斯（专家视角）+ 《聪明的投资者》《穷查理宝典》《投资最重要的事》（方法论）。 | SpaceZephyr/ | 160 | — | ~481 | Automated safety check: Pass | No licence | 3 mo ago |
| 22 | 职业 Skill 工厂 2.0（career-skill-planner 升级版）。用户输入一个职业或行业，本 Skill 自动完成： (1) 遴选该行业 3 位顶尖专家，蒸馏其心智模型和决策方式，生成 3 个专家视角 Skill（参考女娲方法论）； (2) 遴选该行业 3 本顶尖书籍，提炼成可执行方法论，生成 3 个方法论 Skill（参考 book2skills 方法论）； (3) 生成… | SpaceZephyr/ | 160 | — | ~1.9k | Automated safety check: Warn | No licence | 3 mo ago |
| 23 | 小红书热点搜集与选题判断。按关键词/赛道拉取近期高互动笔记，输出热点表格、趋势判断和可直接开写的选题建议。当用户说"小红书热点""小红书最近火什么""查一下 XX 赛道的爆款""小红书选题""找小红书素材""这个词在小红书热不热""小红书热榜/热门笔记/爆款笔记""帮我看看小红书数据"时触发。也适用于用户报出一个赛道词（如"减脂餐""通勤穿搭""AI… | SpaceZephyr/ | 1.6k | — | ~2.5k | Automated safety check: Pass | No licence | 1 mo ago |
| 24 | 根据用户描述的故事内容，润色故事线并拆分为分镜脚本，批量生成风格一致的故事板插图。提供8种视觉风格选择，基于故事类型推荐最佳风格。调用Gemini API生成图片，保存到Obsidian图片目录。触发词："分镜故事"、"故事板"、"做个分镜"、"创建故事板"、"storyboard"、"画个故事"。 | SpaceZephyr/ | 174 | — | ~894 | Automated safety check: Pass | No licence | 3 mo ago |
| 25 | Marty Cagan 视角顾问。以 Cagan 的心智模型和判断方式，为 AI 产品经理场景做分析. An agent skill from SpaceZephyr/career.skill. | SpaceZephyr/ | 160 | — | ~1.3k | Automated safety check: Pass | No licence | 3 mo ago |
| 26 | 根据用户提供的文章、教程、SOP、清单或主题，使用 Codex 内置 imagegen 生图模型生成 3:4 小红书信息图与组图。固定采用轻盈 AI 产品信息图风：白色或浅薰衣草背景、黑色大标题、紫蓝与青柠绿强调、圆角卡片、线性科技图标、流程/对比/清单模块；支持单图和 6–9 张系列图，不需要 API Key… | SpaceZephyr/ | 1.6k | — | ~1.3k | Automated safety check: Pass | No licence | 1 mo ago |
| 27 | Andrej Karpathy 视角顾问。以 Karpathy 的心智模型和工程师式判断，为 AI 产品经理场景做分析。 | SpaceZephyr/ | 160 | — | ~1.2k | Automated safety check: Pass | No licence | 3 mo ago |
| 28 | 将 Markdown 内容转换为精美的图片海报。特别适合将播客摘要、文章内容转为社交媒体分享图片。固定 3:4 比例，支持 YouTube 视频封面作为头图。触发词：「转图片」「Markdown 转图片」「生成海报」「生成分享图」「把这个转成图片」。 | SpaceZephyr/ | 174 | — | ~675 | Automated safety check: Pass | No licence | 3 mo ago |
| 29 | 梁宁视角顾问。以梁宁的心智模型和判断方式，为 AI 产品经理场景做分析. An agent skill from SpaceZephyr/career.skill. | SpaceZephyr/ | 160 | — | ~1.1k | Automated safety check: Pass | No licence | 3 mo ago |
| 30 | 文章转手绘图解 B-roll——输入公众号文章(正文或链接)，优先抽取原文配图，把文章逻辑做成一支手绘线稿风格的动态图解视频，并调用真实视频模型(火山引擎 Seedance 2.0 或 libtv Agent)逐帧生成「手绘生长」动效，拼成成片。白底、黑色单线图标、单一蓝色强调、细曲线箭头，默认 4:3，垫在口播下方。当用户说「文章转图解视频」「手绘图解… | SpaceZephyr/ | 1.6k | — | ~1k | Automated safety check: Pass | No licence | 1 mo ago |
| 31 | 小红书个人笔记数据复盘——基于用户自己创作者后台（创作中心/蒲公英）的笔记数据，做漏斗定位、卡点归因和多篇横向规律发现。当用户说"笔记数据复盘""这条为什么没流量""帮我看看这条数据""小红书数据分析""曝光高但没人点""涨粉不行""哪类内容该加码""我导出了后台数据帮我看看"，或直接贴出后台数据截图/CSV/Excel/几个数字时使用。只分析用户自己账号的笔记表现，不抓取平台数据、不做刷量。 | SpaceZephyr/ | 1.6k | — | ~2.5k | Automated safety check: Pass | No licence | 1 mo ago |
| 32 | 全域内容搜索｜当提到小红书/B站/抖音关键词搜索、笔记/视频详情、评论、博主/UP主作品监控时使用。优先基于 Agent Reach / OpenCLI / bili-cli / 公开只读接口访问；Agent Reach 不可用时，小红书可用 Guaikei API 作为最后兜底。 | SpaceZephyr/ | 1.6k | — | ~797 | Automated safety check: Pass | MIT | 1 mo ago |
| 33 | 公众号长文写作（1500–4000 字）。先诊断作者手上已有什么（一个念头 / 一堆素材 / 半篇草稿 / 一份大纲 / 一篇不满意的成稿），再路由到对应的六种写法之一，产出成稿并过公众号专属质检。当用户说"写篇公众号""帮我写文章""这个主题怎么写""我有一堆素材不知道怎么组织""帮我扩写""这篇改一下""写不下去了""长文""深度文"时触发。 | SpaceZephyr/ | 1.6k | — | ~1.1k | Automated safety check: Pass | No licence | 1 mo ago |
| 34 | 公众号定位分析 + 三件套设计（账号简介 / 关注后自动回复 / 自定义菜单）。先通过分层访谈和历史文章反推，收敛出一句话定位，再派生出可直接粘贴进公众号后台的三份内容，全部带字数校验。当用户说"公众号定位""账号简介怎么写""功能介绍""公众号介绍""关注后回复""欢迎语""自动回复""菜单怎么设计""菜单栏""公众号装修""新号怎么起步""号没人关注"时触发。 | SpaceZephyr/ | 1.6k | — | ~1.4k | Automated safety check: Pass | No licence | 1 mo ago |
| 35 | 生成设计美观的图表 HTML 文件。支持 10 种图表类型：流程图、架构图、ER 图、商业模式画布、用户旅程图、思维导图、竞品分析图、SWOT 分析、产品路线图、组织架构图。支持 3 种内置视觉风格（黑白简约、深色暗调、Claude 暖色）+ 品牌风格扩展。 | SpaceZephyr/ | 174 | — | ~1.5k | Automated safety check: Pass | No licence | 3 mo ago |
| 36 | 【公众号配图版】把公众号文章/段落拆成逻辑关系图，做成可直接放进公众号的配图。生成逻辑关系 SVG，默认输出独立 HTML（可本地预览、可截图导出 PNG），也可交给 Codex/workbuddy 内置出图模型出成图片。支持递进、流程、循环、层次、对比、矩阵六种关系。当用户给文章/段落/论述并要求生成逻辑图、关系图、配图、可视化时触发。支持中文，一次可拆多张。 | SpaceZephyr/ | 1.6k | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 37 | 《Prediction Machines: The Simple Economics of Artificial Intelligence》(Agrawal / Gans / Goldfarb, HBR Press 2022 更新版) 方法论。把"AI = Cheap Prediction"经济学视角转化为 AI PM 的战略级判断框架， 用于：功能要不要 AI 化、AI 需求立项… | SpaceZephyr/ | 160 | — | ~1.3k | Automated safety check: Pass | No licence | 3 mo ago |
| 38 | 创作者全域内容搜索总控 Skill。用户发送平台名+关键词、平台链接，或要求分析博主、文章风格、热度、点赞、收藏、评论、爆款原因、选题方向时触发；根据平台和任务自动路由到小红书热门笔记、全域内容搜索、公众号爆款搜索、公众号赛道分析等分支 Skill。 | SpaceZephyr/ | 1.6k | — | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 39 | 公众号短文写作（1000 字以内，纯文字不配图）。把一个观察、一次实测、一段思考写成短平快的推送，或把长文/素材压成短文。核心是一套风格规则：第一人称不说教、去 AI 腔、靠分段做节奏、收尾落到具体画面。当用户说"写个短的""公众号短文""一千字以内""随手写一条""这事写个短篇""压成短文""不配图那种"时触发。 | SpaceZephyr/ | 1.6k | — | ~1.1k | Automated safety check: Pass | No licence | 1 mo ago |
| 40 | 40.Space Video 视频创作总控/导演。把一条视频从「参考素材 → 选题 → 脚本 → 剪辑 → B-roll → 字幕 → 封面」串成一条流水线，判断当前该走哪一步、调用哪个 space-video- 子技能，并在成片后做复盘。当用户说「做个视频」「我要拍条口播」「这个视频从头帮我做」「视频工作流」「video pipeline」，或不确定该用哪个视频子技能时触发。 | SpaceZephyr/ | 1.6k | — | ~527 | Automated safety check: Pass | No licence | 1 mo ago |
| 41 | 视频口播脚本撰写，两大特色——(1) 去 AI 味，把书面/AI 腔改成能念出口的真人口语；(2) 把模糊想法逼成一份精确到秒的分镜脚本（每个镜头讲什么、怎么呈现、停多久、怎么切）。当用户说「写口播脚本」「这段太 AI 了改成人话」「口播稿」「分镜脚本」「精确到秒」「script」「改成能念的」时触发。输入可以是选题正文、一段草稿，或一句模糊描述。 | SpaceZephyr/ | 1.6k | — | ~442 | Automated safety check: Pass | No licence | 1 mo ago |
| 42 | 视频选题与文案前端。做四件事——(1) 下载抖音/YouTube/B站参考视频并去水印、(2) 提取逐字稿、(3) 生成视频选题与钩子、(4) 撰写标题和口播正文/文案。当用户说「帮我想视频选题」「这条爆款拆一下」「下载这个视频」「提取文案/逐字稿」「起视频标题」「写口播正文」「video 选题」时触发。是整条视频流水线的入口。 | SpaceZephyr/ | 1.6k | — | ~571 | Automated safety check: Pass | No licence | 1 mo ago |
| 43 | 小红书账号整体诊断与竞品对标。对一个或多个小红书账号做量化体检——定位清晰度、内容垂直度、封面统一性、标题钩子率、更新节奏、互动率、爆款率、粉丝转化效率八个维度打分，定位卡点并给出可执行改动。当用户说"账号诊断""帮我看看我的号""我的号没起色/不涨粉/流量下滑""主页体检""账号定位有问题吗""竞品账号分析""对标账号拆解""这个博主为什么能起来""帮我和竞品比一比"，或直接贴出小红书主页链接… | SpaceZephyr/ | 1.6k | — | ~3.1k | Automated safety check: Pass | No licence | 1 mo ago |
| 44 | 小红书创作总控台。判断用户当前卡在哪一环，路由到对应的专项技能，并把多步骤工作流串起来执行。当用户说"做小红书""帮我运营小红书""小红书从头到尾走一遍""我想开始做小红书""小红书全流程""不知道从哪下手""帮我搞小红书"，或同时提出跨多个环节的需求（如"帮我想选题顺便写出来配好图"）时触发。单一环节的需求应直接使用对应专项技能，不必经过本技能。 | SpaceZephyr/ | 1.6k | — | ~1k | Automated safety check: Pass | No licence | 1 mo ago |
| 45 | 小红书起号定位顾问。用引导式对话帮真人创作者定下"做什么方向、给谁看、靠什么活下去"，产出赛道选择、定位句、人设三件套（账号名/简介/视觉）、内容支柱与前 20 篇选题、冷启动路径。当用户说"想做小红书但不知道做什么""帮我定位""起号""小红书发什么方向""账号定位""不知道发什么""从零开始做小红书""我适合做什么赛道""小红书怎么起步""重新定位一下账号"时触发。也适用于用户只丢来一句自我… | SpaceZephyr/ | 1.6k | — | ~3.2k | Automated safety check: Pass | No licence | 1 mo ago |
| 46 | 小红书笔记正文撰写。输入主题/产品/经历/素材，产出可直接发布的小红书正文（含开头 3 行、分段骨架、结尾互动、标签组合、合规自检）。覆盖种草测评、干货教程、个人故事、合集清单、避雷拔草、好物分享、经验复盘 7 种笔记类型。当用户说"写小红书""小红书文案""发笔记""笔记正文""种草文""种草笔记""避雷帖""干货笔记""帮我写篇小红书""这个怎么发小红书""小红书怎么写""笔记体检""改成小… | SpaceZephyr/ | 1.6k | — | ~3.6k | Automated safety check: Pass | No licence | 1 mo ago |
| 47 | 当用户想要生成图片、画图、绘画、创建图像、AI作画时使用此 Skill。支持文生图和图生图. An agent skill from SpaceZephyr/design-buddy. | SpaceZephyr/ | 174 | 2 repos | ~214 | Automated safety check: Pass | No licence | 3 mo ago |
| 48 | AI 全能图表生成器（扩展版）。一键生成 35+ 种设计美观的图表 HTML 文件，涵盖技术架构、流程逻辑、业务战略、数据可视化、信息展示 5 大类别。支持 3 种内置视觉风格（黑白简约、深色暗调、Claude 暖色）+ 品牌风格扩展。 | SpaceZephyr/ | 174 | — | ~1.6k | Automated safety check: Pass | No licence | 3 mo ago |
Questions, answered from the data.
What is the best skill by SpaceZephyr?
WeChat Hot Article Analysis from SpaceZephyr/creator-buddy ranks first of the 62 skills by SpaceZephyr listed here, with the highest score: its repository has 1.6k GitHub stars, its SKILL.md loads about 847 tokens and it passes the automated safety check with no findings. Next come Xiaohongshu Multi-Page HTML Cards and WeChat Viral Article Finder.
Are SpaceZephyr's skills official?
None yet. All 62 skills by SpaceZephyr listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.