Agent Skills Index

Agent skills index, page 24

Browse this index of public skills, or use search to access the full library.

Open search

No.: 2,301
html-ppt-tech-sharingOpenDesign internals: how the agent stream, sandbox, and artifacts work — an engineering deep-dive talk. Built as a decision-grade AI literacy deck for engineers, dev community.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,302
imagegenGenerate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
Repository: openai/skills
GitHub stars: 28,536Updated: Apr 15, 2026
No.: 2,303
sn-deep-research用于用户请求深度研究、系统性研究、竞品分析、方案对比、趋势分析或事实核查时。**遇到以下任一情况就主动使用本 skill，不要自行搜几条就回答**：①用户出现触发词：深度研究 / 深度调研 / 深入研究 / 全面研究 / 系统研究 / 调研 / 调查 / 尽调 / 行业研究 / 市场研究 / 竞品分析 / 政策研究 / 技术研究 / 趋势研究 / 事实核查 / 写一份研究报告 / 调研报告 / 深度报告 / research / deep research；②请求需要跨多来源取证、多维度对比、交叉验证才能给出可靠结论；③用户要求产出报告、白皮书、行业分析或尽调文档；④话题涉及最新政策/市场/产品/价格/法规，需要系统核查。无核验要求的简单常识问答不使用。模糊或宽泛的"研究/了解一下 X"也优先触发。仅不用于：一句话摘要、已给定单一来源的整理、纯文字润色改写。
Skill content language: Chinese
Repository: OpenSenseNova/SenseNova-Skills
GitHub stars: 6,023Updated: Aug 25, 2026
No.: 2,304
university-exam-prep大学备考苏格拉底式学习助手，专为应对"面向课本和PPT考试"设计。当用户说"帮我复习"、"准备考试"、"备考"、"期末复习"、"模拟学习"、"突击复习"等时触发。核心特点：(1)强制要求用户上传课本/PPT/考纲等原始材料——没有材料就无法有效辅导；(2)使用苏格拉底式提问法，不直接灌输而是引导思考；(3)专注于应用型和理解型内容，而非纯概念记忆；(4)模拟真实考试场景进行针对性练习；(5)分析材料识别高频考点和重难点。适用于大学各科目期中期末考试备考、突击复习、考前模拟。
Skill content language: Chinese
Repository: staruhub/ClaudeSkills
GitHub stars: 731Updated: Jul 21, 2026
No.: 2,305
maoxuan-enhanced毛泽东深度思维伙伴 v2.0：不只是框架应用，而是真正以毛泽东的世界观和方法论与你展开对话——先调查研究，再矛盾定位，再战略分析，再追问反诘。 12个核心心智模型 · 调查前置协议 · 毛式反问追问库 · 231篇原典锚点基于《毛泽东选集》五卷及原典著作全面提炼。触发词：毛选、教员、毛泽东、用毛泽东的方式、教员怎么看、帮我分析
Skill content language: Chinese
Repository: zhangtianruiwork-droid/Maoxuan-Changzheng
GitHub stars: 455Updated: Apr 22, 2026
No.: 2,306
script-forging将成熟故事稳定转化为可拍摄执行的影视剧本、分镜方案与后续 AI/拍摄可复用的数字资产清单。适用于用户要求"故事变剧本、小说改剧本、生成标准剧本、分场大纲、剧本一稿、剧本化提示包、用 AI 写剧本、剧本转分镜、分镜表、逐镜头分镜、完整分镜、拍摄分镜、AI 视频逐镜、镜头脚本、镜头表、场景清单、道具清单、角色出场清单、数字资产清单"等任务。核心流程：故事原文 → 专业形态建议 → 剧本化提示包 → 分场大纲 → 标准剧本 → 自检修订 → 分镜生成 → 数字资产清单。
Skill content language: Chinese
Repository: zhlmi/script-forging
GitHub stars: 279Updated: Jun 5, 2026
No.: 2,307
life-science-evidence-reviewGenerate evidence-based literature reviews, structured evidence synthesis, and knowledge-gap analyses for life science research.
Repository: ZZL-Zoro/Life-Science-Evidence-Review
GitHub stars: 34Updated: Aug 12, 2026
No.: 2,308
codex-visio-paper-figure-skillConvert paper figures and AI-generated diagrams into editable Microsoft Visio (.vsdx) files with native shapes, text, and connectors, then export to SVG/PDF/PNG/PPTX
Repository: reason-machines/codex-skills
GitHub stars: 2Updated: Jun 24, 2026
No.: 2,309
frontendBuilds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain way.
Repository: code-yeongyu/oh-my-openagent
GitHub stars: 70,728Updated: Oct 29, 2026
No.: 2,310
record-browser-gifRecord browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with `gh --attach`; publication requires gh v2.99.0 or later, and a GIF over 5 MiB is split into parts. Use when asked to make, record, or generate a GIF that demonstrates a browser workflow, and for every pull request that changes product-user-visible GUI behavior, which MUST include a GIF recorded from the pull request's real server and model flow.
Repository: deepseek-ai/deepseek-harness
GitHub stars: 273,539Updated: Oct 28, 2026
No.: 2,311
scrapling使用 scrapling 进行网页抓取和数据提取。自动选择 Fetcher，支持 Cloudflare/WAF 绕过、Session 登录、HTML 解析。当用户提到 scrape/crawl/fetch page/extract data/爬取/抓取/绕过Cloudflare/解析HTML/批量采集时触发。
Skill content language: Chinese
Repository: fengshao1227/ccg-workflow
GitHub stars: 5,977Updated: Mar 31, 2026
No.: 2,312
codebase-memory-mcpUse when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead or complex code, or handling explicit Codebase Memory requests. Otherwise skip tasks confined to a supplied known file, tiny one-file check, exact literal, configuration value, error string, or non-code text.
Repository: github/awesome-copilot
GitHub stars: 40,822Updated: Oct 7, 2026
No.: 2,313
cli-anything-libreofficeCommand-line interface for Libreoffice - A stateful command-line interface for document editing, producing real ODF files (ZIP archives with ...
Repository: HKUDS/CLI-Anything
GitHub stars: 58,293Updated: Apr 29, 2026
No.: 2,314
storytelling-advisorShape pitches, brand stories, presentations, and creative writing with narrative frameworks such as the Hero's Journey, Story Spine, and Freytag's Pyramid. Use when a user wants to structure, critique, or strengthen a story.
Repository: iflytek/skillhub
GitHub stars: 5,391Updated: Jul 31, 2026
No.: 2,315
baoyu-comicKnowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
Repository: JimLiu/baoyu-skills
GitHub stars: 27,306Updated: Nov 1, 2026
No.: 2,316
bgpt-paper-searchSearches BGPT scientific papers by topic or DOI and retrieves claim-level evidence extracted from full text, including experiments, reported statistics, scope, limitations, and provenance. Use for literature reviews, evidence synthesis, and finding experimental details beyond abstracts.
Repository: K-Dense-AI/scientific-agent-skills
GitHub stars: 56,174Updated: Oct 1, 2026
No.: 2,317
xgaida-x-nixi-audioЗвук Guildmaster: весь аудио-слой за фасадом IAudioService (FMOD-реализация, банки, шины и микс), ключи {contentId}.{action} и AudioCatalog, боевой и забеговый презентеры, звук интерфейса, плюс генеративный пайплайн scripts/audio — карта звука, нормализация, сборка банков. Зови на любую задачу про звук, SFX, амбиент, стингеры, громкость, подбор сэмплов, речь блипами и проигрывание музыки в игре, а также на правки под scripts/audio, FMOD Project, Core/Audio. НЕ применять к: СОЗДАНИЮ музыки и промптам Suno (music), боевому времени и симуляции (combat-sim), визуальному джусу (gamefeel-vfx), тех-доке об аудио (tech-scribe).
Skill content language: Russian
Repository: Kaliguri/Guildmaster-Autobattler
GitHub stars: 1Updated: Aug 3, 2026
No.: 2,318
screen-detox当用户刷手机/短视频/社交媒体上瘾、感觉空虚、想戒断多巴胺零食时调用。核心理念: 所有屏幕活动与更少幸福相关(作者断言无例外); 屏幕=用长期后果换短期快感的多巴胺零食; 用习惯替换五步戒断。不适用于: 工作需要屏幕的职业场景(区分工作屏幕与消费屏幕)。 Triggers: 刷手机/上瘾/短视频/社交媒体/多巴胺/戒断/屏幕时间/screen time/dopamine/addiction
Skill content language: Chinese
Repository: kangarooking/cangjie-skill
GitHub stars: 12,220Updated: Aug 30, 2026
No.: 2,319
google-meetJoin a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Oct 29, 2026
No.: 2,320
investment-researchAI Berkshire skill: 投资研究：巴菲特-芒格-段永平-李录四大师综合分析框架. Source: skills/investment-research.md.
Skill content language: Mixed languages
Repository: xbtlin/ai-berkshire
GitHub stars: 17,019Updated: Oct 18, 2026
No.: 2,321
xiaobei-skill-rebuild-image-in-powerpointUse when a user wants Codex to directly operate PowerPoint and reconstruct an entire reference image as editable PowerPoint objects while preserving its full layout, labels, connectors, and visual relationships. Do not use for paper-to-deck generation or VBA-only output.
Repository: xiao24bei/xiaobei-skill
GitHub stars: 604Updated: Aug 27, 2026
No.: 2,322
paper-writerDrafts publishable paper prose from the author's own materials, from a single paragraph to a full manuscript, across STEM and non-STEM fields. Every factual claim traces to user input, verified retrieval, or field common knowledge; citations pass an independent verification ladder; delivery is clean prose with zero placeholder tags. Use when the user asks to write a section, turn an idea or results into paper text, or draft a full paper.
Repository: HKUSTDial/Supervisor-Skills
GitHub stars: 11,786Updated: Jul 4, 2026
No.: 2,323
flova-ecommerce-visual-kitUse when 用户要基于产品图生成电商产品视觉全案、主图、详情页、卖点图、白底 KV、材质特写、对比验证图或平台电商静态图集；默认不进入视频流程。
Repository: LYL1015/JarvisHub
GitHub stars: 623Updated: Jul 26, 2026
No.: 2,324
zizhi-tongjian资治通鉴智慧锦囊：精通《资治通鉴》，用历史智慧解决现代职场、管理、人生困境。绝对忠于史实，强制出处说明，降维翻译，结构化输出可操作建议。
Skill content language: Chinese
Repository: memory125/Chinese-Classics-Skills
GitHub stars: 8Updated: Mar 25, 2026
No.: 2,325
openakita-skills-chinese-novelistGuide AI to write Chinese novels and fiction with structured character creation, plot architecture (起承转合), dialog writing, scene description, and genre-specific techniques for 玄幻, 都市, 悬疑, and 言情 genres.
Skill content language: Chinese
Repository: openakita/openakita
GitHub stars: 2,012Updated: Apr 24, 2026
No.: 2,326
openjiuwen-deepsearch知识增强型深度检索与深度研究，支持查询规划、信息收集、理解反思、研究报告生成等多 Agent 协同。使用场景：金融分析研报、学术与政策研究、企业级深度搜索等复杂推理任务，可以生成Markdown、Doc和Html格式的研究报告。**每次使用该技能之前都先完整阅读一遍SKILL.md学习技能。**
Skill content language: Chinese
Repository: openJiuwen-ai/jiuwenswarm
GitHub stars: 8,565Updated: Jul 27, 2026
No.: 2,327
jsvmp-bytecode-recoveryJSVMP/VMP 虚拟机保护逆向方法论 — 面对大数组+解释器+派发循环这类把原始逻辑编译成字节码、无法用 AST 直接还原的硬骨头（抖音 a_bogus、极验4 w、瑞数、携程等），用"先定位解释器→插桩记录 opcode→反汇编→重建目标路径"的纪律化流程逆向，而非盲目扣代码或硬补环境。触发词：「JSVMP」「虚拟机保护」「vmp」「字节码」「opcode」「大数组解释器」「a_bogus」「w参数」「派发循环」「switch解释器」「扣不动这段代码」。当目标加密逻辑是 VM 字节码、AST 反混淆已确认无效时使用。边界：仅处理 VM 字节码还原方法论；还原出算法后转交 param-encryptor；若选择放弃纯算转走补环境则转交 env-patcher。
Skill content language: Chinese
Repository: woxiangyangzhimao/skills
GitHub stars: 14Updated: Jul 2, 2026
No.: 2,328
generate-master-plan基于 Jack Daniels 跑步训练法体系，根据用户的赛事目标、备赛周期、历史训练数据与当前能力水平，生成结构化全周期马拉松备赛训练计划。计划包含阶段划分、阶段目标、负荷规则、关键训练课、力量训练与恢复策略，遵循科学进阶逻辑，控制训练风险，避免过度训练与运动损伤，助力用户达成赛事目标。
Skill content language: Chinese
Repository: zhaochy1990/running
GitHub stars: 0Updated: Oct 27, 2026
No.: 2,329
construction-plan施工方案智能生成助手。根据工程类型、规模、地质条件、工期要求等信息，自动生成结构化施工方案。适用场景： (1) 用户说"帮我写施工方案"、"生成施工组织设计"、"编制专项施工方案" (2) 涉及土建、市政、装饰装修、机电安装、桥梁、隧道等各类工程施工方案编制 (3) 需要生成安全专项方案（高支模、深基坑、脚手架、起重吊装等危大工程） (4) 施工方案审查、优化、补充完善 (5) 施工工序策划、资源配置计划、质量控制措施编制
Skill content language: Chinese
Repository: Kernel8901/ai-agent-skills-classification
GitHub stars: 6Updated: Apr 4, 2026
No.: 2,330
directYandex Direct (API v5/v501) advertising audit, management, and optimization for Unified Performance Campaigns (ЕПК) and combinatorial ads. Full account audits, campaign management, keyword and autotargeting operations, reports with Metrika goals, weekly budget analysis, and optimization recommendations for Russian market PPC. Triggers on: "Яндекс Директ", "Yandex Direct", "директ", "ЕПК", "РСЯ", "YAN", "direct audit", "direct campaigns", "direct report", "direct optimize".
Repository: Silverov/yandex-direct-skill
GitHub stars: 59Updated: Oct 22, 2026
No.: 2,331
traditional-chinese-medicine-master中医诊疗 — 中医临床医师的认知操作系统 (经典理论阴阳五行脏腑气血经络六经卫气营血三焦 + 四诊八纲 + 治法 + 方剂学经方时方 + 中药学四气五味归经炮制 + 针灸学经络穴位手法灸法 + 推拿按摩 + 中医各科内外妇儿骨伤皮肤眼耳鼻喉肛肠老年急症 + 中西医结合 + 循证中医 + NATCM 监管 + 中医诊所备案 + 国家级名老中医学术继承人 — 不含道家修炼 / 风水算命 / 中医养生科普 / 中医美容 / 民族医学藏蒙维傣) (Traditional Chinese Medicine (TCM) clinical practice — the cognitive operating system of practicing TCM physicians covering (a) 经典理论 (阴阳/五行/脏腑/气血津液/经络/六淫/七情/六经/卫气营血/三焦) classical theory, (b) 四诊 (望闻问切) clinical observation/inquiry/pulse + 八纲 (阴阳/表里/寒热/虚实) syndrome differentiation, (c) 治法 (汗吐下和温清消补 + 扶正祛邪) therapeutic principles, (d) 方剂学 (经方时方验方) formula science, (e) 中药学 (四气五味/归经/七情/炮制/配伍禁忌) materia medica, (f) 针灸学 (经络穴位/手法/灸法/电针) acupuncture+moxibustion, (g) 推拿按摩 tuina massage, (h) 中医各科 (内/外/妇/儿/骨伤/皮肤/眼/耳鼻喉/肛肠/老年/急症) clinical specialties, (i) 中西医结合 integrative medicine, (j) 循证中医 + 临床流行病学 evidence-based TCM + 现代研究, (k) 中医诊所备案 / 中医师资格 / NATCM 监管 / 药典 / GMP regulatory framework, (l) 国家级名老中医学术继承人项目 transmission program; NOT 道家修炼 / 风水 / 算命八字 (那是玄学不是中医), NOT 中医养生科普 (是衍生不是临床主体), NOT
Skill content language: Chinese
Repository: swaylq/master-skill
GitHub stars: 174Updated: May 18, 2026
No.: 2,332
afsim-projectAFSIM 2.9.0 仿真技能：创建、编译、调试、可视化和分析仿真场景。工作流：写 .txt → mission.exe 编译 → 修复错误 → mystic.exe 可视化 → Python 分析。
Skill content language: Chinese
Repository: abydym/AstraLogic
GitHub stars: 4Updated: Jun 11, 2026
No.: 2,333
kingstvis-socketUse when running KingstVIS capture/export through SocketAPI with one explicit `capture` command and fully specified parameters.
Repository: docevilOck/agent-skills-hook
GitHub stars: 4Updated: Jun 3, 2026
No.: 2,334
male-beast-tamingUse when generating or analyzing male-oriented beast taming, pet evolution, monster partner, creature collection, or battle companion outlines and chapter outlines.
Skill content language: Chinese
Repository: Mochocyang/QMAI
GitHub stars: 859Updated: Oct 4, 2026
No.: 2,335
drawioAlways use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF. Exception: in a chat that shows diagrams inline (VS Code's or Cursor's own chat, Claude.ai, ChatGPT) where the draw.io MCP server's create_diagram tool is available, call that tool instead, unless the user asks for a file or an export. Claude Code, Codex and Copilot CLI, also in their VS Code and JetBrains extensions, don't show diagrams inline: use this skill there.
Repository: jgraph/drawio-mcp
GitHub stars: 5,648Updated: Oct 16, 2026
No.: 2,336
naver-shopping-search네이버 쇼핑 공개 BFF JSON을 k-skill-proxy로 조회해 상품 후보, 최저가, 판매처 링크를 보수적으로 가격비교한다. 돌쇠에서는 공식 표면을 통한 후속 액션까지 진행한다.
Repository: NomaDamas/k-skill
GitHub stars: 8,276Updated: Sep 15, 2026
No.: 2,337
llm-trading-agent-security日本語翻訳：このファイルは llm-trading-agent-security 用の日本語翻訳が必要です
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Oct 1, 2026
No.: 2,338
book-distiller炼金书：输入书名或电子书，自动深度调研→方法论提炼→生成该书的可运行框架Skill。两种入口：(1)明确书名→直接蒸馏 (2)模糊学习需求→诊断荐书→再蒸馏。触发词：「蒸馏这本书」「炼金XX」「把XX这本书做成skill」「XX的方法论skill」「更新XX的书skill」。模糊需求也触发：「我想系统学谈判」「有没有一本书能帮我提升XX」。 English triggers: "distill [book]", "turn [book] into a skill", "book to framework skill". 不在用户只要书摘、读书笔记、买书推荐或查某个概念时触发——只在需要生成「可运行的方法论Skill」时激活。
Skill content language: Chinese
Repository: AINoSleep/book-distiller-skill
GitHub stars: 5Updated: Aug 17, 2026
No.: 2,339
prop-prompt道具最终提示词规范 — 白底单品静物，标准产品摄影视角：比例准确、边缘完整、背景不承载叙事
Skill content language: Chinese
Repository: chatfire-AI/huobao-drama
GitHub stars: 17,026Updated: Sep 5, 2026
No.: 2,340
mx-zixuan妙想自选管理skill，基于东方财富通行证账户数据及行情底层数据构建，支持通过自然语言查询、添加、删除自选股。
Skill content language: Chinese
Repository: datawhalechina/hello-agents
GitHub stars: 86,146Updated: May 17, 2026
No.: 2,341
douyin-video-forge抖音短视频全链路自动化制作。适用于：收到客户项目需要制作抖音推广视频、策划短视频内容、生成视频脚本、分析抖音热点趋势、制作爆款短视频。通过浏览器采集抖音热榜和视频数据，生成分段脚本，调用可灵API生成视频并拼接成片。
Skill content language: Chinese
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: Jun 1, 2026
No.: 2,342
blog-draft根据想法和资料撰写博客草稿。适用于用户想写博客、基于研究创建内容，或起草文章的场景。流程会引导你完成调研、头脑风暴、提纲编写和带版本控制的迭代撰写。
Skill content language: Chinese
Repository: luongnv89/claude-howto
GitHub stars: 46,582Updated: Apr 6, 2026
No.: 2,343
field-notes-editorial-templateEditorial "Field Notes" report template with soft paper background, serif hero typography, rounded pastel insight cards, and a retention chart panel. Use when users ask for a premium magazine-style business report, board memo one-pager, or elegant data storytelling layout.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: May 9, 2026
No.: 2,344
antigravity-cliOperate the Antigravity CLI (agy): plugins, auth, sandbox.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Jun 21, 2026
No.: 2,345
configure-channelConfigure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: Aug 19, 2026
No.: 2,346
guizang-ppt-skill生成横向翻页网页 PPT（单 HTML 文件），含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格：① "电子杂志 × 电子墨水"（衬线 + 流体背景 + 暖色） ② "瑞士国际主义"（无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮）。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT，或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"时使用。
Skill content language: Chinese
Repository: proma-ai/Proma
GitHub stars: 2,243Updated: Aug 8, 2026
No.: 2,347
xiaozhi-teach-math-lesson-planner数学教师的备课工具（初中与高中；高中覆盖必修与选择性必修）：把一节数学课的概念建构路径、例题示范与变式训练排成可上的教案。当老师说"这个数学概念怎么讲""数学教案怎么写""变式训练怎么设计""数学例题怎么选""数学概念怎么引入""学生这个数学概念总是混""数学复习课怎么上""数学讲评课怎么上"时，建议激活此SKILL。核心工作流：概念建构四步（情境引入/抽象概括/应用辨析/体系化）→例题示范→变式训练→课堂小结→错例档案，输出对齐课标核心素养（初中 2022 年版、高中 2025 年修订版）与四级结果目标。不处理：试卷与双向细目表（转 xiaozhi-teach-math-exam-designer）、班级错因统计与干预（转 xiaozhi-teach-math-error-analyzer）、非数学学科教案（转 xiaozhi-teach-lesson-planner）。
Skill content language: Chinese
Repository: qizhitang/xiaozhi-skills
GitHub stars: 111Updated: Oct 21, 2026
No.: 2,348
lottery-draw-query查询各类彩票开奖结果、历史开奖记录、中奖情况及彩票分类，适用于彩票开奖查询、历史追溯、奖池了解等场景
Skill content language: Chinese
Repository: qq5855144/GitHubM
GitHub stars: 29Updated: May 30, 2026
No.: 2,349
space-chart-image使用 AI 图片生成技术绘制美观的图表。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。6 种内置视觉风格。触发词："画个 XX 图"、"生成商业模式画布"、"做个架构图"、"画 ER 图"、"帮我画个流程图"、"生成用户旅程图"、"做个思维导图"、"竞品分析图"、"SWOT 分析图"、"产品路线图"、"组织架构图"、"帮我可视化图表"。【公众号配图版】用户给内容 → 产出公众号配图。优先用当前环境内置出图模型（Codex 内置 image_gen/image2、workbuddy 出图模型）直接生成 PNG；无内置模型时回退 scripts/ 下的 API 脚本。
Skill content language: Chinese
Repository: SpaceZephyr/creator-buddy
GitHub stars: 1,830Updated: Aug 4, 2026
No.: 2,350
web-online-exhibition-masterWeb 线上展览开发 (虚拟展厅) (Web 线上展览 / 虚拟展厅开发 (从业者/工程视角) — 用 web 技术开发线上展览、虚拟展厅、云展会、数字展馆，覆盖 3D 空间、全景漫游、WebXR、文博数字化、营销云展厅、3D 商品展示等形态。覆盖: (a) 技术栈 — 3D web(Three.js / React Three Fiber / Babylon.js / Google model-viewer / WebGL / WebGPU)、全景(Pannellum / Marzipano / Photo Sphere Viewer / krpano / 720云)、WebXR(WebXR Device API / A-Frame)、资产管线(glTF·GLB / Draco / Meshopt / KTX2 纹理压缩 / gltf-transform / LOD); (b) 自研 vs SaaS 平台选型(国内: 众趣 / 酷雷曼 / 比目鱼 / 会鸽 / 3DVista; 海外: Matterport / Kuula / Artsteps / Spatial); (c) 性能优化(大场景加载 / 模型轻量化 / draw call / 移动端 / 首屏 / 显存)——web 3D 第一性难题; (d) 策展与导览(动线设计 / 热点 hotspot / 语音讲解 / 交互); (e) 文博数字化(IIIF / 数字孪生 / 高清文物) 与会展·电商商业化(营销云展厅 / 数据埋点 / 线索转化); (f) 部署(CDN / 流式加载 / 跨端兼容 / WebGL 降级)。学派分歧: 自研 Three.js vs SaaS 平台、真 3D 重场景 vs 720 全景轻量、WebGL vs WebGPU、文博考据派 vs 营销转化派、沉浸优先 vs 加载优先。不含: 线下展陈 / 展台搭建、原生 VR App(非 web)、通用 3D 游戏开发、纯 3D 建模教程。) Master OS — automated mastery of Web 线上展览 / 虚拟展厅开发 (从业者/工程视角) — 用 web 技术开发线上展览、虚拟展厅、云展会、数字展馆，覆盖 3D 空间、全景漫游、WebXR、文博数字化、营销云展厅、3D 商品展示等形态。覆盖: (a) 技术栈 — 3D web(Three.js / Reac
Skill content language: Chinese
Repository: swaylq/master-skill
GitHub stars: 174Updated: Jun 7, 2026
No.: 2,351
docx创建、编辑、校验和转换 Word DOCX，支持把完整 LaTeX 论文转换为 DOCX，以及数学建模论文模板、原生公式、三线表、修订和批注。
Skill content language: Chinese
Repository: XiaoMaColtAI/math-modeling-skill
GitHub stars: 1,897Updated: Aug 15, 2026
No.: 2,352
slide-makerBuild, redesign, and critique clean, presentation-grade slide decks (.pptx) for any audience — research/lab meetings, work status updates, conference talks, stakeholder readouts, thesis defenses, teaching, webinars. Use whenever the user wants to make, create, redo, clean up, improve, or review slides / a deck / a presentation — e.g. "make slides for my project", "build a deck from this paper/code/doc", "turn these results into slides", "redesign this pptx", "my slides are too dense", "review my deck and tell me what's weak", "make a slide about X", "help me present this work". Works with or without a template (matches theirs, else designs a clean one) and with or without source material (mines provided code/docs/figures, else web-researches and fact-checks), in any language (e.g. English or Chinese). Interviews first, then runs an actor–critic loop until an independent critic consents. Trigger even without the words "skill", "deck", or "pptx".
Repository: addsumtech/slides_maker
GitHub stars: 645Updated: Oct 31, 2026
No.: 2,353
python-patternsPythonic idiomlar, PEP 8 standartları, type hint'ler ve sağlam, verimli ve bakımı kolay Python uygulamaları oluşturmak için en iyi uygulamalar.
Skill content language: Turkish
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jun 7, 2026
No.: 2,354
content-hash-cache-pattern使用SHA-256内容哈希缓存昂贵的文件处理结果——路径无关、自动失效、服务层分离。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Mar 3, 2026
No.: 2,355
continuous-learning-v2基于本能的学习系统，通过钩子观察会话，创建带置信度评分的原子本能，并将其进化为技能/命令/代理。v2.1版本增加了项目范围的本能，以防止跨项目污染。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jul 4, 2026
No.: 2,356
deployment-patternsDeployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Mar 23, 2026
No.: 2,357
huashu-data-pro数据分析与办公提效全能助手。覆盖数据处理、分析洞察、报告撰写、PPT制作、数据可视化的端到端工作流。始终从专家视角出发，帮用户多想一步。遇到不确定的问题主动与用户确认。支持：Excel数据分析、投放数据复盘、ROI测算、数据可视化、报告生成、PPT制作、公式生成。当用户提到"分析数据"、"做报告"、"做PPT"、"Excel"、"投放分析"、"ROI"、"复盘"、 "周报"、"月报"、"数据处理"、"图表"、"可视化"、"汇报"、"表格"、"公式"时使用此技能。
Skill content language: Chinese
Repository: alchaincyf/huashu-skills
GitHub stars: 2,209Updated: Sep 22, 2026
No.: 2,358
business-operations-skillsRoute internal operations requests to the right BizOps skill: process, vendors, capacity, internal comms, SOPs, procurement. Use whenever the user asks where the bottleneck is or about vendor health.
Repository: alirezarezvani/claude-skills
GitHub stars: 29,341Updated: Nov 3, 2026
No.: 2,359
grill-with-docsUse when a plan should be stress-tested against the project's own docs (CONTEXT.md glossary, docs/adr decisions), or the user says 'grill with docs'. Scans ADRs with adr_scanner.py and updates the docs inline as terms and decisions settle.
Repository: alirezarezvani/claude-skills
GitHub stars: 29,341Updated: Oct 30, 2026
No.: 2,360
ffmpegVideo and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.
Repository: calesthio/OpenMontage
GitHub stars: 76,985Updated: Mar 29, 2026
No.: 2,361
testcase-generator测试用例生成器 - 基于等价类划分和边界值分析理论,按测试点(POINT)分批生成高质量测试用例,输出为 Markdown 格式。当用户执行 /testcase-gen 命令或需要生成测试用例时使用。
Skill content language: Chinese
Repository: chyax98/twu
GitHub stars: 12Updated: Jan 22, 2026
No.: 2,362
develop-web-gameUse when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Oct 24, 2026
No.: 2,363
senior-backendComprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Dec 20, 2025
No.: 2,364
midjourney将中文室内设计场景描述、关键词及建筑特征翻译成适用于Midjourney的英文提示词。
Skill content language: Mixed languages
Repository: ECNU-ICALK/AutoSkill
GitHub stars: 610Updated: Mar 13, 2026
No.: 2,365
1997-pro-web-reverse-casebook基于 1997.pro 全站 42 篇文章提炼的 Web/JS 逆向案例知识库。适用于 Akamai/Kasada/PX/reese84/同盾/a_bogus/腾讯滑块/阿里滑块/JSVMP/227/226/wasm/protobuf/rid/fuid/fs/bx-pp/run_js/storage.estimate/animationend 等案例线索，以及风控指纹、补环境、JSVMP/平坦流/WASM、验证码、协议参数链的场景判断、方法路由与案例对照；默认与 web-js-reverse-master-flow 及 jshook + js-reverse + chrome-devtools-mcp 三 MCP 协同使用。
Skill content language: Chinese
Repository: firstrui/codex-reverse-skills
GitHub stars: 46Updated: Mar 25, 2026
No.: 2,366
linkedin-post-formatterFormat and draft compelling LinkedIn posts using Unicode bold/italic styling, visual separators, structured sections, and engagement-optimized patterns. USE FOR: draft LinkedIn post, format text for LinkedIn, create social media post, write thought leadership post, convert content to LinkedIn format, LinkedIn carousel text, Unicode bold italic formatting.
Repository: github/awesome-copilot
GitHub stars: 40,822Updated: Apr 15, 2026
No.: 2,367
wecomcracker从当前 Windows 用户自己的企业微信本地聊天中重建个人工作历史：整理有证据支持的时间线，找回任务与承诺，识别决定、期限、交付物、阻塞、依赖、已完成事项和未闭环跟进，并生成可审阅的项目管理交接预览。当企业微信 API 或 CLI 的历史范围不足时，使用零第三方 Python 依赖、Windows CNG 和不可变只读 SQLite 查询来解密、校验、检查、列出和搜索本地 wxSQLite3 数据库。不得用于其他人的账号、远程机器、绕过 Windows 权限、发送消息，或把推断出的任务直接写入外部项目系统。
Skill content language: Chinese
Repository: kizzhang/wecomcracker
GitHub stars: 5Updated: Jul 21, 2026
No.: 2,368
no-mistakesValidate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach the configured push target. Use when the user asks to run no-mistakes, gate or ship or validate their changes, push safely, asks you to do a task and then validate it, or invokes /no-mistakes.
Repository: kunchenguid/no-mistakes
GitHub stars: 9,144Updated: Nov 3, 2026
No.: 2,369
backend-code-reviewReview backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `src/backend/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.
Repository: langflow-ai/langflow
GitHub stars: 156,356Updated: Mar 19, 2026
No.: 2,370
gelan-trinity-trading格兰书院三位一体交易系统。均线(55+233)+结构(ABCD)+时空(级别嵌套)的完整交易方法论，含仓位管理、做T/加仓抉择、止盈止损、集合竞价、主涨段判断、关键K、维科夫法。
Skill content language: Chinese
Repository: LisonEvf/finance-skills
GitHub stars: 2Updated: May 15, 2026
No.: 2,371
scholar-slidesUse when the user wants a research paper, arXiv/DOI link, or research topic turned into academic slides — journal club / lab meeting (组会汇报), thesis defense (答辩幻灯片), or conference / job talk (学术报告) — or shares a paper and asks to "make slides / 做成 PPT / 讲一下这篇论文", especially when equations, numbers, figures, and citations must stay accurate and editable. NOT for marketing/pitch decks with no scholarly source, NOT for writing the paper itself, and NOT for stylized visual/image decks (use paper-slide-deck for those). No poster or grant-pitch workflow exists in this skill.
Repository: luwill/research-skills
GitHub stars: 876Updated: Oct 24, 2026
No.: 2,372
tooluniverse-natural-product-dereplicationDereplicate a putative natural product and assign its chemical taxonomy. Use to answer "is [compound] a known natural product", "what microbe/organism produces [compound]", "what chemical class is [compound]", "dereplicate this metabolite (by formula/exact mass/InChIKey/SMILES)", or "classify this molecule into ChemOnt". Searches NPAtlas for known microbial natural products (producing organism + literature reference), assigns the ChemOnt kingdom→superclass→class→subclass hierarchy via ClassyFire, resolves systematic IUPAC names to structure via OPSIN, and cross-references identity in PubChem. NOT for general drug/compound identity or ADMET (use tooluniverse-chemical-compound-retrieval / tooluniverse-small-molecule-discovery) and NOT for metabolomics pathway/enrichment analysis (use tooluniverse-metabolomics skills).
Repository: mims-harvard/ToolUniverse
GitHub stars: 1,777Updated: Oct 6, 2026
No.: 2,373
h3-prompt-writingWrite MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.
Repository: MiniMax-AI/MiniMax-H3
GitHub stars: 11,473Updated: Aug 11, 2026
No.: 2,374
pp-faa-registryLook up any US aircraft by tail number from the terminal — live FAA registry inquiries plus a daily-synced offline copy of the full registry for fleet queries, Mode S hex decoding, and expiration alerts no other tool has.
Repository: mvanhorn/printing-press-library
GitHub stars: 1,918Updated: Jul 13, 2026
No.: 2,375
article-magazineHuashu / huashu-md-html-inspired magazine article layout for turning Markdown or notes into a polished long-form HTML essay.
Skill content language: Chinese
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,376
mapsGeocode, POIs, routes, timezones via OpenStreetMap/OSRM.
Repository: NousResearch/hermes-agent
GitHub stars: 260,788Updated: Aug 12, 2026
No.: 2,377
ecom-copy-assistant一站式生成电商平台商品详情页文案，包括标题、核心卖点、规格参数和FAQ问答，适配淘宝、京东、亚马逊三大平台的特定风格规范。当用户需要撰写或优化商品文案，提及产品标题、卖点提炼、商品详情页、listing文案、五点描述、规格表、产品FAQ，或直接提到淘宝标题、京东文案、亚马逊listing、A+页面、电商文案、商品上架等场景时触发。
Skill content language: Chinese
Repository: rongxinzy/RongxinAI
GitHub stars: 161Updated: Oct 25, 2026
No.: 2,378
stripe-integrationImplement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stripe payments, building subscription systems, or implementing secure checkout flows.
Repository: wshobson/agents
GitHub stars: 42,226Updated: May 22, 2026
No.: 2,379
gpt-imageGenerate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation.
Repository: wuyoscar/GPT-Image2-Skill
GitHub stars: 6,005Updated: Sep 9, 2026
No.: 2,380
xiaobei-skill-academic-paper-to-pptUse for 小北在读研 / XiaoBei academic paper-to-PPT workflows: generate thesis-defense or project-report decks from uploaded papers, literature, reports, technical documents, and optional PPTX visual templates. Produces a source-grounded outline, an imagegen visual scheme, one complete bitmap per slide, an imagegen provenance manifest, and an image-only PPTX. Do not use when the user needs editable slide text or native editable charts.
Repository: xiao24bei/xiaobei-skill
GitHub stars: 604Updated: Aug 26, 2026
No.: 2,381
sd25-peSeedance 2.5 prompt optimizer (火山方舟官方 sd25-pe 原文 + 本 app 适配). Decide by what the user wants produced. Wants a video (生成视频 / 出片 / 让它动起来): do NOT pick this skill from those words — load the catimation-video entry and follow its tier plan, which names this skill when it is due. Wants a Seedance 2.5 prompt (writing / rewriting / optimizing a 2.5 提示词, 2.5 的编辑 / 延长 / 关键帧 / 宫格分镜 / 白模 / 多素材主体映射): load this directly. Seedance 2.0 家族的提示词改用 sd2-pe。
Skill content language: Chinese
Repository: 2799662352/ai-image-master
GitHub stars: 8Updated: Sep 6, 2026
No.: 2,382
jpa-patternsPatrones JPA/Hibernate para diseño de entidades, relaciones, optimización de consultas, transacciones, auditoría, indexación, paginación y pooling en Spring Boot.
Skill content language: Spanish
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jun 7, 2026
No.: 2,383
lead-intelligence日本語翻訳：このファイルは lead-intelligence 用の日本語翻訳が必要です
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Oct 1, 2026
No.: 2,384
hermes-imports将本地 Hermes 操作员工作流转换为经过清理的 ECC 技能和发布包工件。在准备将 Hermes 工作流用于公共 ECC 重用而不泄露私有工作区状态、凭据或仅本地路径时使用。
Skill content language: Chinese
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: May 11, 2026
No.: 2,385
fastapi-patternsFastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Jun 7, 2026
No.: 2,386
ito-trainingInspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. ECC implements no training stack of its own.
Repository: affaan-m/ECC
GitHub stars: 297,201Updated: Aug 12, 2026
No.: 2,387
lanhu-design-to-html从蓝湖设计稿链接获取设计信息并还原为HTML页面。Invoke when user provides a lanhuapp.com link, asks to analyze/restore a Lanhu design mockup, or needs to extract design specs from Lanhu.
Skill content language: Chinese
Repository: ApeMan1024/lanhu-design-to-html
GitHub stars: 6Updated: Jul 7, 2026
No.: 2,388
taobao-keyword-searchSearch Taobao and Tmall product listings by keyword, returning paginated product cards with title, price, shop, image, sales, and tags. Use when user asks to search Taobao, find products on Taobao/Tmall, scrape Taobao search results, get product listings from Taobao, collect Taobao items by keyword, 搜索淘宝, 淘宝关键词搜索, 采集淘宝商品, 抓取淘宝搜索结果, 淘宝天猫商品列表. Also applies to bulk keyword searches, price monitoring across keywords, and competitive product research on Taobao.
Repository: browser-act/skills
GitHub stars: 6,325Updated: Jun 10, 2026
No.: 2,389
ltx2AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.
Repository: calesthio/OpenMontage
GitHub stars: 76,985Updated: Mar 29, 2026
No.: 2,390
revopsWhen the user wants help with revenue operations, lead lifecycle management, or marketing-to-sales handoff processes. Also use when the user mentions 'RevOps,' 'revenue operations,' 'lead scoring,' 'outbound pipeline stages,' 'lead routing,' 'MQL,' 'SQL,' 'pipeline stages,' 'deal desk,' 'CRM automation,' 'marketing-to-sales handoff,' 'data hygiene,' 'leads aren't getting to sales,' 'pipeline management,' 'lead qualification,' or 'when should marketing hand off to sales.' Use this for anything involving the systems and processes that connect marketing to revenue. For cold outreach emails, see cold-email. For email drip campaigns, see emails. For pricing decisions, see pricing.
Repository: coreyhaines31/marketingskills
GitHub stars: 58,664Updated: Oct 27, 2026
No.: 2,391
academic-cv-builderFormat CVs for academic positions, including publications, grants, teaching, and research experience. Use when the user mentions academic CV, faculty job, tenure-track, postdoc, PhD, research position, or needs to list publications, grants, conferences, or teaching.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: May 16, 2026
No.: 2,392
cloud-devopsCloud infrastructure and DevOps workflow covering AWS, Azure, GCP, Kubernetes, Terraform, CI/CD, monitoring, and cloud-native development.
Repository: davila7/claude-code-templates
GitHub stars: 33,139Updated: Oct 24, 2026
No.: 2,393
dbs-ai-check扫描文案中的 AI 写作特征并输出检测报告，默认只诊断不改写；用户看完报告说「我想改」后，逐条追问写法背后的意图并给出修改方向。用户要求检查 AI 味、AI 痕迹或机器化表达时使用。
Skill content language: Chinese
Repository: dontbesilent2025/dbskill
GitHub stars: 11,269Updated: Oct 24, 2026
No.: 2,394
cli-anything-qgisStateful QGIS CLI for projects, writable layers, features, layouts, exports, and qgis_process operations using the real QGIS runtime.
Repository: HKUDS/CLI-Anything
GitHub stars: 58,293Updated: Apr 18, 2026
No.: 2,395
script-to-shot-engine基于用户已有的人物、场景、武器与道具美术资产，把打戏、动作场面或对白驱动的对峙文戏（剧本、分场、桥段）设计为动作与张力因果链，并生成简洁、去重、可直接投喂 Seedance 等视频模型的单段或连续多 Clip 提示词。适用于真人、武侠、冷兵器、枪战、玄幻、2D 动画或 3D Boss 战的打斗与追逐，也适用于多人谈判、审问、摊牌、决裂等以台词、视线和微动作推进的室内对峙场景；支持一镜到底、长篇拆段、提高动作可读性、打击感与资产连续性。不用于生成美术资产、分镜宫格或自动评价成片。
Skill content language: Chinese
Repository: jiayushi1-ux/script-to-shot-engine
GitHub stars: 71Updated: Jul 29, 2026
No.: 2,396
complaint-8d-reportGenerates or completes 8D reports (Eight Disciplines) from customer complaint data, with D1–D8 fill-in guidance and a standard template. Supports customer-specific formats (one supplier, multiple customers with different 8D layouts). Use for customer complaints, quality deviations, and defect recurrence prevention.
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: Jul 20, 2026
No.: 2,397
design-consultationBuild a complete design system from scratch with creative risks and realistic product mockups. Useful for kickoff workshops and brand-from-zero work.
Repository: nexu-io/open-design
GitHub stars: 106,055Updated: Aug 18, 2026
No.: 2,398
openclaw-test-performanceBenchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: Aug 16, 2026
No.: 2,399
clawhubSearch ClawHub for skills when a requested capability is not already available; install, verify, update, uninstall, publish, or sync skills.
Repository: openclaw/openclaw
GitHub stars: 393,741Updated: Aug 3, 2026
No.: 2,400
agent-browserDrive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
Repository: paperclipai/paperclip
GitHub stars: 111,284Updated: May 28, 2026