12,194 skills found · Page 402 of 407
shaowen-ye / manuscript-reviewMulti-agent academic manuscript review that generates bilingual annotated docx
vinceglakas / receipt-patternThe Receipt Pattern — auditable AI agent actions in 10 lines. Every agent action leaves a receipt.
MIKUZ12 / exampass将课程资料（PPT/Word/PDF/截图）按章节生成深度知识清单、教授式详细讲解和交互式章节测试，帮助学生高效期末复习。
erayack / svelte-core-bestpracticesSvelte best practices for writing, editing, or reviewing Svelte/SvelteKit components and modules
joshferrara / ghostwriterUse when the user wants to create, generate, build, update, refresh, or improve their personal writing style guide from their own sent writing (Generate mode), OR when they ask the agent to write, draft, reply, rewrite, edit, polish, or humanize something in their voice (Use mode).
Moonweave-Research / ref-verifyPrevents citation hallucination in academic writing. Invoke when: finding papers to support a specific claim; verifying/checking/auditing existing citations or DOIs; confirming whether a paper actually says what the user claims it says ('is that what the paper says?', 'did they actually show X?'); a…
cruisediary / apple-app-review-skillsClaude Code skills & agents to eliminate App Store rejections — 31 checks built from real-world rejection cases across all 5 App Store Review Guidelines sections.
YixiaJack / dating-master-skill全知情感导师 — 基于语用学、依恋理论和信号博弈论的情感洞察 Claude Code Skill
diggiehippie / ai-consulting-onboardingA Claude Code skill that generates a complete client onboarding package for AI consultants and solopreneurs. Creates 4 ready-to-use documents: intake questionnaire, welcome email, service agreement, and project brief.
SystemTce / dify-skillsDify 工作流和插件开发完整技能体系 - 模块化、渐进式披露、生产级质量
Ai-trainee / awesome-jevJev/TypeSafe System One 模型用法参考库，收录 124 条 JEV 实战案例（68 条 X 帖子 + 56 个开源项目，9 大场景），含 Jev 独立评分/精选标记/看点标签/原帖截图/X 链接。当用户提到 Jev/JEV/TypeSafe 的用途、玩法、案例、示例，或需要为 Jev 选型、评估能力边界、回答"Jev 能干什么"，或 Agent 想在用户不主动说明时主动推荐 Jev 玩法时使用。
Jill0099 / causal-inference-mixtapeThis skill should be used when the user asks to "implement a DiD regression", "run a staggered difference-in-differences", "set up an event study", "implement IV / 2SLS", "run a regression discontinuity design", "build synthetic control", "do propensity score matching", "test parallel trends", "run…
HeiGeAi / opc-teamTurn prompt-based agents into auditable ops: state machine, decision log, risk scoring, and memory for Claude Code, OpenClaw, Cursor, Windsurf, and API workflows.
MegaTroll222 / omni-ugc-ad-factoryProduce a UGC-style talking-head video ad end to end on the MaxFusion MCP — research the product with user-supplied competitor leads, tear down 5 competitor Meta ads and 5 organic TikToks, write a pain-driven script that sounds like a person talking (never like an ad), reverse-prompt a rights-clean…
porcupine-md / jonggrangDeterministic AI development workflow orchestrator. Manages task boards (.jonggrang/jonggrang-tasks.json), runs 16-phase pipelines (BUGFIX/SMALL/MEDIUM/LARGE), installs lifecycle hooks for Claude Code and OpenCode, and coordinates five specialist roles (Lead/Developer/Reviewer/TestLead/Tester)
ChenZeXian / ok-cosmic金蝶云苍穹开发主 Skill，优先复用 kd-cd-cosmic-commons 封装。适用于插件开发、单据/列表/表单逻辑、操作服务、BOTP 转换、后台视图打开、附件处理、DynamicObject 与元数据处理、弹性域解析及 OpenAPI 集成。默认优先使用仓库封装；在涉及原生插件事件、SDK API、方法签名或封装未覆盖场景时，使用内置脚本进行查询。
Maciejdziuba / local-ai-model-matcherSafely auto-detect the current machine's hardware (GPU, VRAM, system RAM, OS) with read-only commands, then recommend the top 3 local AI models to run — most powerful that fits, best for coding, and best small-and-fast — each with download links
robertoallende / fancy-kanbanGenerate valid fancy-kanban boards — markdown-embedded kanban boards with typed fields, swimlanes, workflow rules, and card face configuration for Obsidian and compatible tools
Klotzkette / airline-local-dashboard-bauenFür Airline – Local Counsel briefen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
WellApp-ai / connectConnect and verify the Well MCP — authenticate, confirm the tools work, and show what to ask
wx4766 / html-to-video把 HTML/Canvas 动画逐帧渲染成 MP4（可配乐、可出 GIF、可出透明层）。当用户说「用代码做视频」「HTML 转视频」「导出 MP4/GIF」「做个动态图解/宣传片/数据动画」「逐帧渲染」时使用。自带渲染器与 11 个开箱即用模板（含多镜头讲解片、竖屏 9:16、前后对比、流程图、字幕卡）、图标/人物/运镜素材库，支持透明输出、外部字幕时间轴与 JSON 镜头表，装好依赖后一条命令出片。
CamilleScholtz / asc-cli-usageGuidance for using asc cli in this repo (flags, output formats, pagination, auth, and discovery)
javimosch / aqUse this skill when the user wants to query aws resources with sql for easy data extraction and analysis.
cockpit-dev / cockpitUse only when the user explicitly asks to use Cockpit, invokes a Cockpit command or skill, or asks to install, configure, develop, debug, inspect, or verify Cockpit itself; do not activate for generic app, Flutter, UI, or E2E work.
yuymf / xiaohongshu-skills小红书自动化技能集合 — CDP 驱动的发布 / 搜索 / 运营工作流。
samikhokhar789 / blueprint-animationBlueprint animation that explains UX decisions step by step. With Before and After, changed parts rebuild. With one screen, each module is annotated with what and why. For case studies and posts.
wca0 / liquid-glass-scifi-uiTransform any frontend project (HTML/CSS/JS, React, Vue, Next.js, Tailwind, 3D WebGL/Cesium/Three.js workbenches, or dashboards) into an authentic Apple Liquid Glass + Sci-Fi high-tech interface
kyle-bartlett / soundshumanKyle's copy of the soundshuman humanizer skill + sloplint scanner (upstream: aashaexo/soundshuman)
xmg2024 / sun-skillJustin Sun Cognitive Framework - 孙宇晨认知操作系统 | 21,829 tweets + 288-page autobiography + 155-episode audio course + 269+ sources → 14 mental models + 19 decision heuristics
monasprox / openclaw-memoryFive-Layer Memory Protection for OpenClaw AI Agents — observer, reflector, reactive watcher, pre-compaction hook, session recovery
