Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Media
5,297 results · page 129 of 177
- View details
generate-taskSkillMedia
Generates one worker task prompt conforming to the CLEAR + selective CoVe task design standard and swarm-task-planner structure. Use when creating or rewriting a single task entry or task block inside a plan — providing a title and brief description as input.
Ready to connect★ 66
- View details
lov-branding-consistencySkillMedia
面向公众号、网站、App、策划案、海报等真实发布场景，为读者可见文本建立受众、品牌角色、组件惯例与信息可见性门禁。Use when generating, editing, rendering, publishing, or reviewing audience-facing copy for brand and context fit.
Ready to connect★ 66
- View details
lov-business-cardSkillMedia
Generate a professional, editorial-style business card (2:1) as a high-resolution PNG and a self-contained interactive HTML. Collects the user's identity (name, roles, tagline, interests, locations, optional avatar), fills a parameterized design template with a chosen theme, and renders it via headl
Ready to connect★ 66
- View details
lov-clash-tun-doctorSkillMedia
Diagnose and repair application connectivity failures caused by Clash Verge Rev TUN routing, rule precedence, stale runtime state, proxy timeouts, or unusable IPv6 paths. Trigger for symptoms such as WeChat images failing to send, Moments images loading slowly, an app hanging after TUN is enabled, o
Ready to connect★ 66
- View details
lov-find-logoSkillMedia
Fetch a company/product logo from public sources (Clearbit, og:image, favicon) given a brand name or URL, score candidates (wide-aspect + transparent preferred), and archive the best + runner-ups to the configured logo collection directory. Trigger when the user says "find logo", "找 logo", "抓 logo",
Ready to connect★ 66
- View details
lov-frontend-designSkillMedia
把需求、现有界面与真实素材落实为有辨识度、交互一致的前端，覆盖页面、组件、导航、GSAP 展示及图片音视频。触发：设计前端、界面不够专业、制作交互案例集；design or refine a frontend UI.
Ready to connect★ 66
- View details
lov-image-creatorSkillMedia
按用途生成图像、制作可编辑图文布局或整理图像提示词。支持明确输入与结果回读。Use to create an image, designed
Ready to connect★ 66
- View details
lov-image-translation-errataSkillMedia
Compare the original text in a screenshot with its machine translation and generate an errata image that preserves the error traces, provides correct translations, and keeps the original layout as much as possible; used for "image translation errata", "point out machine translation errors", and crea
Ready to connect★ 66
- View details
lov-install-designSkillMedia
将项目品牌设计规范映射到已有前端样式与组件系统。支持明确输入与结果回读。Use to install a project design system.
Ready to connect★ 66
- View details
lov-media-fetchSkillMedia
Use when the user asks to find and download a film, series, or long video. Uses aria2 as the default transfer backend, handling multi-source speed testing, resumable downloads, capacity pre-checks, version verification, and subtitle acceptance; also suitable for requests like "help me download this
Ready to connect★ 66
- View details
lov-media-preprocessorSkillMedia
对实录视频做全片增强与内容分段，保留有价值内容、剔除已核验无效区间，输出素材库与源时间码。Use when 用户说“全片提亮”“智能分段”“清理课程素材”或 “preprocess and segment video”。
Ready to connect★ 66
- View details
lov-media-publisherSkillMedia
Publish local videos to WeChat Channels or Bilibili via the logged-in creator dashboard, gated by media pre-checks, description source freezing, field read-back, cover safe-zone checks, final draft confirmation, and list read-back. Use when users ask to publish, draft, schedule, or check a video pos
Ready to connect★ 66
- View details
lov-nano-banana-proSkillMedia
将图像需求整理为结构清晰、遵循参考素材的生成或编辑提示词。支持明确输入与结果回读。Use to create a structured image
Ready to connect★ 66
- View details
lov-professional-portraitSkillMedia
Turn a single-person photo into a polished professional portrait while preserving the person's identity. Use restrained skin retouching, exposure cleanup, optional hat removal and hairstyle reconstruction, background polish, and an explicit quality gate. Trigger when the user asks for a professional
Ready to connect★ 66
- View details
lov-riso-portraitSkillMedia
Redraw a single-person photo with gpt-image-2 into an identity-faithful Riso portrait, then check facial features, fingers, accessories, and the circular crop. Use when the user asks for '做成 Riso 人像', '生成孔版印刷头像', or 'create a Riso portrait'.
Ready to connect★ 66
- View details
planningSkillMedia
Use when Stage 1 Discovery is complete and design must begin — transforms the ARTIFACT:DISCOVERY into an actionable ARTIFACT:PLAN via RT-ICA prerequisite verification. Produces approach, components, success criteria, acceptance tests, and risks. Blocks on missing prerequisites before design proceeds
Ready to connect★ 66
- View details
pm-agileSkillMedia
Use when: a project is starting and needs an agile development process established, team collaboration mechanisms designed, and iteration cadence planned. Do NOT use when: the team already has a mature agile process, or only needs a single project management tool rather than process design.
Ready to connect★ 66
- View details
pm-brainstormSkillMedia
Use when: the user needs creative solutions, wants to explore product directions, brainstorm ideas, or analyze the core problem; the user says "I want to build an XX", "help me plan an XX product", or "help me design the requirements"; the user gives a new product direction but has not yet completed
Ready to connect★ 66
- View details
pm-brand-motionSkillMedia
Use when: you need to design motion direction for a brand, create logo animation demos, define brand motion personality, or transition from a static logo to dynamic presentation. Do NOT use when: professional-grade motion deliverables are needed (leave that to designers), finished motion assets alre
Ready to connect★ 66
- View details
pm-business-modelSkillMedia
Use when: designing a business model canvas, planning profit models, developing pricing strategies, or designing revenue models. Do NOT use when: the business model is already established and validated, or only a simple pricing adjustment is needed rather than a full design.
Ready to connect★ 66
- View details
pm-interviewSkillMedia
Use when: you need to design user interview/user research plans, write interview guides, plan samples and recruitment, or define interview execution and analysis methods. Do NOT use when: doing desk research only for requirements (use pm-demand); or when a clear conclusion already exists and only a
Ready to connect★ 66
- View details
pm-positionSkillMedia
Use when: you need to clarify product positioning, design a business model, plan monetization, set pricing strategy, or do revenue forecasting. Do NOT use when: product positioning is already clear and you only need execution without repositioning.
Ready to connect★ 66
- View details
pm-protoSkillMedia
Use when: you need to design product prototypes, plan interaction flows, determine interface layouts, or bridge from PRD to visuals. Do NOT use when: the prototype has already been completed by a designer, or only a text description is needed with no visual output.
Ready to connect★ 66
- View details
pm-riskSkillMedia
Use when: performing risk review after a technical design is completed, identifying and assessing risks before launch, or managing risks at key project milestones. Do NOT use when: the project is very small with controllable risks, or a complete risk management process already exists and no new one
Ready to connect★ 66
- View details
propkitSkillMedia
Guides Figma-style property panel composition using fig-field rows and FigUI3 controls, including React JSX. Use when building labeled property panels or choosing between raw fig-* rows and propskit-* wrappers (fig-lab).
Ready to connect★ 66
- View details
rtfpSkillMedia
Scan Claude Code session transcripts to find the strongest user reactions to assistant instruction-following failures, reconstruct the triggering assistant output, and render a shareable terminal-style PNG artifact. Use when you want to surface and share a moment where the assistant completely misse
Ready to connect★ 66
- View details
sgc-electron-delta-updaterSkillMedia
Design, implement, and verify delta auto-updates for Electron desktop apps, covering macOS Sparkle, code signing, appcast, release artifacts, and failure interception. Use when the user mentions delta updates, Sparkle, checking for updates, appcast, DMG updates, or delta updater.
Ready to connect★ 66
- View details
steve-jobs-perspectiveSkillMedia
Steve Jobs' thinking frameworks and communication style. Based on deep research into 30+ primary sources — Isaacson's authorized biography, the Stanford commencement speech, the Lost Interview, the D Conference series, and Make Something Wonderful — it distills 6 core mental models, 8 decision heuri
Ready to connect★ 66
- View details
workflow-designSkillMedia
Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.
Ready to connect★ 65
- View details
ai-media-generation-expertSkillMedia
Expert guide for AI image generation (Flux, DALL-E, Stable Diffusion), video generation (Sora, Runway), voice synthesis (ElevenLabs TTS), and speech recognition (Whisper STT) integration / Panduan ahli integrasi AI generasi gambar, video, suara (TTS), dan pengenalan suara (STT).
Ready to connect★ 65
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.