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
5,210 results · page 34 of 174
- View details
update-brand-kitSkillMedia
Maintain a brand kit — the canonical brand context an ad or content pipeline reads (positioning, audience, voice, standing instructions, brand-type, value-props, colors), plus manage the product list and attach product photos. Use when someone says "update my brand kit", "set my brand voice/audience
Ready to connect★ 1k
- View details
jlcpcbSkillMedia
JLCPCB PCB fabrication and assembly — BOM/CPL generation, basic vs extended parts, assembly constraints, design rules, ordering workflow. Use with KiCad for JLCPCB manufacturing. Use this skill when the user mentions JLCPCB, wants to order PCBs or assembled boards, needs prototype bare PCBs and sten
Ready to connect★ 1k
- View details
pcbwaySkillMedia
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assem
Ready to connect★ 1k
- View details
generate-code-snippetSkillMedia
Generate a concise, shareable code snippet URL for code.franciscomoretti.com. Use when preparing a code image or short snippet for Twitter, X, social sharing, or a presentation.
Ready to connect★ 1k
- View details
lazy-prefetch-patternSkillMedia
Use the ChatJS React Query v5 lazy-prefetch pattern without blocking server rendering. Use when prefetching tRPC queries in Next.js Server Components or changing query dehydration and hydration behavior in apps/chat.
Ready to connect★ 1k
- View details
next-cache-components-adoptionSkillMedia
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the `cacheComponents` flag, work through a flood of blocking-prerender / instant validation errors, run the `cache-components-instant-
Ready to connect★ 1k
- View details
triage-visual-changesSkillMedia
Triage a UI Verify build from your coding agent via the UI Verify MCP — bucket a build's changed stories into real regressions vs cosmetic reflow vs rendering noise, summarize the real regressions for a PR comment, and accept baselines in bulk. Use after a UI Verify build reports changes and you wan
Ready to connect★ 1k
- View details
content-factorySkillMedia
Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing
Ready to connect★ 1k
- View details
museum-artSkillMedia
Source authentic, high-res PUBLIC-DOMAIN artwork from museum open-access APIs (Met, Cleveland, SMK, Rijksmuseum, NGA, Art Institute of Chicago, Getty, Smithsonian) instead of AI-generated or generic-stock imagery. The default move whenever a visual needs an aesthetic, credible image (blog heroes, de
Ready to connect★ 1k
- View details
taste-skillSkillMedia
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
Ready to connect★ 1k
- View details
claude-typerSkillMedia
Render a Claude-style prompt typing animation video by calling Remotion CLI against the remote site https://www.laosunwendao.com. Use when the user asks for "做一个 claude 的提示词打字机动画", "做 Claude 打字动画", "创建提示词动画", or similar requests that convert a text prompt into a typing-animation video.
Ready to connect★ 1k
- View details
electron-ipcSkillMedia
Safe Electron IPC patterns for renderer-main communication with preload bridges, channel design, replies, and serialization limits.
Ready to connect★ 1k
- View details
youtubeSkillMedia
Extract transcripts from YouTube videos via the YouTube caption system
Ready to connect★ 1k
- View details
twmd-evolveSkillMedia
Evolution via the canonical EVOLVE-PIPELINE — data-driven content evolution (v1/v2), pipeline self-refactoring (Mode 3), and goal-driven design evolution (Mode 4: think→diverge→report→implement). TRIGGER when: user says "跑 EVOLVE", "數據驅動進化", "evolve-pipeline", "進化 X pipeline 本身", "設計 X（技能/器官）", "深度思
Ready to connect★ 1k
- View details
twmd-music-media-auditSkillMedia
Audit for missing iframes in Music / People (actors / athletes) entries, per the EDITORIAL §媒體編織 baseline. Produces a heal candidate list in reports/music-media-audit/YYYY-MM-DD.md. TRIGGER when: user says "音樂 audit", "缺影片", "music media audit", "iframe 盤點".
Ready to connect★ 1k
- View details
ap-plannerSkillMedia
L3 conditional G1 planner - adds detail only when a roadmap item explicitly requires it, including debug depth-lock and unresolved design forks.
Ready to connect★ 1k
- View details
anthropic-frontend-designSkillMedia
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
Ready to connect★ 1k
- View details
audit-biomedical-paper-evidenceSkillMedia
Reviews life science or biomedical papers provided by the user—PDFs, abstracts, body text, figures, panels, captions, or screenshots—to identify the core scientific question, explain the experimental design and evidence chain figure by figure, and audit mechanisms, causality, rescue experiments, met
Ready to connect★ 1k
- View details
figure-composerSkillMedia
Compose or improve a publication-grade multi-panel scientific figure from a claim, concrete data paths, or an existing image. Use for figure outlining, parallel panel rendering, exact-grid composition, visual inspection, and adversarial figure review. Use figure-style for one standalone plot and pap
Ready to connect★ 1k
- View details
indication-dossierSkillMedia
Build a sourced research dossier for one therapeutic indication — patient population, epidemiology, disease biology, standard of care, regulatory path, and landmark trials. Use when the user asks for an indication overview, disease landscape, or trial-design background.
Ready to connect★ 1k
- View details
self-awarenessSkillMedia
Wisp-science's actual agent tool surface and runtime boundaries. Load this when deciding which Wisp tool can perform a task, checking whether Python can reach agent or desktop capabilities, choosing between interactive analysis and persisted Runs, or answering questions about delegation, images, ski
Ready to connect★ 1k
- View details
menusSkillMedia
Reference for OrangeHRM's menu system — the `MenuItem` entity in `ohrm_menu_item` (hierarchical via `parent_id` + `level`, ordered by `order_hint`, linked to a `Screen` via `screen_id`), the side panel + top menu rendering pipeline (server-computed in `MenuService::getMenuItems()`, passed to the Twi
Ready to connect★ 1k
- View details
ai-image-genSkillMedia
General AI image generation: text-to-image / image-to-image / image variants. Use when the user says AI image generation, AI drawing, text-to-image, image-to-image, generate a picture, generate an illustration, image generation, AI image output, edit image, change image, image editing, 'draw me one'
Ready to connect★ 1k
- View details
ai-video-genSkillMedia
AI video generation: text-to-video / image-to-video / digital-human first-frame driving. Generates videos asynchronously via pluggable providers (Tongyi Wanxiang Wan / Volcano Seedance / Kuaishou Kling / OpenAI-compatible); users supply their own API key. Use when the user says AI video generation,
Ready to connect★ 1k
- View details
audio-denoiseSkillMedia
Audio denoising: removes background noise, electrical hum, wind noise, and buzzing from recordings using an ffmpeg filter chain (afftdn/highpass/lowpass). Use when the user says "降噪" (denoise), "去噪", "去杂音", "消除背景噪声" (remove background noise), "电流声" (electrical hum), "风噪" (wind noise), "录音有杂音" (recor
Ready to connect★ 1k
- View details
audio-editingSkillMedia
General audio processing: audio clipping/trimming, format transcoding (mp3/wav/m4a/aac), volume normalization, extracting audio tracks from video, multi-segment joining, fade in/out, and speed change (pitch-preserving). Use when the user says "剪音频", "裁一段", "转成 mp3", "调音量/响度", "提取音轨/扒音频", "拼接音频", "淡入
Ready to connect★ 1k
- View details
audio-mixSkillMedia
Audio mixing: blends narration voiceover + background music + sound effects into one track, with BGM auto-looping to fill length and auto-ducking (BGM is automatically lowered while narration is speaking to keep vocals clear). Use when the user says: mix audio, audio mixing, narration with backgroun
Ready to connect★ 1k
- View details
audio-visualizerSkillMedia
Audio visualization video: renders pure audio (podcast clips, music, spoken highlights, radio) into a video with dynamic waveform/spectrum, plus cover art and title, ready to post to video-only platforms like Douyin/Bilibili/Channels. Use when the user says 音频可视化, 音频转视频, 播客做成视频, 音频波形视频, 音乐可视化, 给音频配画
Ready to connect★ 1k
- View details
auto-short-videoSkillMedia
One-line topic → finished short video: automatically chains copy → images/AI video → voiceover → subtitles → BGM → assembly, orchestrating Easel production-layer components into a 'one-click video' pipeline. **Single video, voiceover/news style; default is per-sentence images with Ken Burns easing,
Ready to connect★ 1k
- View details
beat-sync-videoSkillMedia
Beat-synced videos / music beat videos: detects the beat of background music so images or clips switch on the beat, with push-in/white-flash effects, creating high-energy beat-synced short videos. Use when the user says 卡点视频, 踩点视频, 音乐卡点, 节奏卡点, 按音乐切换, 鼓点视频, 踩节奏, beat 卡点, 图片卡点, or 卡点混剪. Based on share
Ready to connect★ 1k
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.
53,585 of the 54,017 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.