20 skills · sorted by relevance
Create a video outro as a single HTML file, with geometric logo pieces assembling into place, a glow effect, and a tagline reveal. Add the brand name and a call to action to finish the sequence.
Create a video outro as a single HTML file, with geometric logo pieces assembling into place, a glow effect, and a tagline reveal. Add the brand name and a call to action to finish the sequence.
Create opening and closing video cards with titles, subtitles, logos, and follow prompts. Attach them to a main video with direct cuts or transitions, while matching frame size, frame rate, and audio.
Create a branded video ending in a single HTML file. Geometric pieces assemble into a logo, followed by a glow, brand name, tagline, and call to action. The animation plays once and holds the completed end card.
Build coordinated animation sequences with GSAP timelines. Set when each movement starts, overlap effects, name key moments, combine smaller sequences, and control playback, including pause, reverse, restart, and jumps to a specific point.
Create short video clips from text or still images with LTX-2.3 22B. Generate supporting footage, animated backgrounds, or moving portraits while specifying camera motion, lighting, dimensions, and duration, with clips around five seconds by default.
Build coordinated animation sequences with GSAP timelines. Set when each movement starts, overlap effects, name key moments, combine smaller sequences, and control playback, including pause, reverse, restart, and jumps to a specific point.
Use when the user asks to "turn this idea into posts for every platform", "write the X thread / LinkedIn post / 小红书 note", or "spec the carousel slides"; turns one idea into N platform-native ready-to-paste packages — post/thread, caption, Threads text, 小红书 note, link post with first-comment placement — each adapted per the dated platform norm card (never verbatim cross-posting), every product claim held to approved claims-ledger wording or flagged [needs source], every variant tagged {formula | hook family | CTA type | signal optimized}, plus a carousel slide-spec mode (intro/content/outro slide roles, per-element char budgets, 小红书 3:4 / IG 4:5 / LinkedIn document PDF artboards, text-safe-zone + alt-text checklist). Not for creator deliverable briefs — use brief-generator; not for repurposing existing assets with paid boost — use content-amplifier. 社媒文案/一稿多发改写/小红书笔记/轮播图脚本
The English summary is being prepared. Showing the original description.
Create and edit professional motion graphics videos with Remotion (React-based video). Use this skill EVERY time the user wants to create a video, edit a video, animate something, build an intro/outro/logo animation, make a Reel/Short/promo/launch video, add text animations or captions to footage, composite images and B-roll into a video, or mentions Remotion, motion graphics, video rendering, or "make this video look better/less generic". Also trigger when editing an existing Remotion project or when the user complains their video looks basic, generic, or amateur — this skill contains the exact fixes. Always read this skill BEFORE writing any Remotion code.
The English summary is being prepared. Showing the original description.
Generate podcast scripts from text content. Use Tone.js and Howler.js for audio mixing. Create intro/outro music, transitions, sound effects.
The English summary is being prepared. Showing the original description.
Produce audio-first podcast episodes with generative tools — design the show and episode format (interview, narrative, news brief, two-host conversational), write scripts for the ear, decide between fully-synthetic and hybrid (recorded human + synthetic) production and meet the disclosure duty each triggers, cast and direct multi-voice TTS for consistency and chemistry, build episode structure (cold open, intro/outro, segments, ad slots), assemble and edit, clear music and SFX rights, hit podcast loudness and delivery standards, ship metadata/chapters/transcripts through RSS, and pass platform AI-content policy and QA before publishing. Use this skill whenever the deliverable is a podcast episode or a podcast show bible, or when an agent must make production, rights, disclosure, or delivery decisions for spoken-word audio. Not for music tracks, single-voice notification prompts, or video where picture leads (route audio-for-video to a video skill).
The English summary is being prepared. Showing the original description.
Adds professional packaging and motion graphics to videos. Use when the user asks to add intros, outros, subtitles, transitions, watermarks, or lower thirds to a video. Supports multiple styles and custom options, no API key required.
The English summary is being prepared. Showing the original description.
Construa, depure e otimize aplicativos com Claude API / SDK Anthropic. Aplicativos construídos com esta skill devem incluir cache de prompt. Também lida com migração de código Claude API existente entre versões de modelo (4.5 → 4.6, 4.6 → 4.7, substituições de modelo descontinuado). TRIGGER quando: código importa `anthropic`/`@anthropic-ai/sdk`; usuário solicita Claude API, SDK Anthropic ou Managed Agents; usuário adiciona/modifica/afina um recurso Claude (cache, thinking, compaction, tool use, batch, files, citations, memory) ou modelo (Opus/Sonnet/Haiku) em um arquivo; dúvidas sobre prompt caching / cache hit rate em um projeto SDK Anthropic. SKIP: arquivo importa `openai`/SDK de outro provedor, nome de arquivo como `*-openai.py`/`*-generic.py`, código agnóstico de provedor, programação geral/ML.
The English summary is being prepared. Showing the original description.
Guia completo para criar diagramas de software usando sintaxe Mermaid. Use quando usuários precisarem criar, visualizar ou documentar software por meio de diagramas, incluindo diagramas de classe (modelagem de domínio, design orientado a objetos), diagramas de sequência (fluxos de aplicação, interações de API, execução de código), fluxogramas (processos, algoritmos, jornadas do usuário), diagramas de relacionamento de entidades (esquemas de banco de dados), diagramas de arquitetura C4 (contexto do sistema, containers, componentes), diagramas de estado, git graphs, gráficos de pizza, gráficos de Gantt ou qualquer outro tipo de diagrama. Acionadores incluem solicitações para "diagram", "visualize", "model", "map out", "show the flow" ou ao explicar arquitetura de sistema, design de banco de dados, estrutura de código ou fluxos de usuário/aplicação.
The English summary is being prepared. Showing the original description.
Criando visualizações de dados interativas usando d3.js. Esta habilidade deve ser usada ao criar gráficos customizados, diagramas de rede, visualizações geográficas ou qualquer visualização de dados complexa baseada em SVG que requeira controle fino sobre elementos visuais, transições ou interações. Use isto para visualizações personalizadas além das bibliotecas de gráficos padrão, seja em React, Vue, Svelte, JavaScript vanilla ou qualquer outro ambiente.
The English summary is being prepared. Showing the original description.
Fornece orientação para treinar LLMs com aprendizado por reforço usando verl (Volcano Engine RL). Use ao implementar RLHF, GRPO, PPO ou outros algoritmos de RL para pós-treinamento de LLMs em escala com backends de infraestrutura flexíveis.
The English summary is being prepared. Showing the original description.
Envie e receba mensagens criptograficamente assinadas entre agentes de IA usando o Agent Messaging Protocol (AMP). Use quando o usuário pedir para "enviar uma mensagem para um agente", "verificar caixa de entrada do agente", "mensagear outro agente", "responder a uma mensagem", "notificar um agente" ou qualquer tarefa de comunicação entre agentes.
The English summary is being prepared. Showing the original description.
Create AI-powered podcasts with text-to-speech, music, and audio editing. Tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, media merger. Capabilities: multi-voice conversations, background music, intro/outro, full episodes. Use for: podcast production, audiobooks, voice content...
The English summary is being prepared. Showing the original description.
Use when the user asks to "turn this idea into posts for every platform", "write the X thread / LinkedIn post / 小红书 note", or "spec the carousel slides"; turns one idea into N platform-native ready-to-paste packages — post/thread, caption, Threads text, 小红书 note, link post with first-comment placement — each adapted per the dated platform norm card (never verbatim cross-posting), every product claim held to approved claims-ledger wording or flagged [needs source], every variant tagged {formula | hook family | CTA type | signal optimized}, plus a carousel slide-spec mode (intro/content/outro slide roles, per-element char budgets, 小红书 3:4 / IG 4:5 / LinkedIn document PDF artboards, text-safe-zone + alt-text checklist). Not for creator deliverable briefs — use brief-generator; not for repurposing existing assets with paid boost — use content-amplifier. 社媒文案/一稿多发改写/小红书笔记/轮播图脚本
The English summary is being prepared. Showing the original description.
Identifica padrões entre muitas peças de copy — quais ganchos, ângulos, formatos, temas e horários rendem mais. Use quando o usuário disser "o que funciona melhor", "qual padrão", "por que uns posts vão bem e outros não", "analisar histórico", "o que devo fazer mais", "tendência do conteúdo". Exige volume: abaixo de 20 peças, o resultado é observação, não padrão.
The English summary is being prepared. Showing the original description.