convez.ai
SkillMarketing & VendasAvançado
CapstraLabs

Capturable Skills

CapstraLabs/capturable-skills

Claude como diretor de vídeo: planos multi-cena, continuidade de personagens, UGC ads

Ver no GitHub
InicialPluginScore · de 0 a 100

Conjunto de skills que transformam Claude em diretor de vídeo para a plataforma Capturable.ai, permitindo criar vídeos multi-cena com personagens e produtos consistentes. Integra-se via API nativa (sem automação de navegador) com suporte a planejamento de custos, continuidade visual e renderização end-to-end através de GPUs próprias ou provedores agregados.

Instalação

$npx convez-ai CapstraLabs/capturable-skills

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
50%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Gerar vídeos de produtos com múltiplas cenas com branding consistente
  • Criar anúncios UGC (User Generated Content) em formato 9:16 para redes sociais
  • Produzir vídeos comerciais com personagens reutilizáveis e continuidade visual
  • Planejar e renderizar campanhas de marketing em vídeo com estimativa de custos prévia

Veredito

Skill robusta e prática que resolve um problema real — geração de vídeos profissionais com continuidade — sem gambiarras de automação. API-first, costed planning e suporte a múltiplos modelos/provedores a tornam viável para pipelines de produção em escala. Requer conta Capturable e API key, mas funciona no plano gratuito.

README

A tradução para o português deste README ainda está na fila.

Capturable AI Skills

AI agent skills that turn Claude (or any Markdown-skill-capable agent — Claude Code, Cursor, Codex, Copilot) into a video director for Capturable: plan multi-scene videos with consistent characters, generate images and product shots, and render everything through one API.

Works on the free plan out of the box (flagship Capturable Gen 2 models, self-hosted GPUs). Paid plans unlock aggregated providers — Kling, Google Veo, and more — through the same calls.

Why this beats browser-automation packs

  • Real API, no Playwright. Every skill calls https://api.capturable.ai directly with your API key. No browser windows, no flaky selectors, no "prompt bar didn't clear" bugs.
  • Plan before you spend. Planning is a costed review step: Claude drafts the full scene plan and shows you the credit estimate before any GPU renders.
  • Scene continuity. Characters, products, and branding stay consistent across every scene of a multi-shot video — the thing single-clip generators can't do.
  • One pipeline, end to end. Idea → scene plan → keyframes → motion → final video, polled and downloaded by your agent.

Install

Claude Code marketplace

/plugin marketplace add CapstraLabs/capturable-skills
/plugin install capturable@capturable

npx skills (cross-agent)

npx skills add CapstraLabs/capturable-skills

Manual (any agent)

Clone this repo and copy the skill folders into your agent's skills directory (e.g. .claude/skills/ or .cursor/skills/):

git clone --depth 1 https://github.com/CapstraLabs/capturable-skills.git

Agent-driven install: paste INSTALL_FOR_AGENTS.md into your agent.

API key

  1. Create a free account at capturable.ai.
  2. Create an API key at capturable.ai/settings/api-keys (aicl_…).
  3. Export it: CAPTURABLE_API_KEY=aicl_... (env var, or your agent's secret store).

Skills

SkillInvokeDescription
capturable-video-director/capturable:video-directorFlagship. Claude becomes the director: prompt → costed multi-scene plan → review → continuity render → final video. Characters, branding, and places stay consistent across scenes.
capturable-generate/capturable:generateFast single operations: text-to-image, image-to-video animation, one-call quick videos, job polling, model listing, quotes, credit balance.
capturable-product-shot/capturable:product-shotProduct placement photography: your real product image composited into generated scenes (studio, lifestyle, hero, seasonal). 1–4 variants per call.
capturable-character/capturable:characterRegister reusable characters and brand assets (logo / product / packaging) from photos. Returns IDs consumable by the director and UGC skills.
capturable-ugc-ads/capturable:ugc-adsUGC-style ad pipeline: presenter character → hook-first 9:16 script → continuity render. Includes hook frameworks, beat timelines, and platform presets (TikTok / Reels / Shorts).

The skills chain: register a character or brand asset with capturable-character → reference it in capturable-video-director or capturable-ugc-ads → render. capturable-generate and capturable-product-shot are self-contained.

Quick reference

What you wantSkillNote
Full multi-scene video with consistent characterscapturable-video-directorPlan is reviewed (with cost) before rendering
One-shot video from a prompt, no review stepcapturable-generatePOST /videos/quick — plan + auto-approve + render
Image from a promptcapturable-generateCapturable Gen 2 Image on free plan
Animate a still image into a clipcapturable-generatefirst-frame animation
Product photo with my real product in itcapturable-product-shotImage-edit recipe keeps the product pixel-faithful
Reusable face/character across videoscapturable-character → directorConsent-tracked character references
Brand logo/packaging in every scenecapturable-character (branding)brandingType: logo | product | packaging
TikTok/Reels UGC adcapturable-ugc-ads9:16, hook-first beat structure
Cost before committinganyPOST /quote is free and authoritative
Use Kling / Veo instead of Gen 2any (Pro plan)Same calls, set videoModel; GET /models lists what your plan allows

Plans & models

  • Free / Connect — API keys are pinned to the self-hosted Capturable Gen 2 stack (capturable-gen2-image, capturable-gen2-video): real renders, zero aggregator spend, weekly allowance.
  • Pro+ — full-mode keys choose any plan-eligible model (Kling, Google Veo, Seedance, GPT Image, …) via the same endpoints.

Skills always call GET /v1/integrations/models first, so they only ever offer models your plan can actually render with.

Docs

  • INSTALL.md — all install paths
  • COOKBOOK.md — end-to-end recipes (brand ad, UGC batch, product catalog refresh)
  • OpenAPI: https://api.capturable.ai/v1/integrations/openapi.json
  • Prefer MCP? npx -y @capturable/mcp-server wraps the same API as tools.

License

MIT — see LICENSE.

Ver o original no GitHub

Bom para

Relacionados