Communitygithub.com

Vange-wang/ai-knowledge-video-skills

Gere legendas completas e cronometradas em chinês a partir da narração canônica e da narração final. Use quando um vídeo de conhecimento vertical precisar de cobertura total de legendas, segmentação de dicas legível, ênfase em palavras-chave, saída SRT ou JSON e uma verificação automatizada de que as legendas não omitem a narração.

O que é ai-knowledge-video-skills?

Esta skill é especializada na geração de legendas completas e cronometradas para vídeos de conhecimento vertical, garantindo que a narração canônica seja refletida fielmente nas legendas. Ela produz arquivos JSON, SRT, um mapa de narração para dicas e os elementos HTML de legenda necessários para a composição do vídeo. O processo inclui verificação automatizada via script PowerShell que compara a narração canônica com o HTML final, bloqueando a entrega em caso de divergência. Suporta segmentação de dicas com 7 a 14 caracteres chineses (podendo chegar a 16-18 para unidades semânticas) e ênfase contida em palavras-chave sem alterar o texto original.

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Vange-wang/ai-knowledge-video-skills/tree/HEAD/skills/ai-video-captions
Ver original→Navegar por todas as habilidades

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentação

Legendas de Vídeo com IA

Use a narração final exata como fonte do texto da legenda e a narração aprovada como fonte de temporização. Nunca substitua legendas completas por resumos.

Produza JSON de legenda, SRT, um mapa de narração para dicas e os elementos HTML de legenda exigidos pela composição. Mostre uma dica por vez. Almeje 7–14 caracteres chineses por dica e permita 16–18 apenas quando uma unidade semântica não puder ser dividida. Use ênfase contida em palavras-chave sem alterar o texto.

Execute scripts/verify-caption-coverage.ps1 contra a narração canônica e o HTML final. Uma incompatibilidade bloqueia a entrega. Se a narração ou a temporização da voz mudar, regenere a temporização e execute novamente o verificador.

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

Vange-wang/ai-knowledge-video-skills

Coordinate the full production of a vertical AI knowledge video from mixed source materials through analysis, script, visuals, mandatory character and voice approval, captions, HyperFrames composition, motion, calibration, and delivery. Use when the user wants an end-to-end short-video workflow or needs to resume or revise one stage without losing downstream dependencies.

Vange-wang/ai-knowledge-video-skills

Perform the final global calibration and delivery gate for a HyperFrames vertical video. Use to inspect all visual positions and animation paths, eliminate accidental overlap or drift, verify full captions and technical encoding, render the final MP4, and export a storyboard for review.

Vange-wang/ai-knowledge-video-skills

Complete the mandatory character-design gate for a vertical explainer video. Use when the specific presenter character is not yet chosen, when generating candidates and action sheets, or when replacing an approved character while preserving consistent proportions and clean transparent pose assets.

Vange-wang/ai-knowledge-video-skills

Analyze mixed source materials for a vertical AI knowledge video, including images, outlines, copy, scripts, videos and benchmarks. Use before writing the script to separate user instructions from source content and extract the audience problem, core argument, evidence, structure and visualization opportunities.

Vange-wang/ai-knowledge-video-skills

Assemble a portrait knowledge-video composition in HyperFrames from approved script, character, voice, captions and visual assets. Use to build deterministic 1080x1920 scene structure, media integration, safe-area layout and a paused GSAP timeline before detailed motion and sound polish.

Vange-wang/ai-knowledge-video-skills

Add controlled motion, scene transitions, background music and sound effects to an assembled HyperFrames vertical video. Use when the static composition is approved and needs tight pacing, readable animation, clean transitions and voice-first audio mixing.

Vange-wang/ai-knowledge-video-skills

Write a tight Chinese short-video script for AI knowledge and business education from an approved content analysis. Use to produce the 3–5 second hook, narrative progression, full narration, rhythm, visual notes, audio cues and CTA for a portrait video.

Vange-wang/ai-knowledge-video-skills

Produce and normalize illustrations, diagrams, icons, cards, backgrounds and other visual assets for a 9:16 AI knowledge video. Use after the visual plan to build a coherent asset library with clean hierarchy, consistent style and no accidental text or alignment defects.

Vange-wang/ai-knowledge-video-skills

Turn an approved narration into a detailed 9:16 storyboard and shot plan. Use to decide scene timing, character actions, illustrations, diagrams, background treatment, captions, transitions and sound cues before asset production or HyperFrames implementation.

Vange-wang/ai-knowledge-video-skills

Complete the mandatory voice-selection and voiceover gate for a vertical knowledge video. Use when the concrete voice is unresolved, when comparing providers or voices, when generating an approval preview, or when producing final narration with preset or authorized cloned speech.

Habilidades Relacionadas

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

affaan-m/ECC

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...

community

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

community