Skill para analisar conteudo de video existente: baixar, extrair frames, transcrever audio e responder perguntas sobre o que acontece no video. Use quando precisar entender, resumir ou buscar informacao dentro de um video ja existente — nao para gerar video novo (isso e skill 27). Trigger em: "transcrever video", "transcrever esse video", "baixar video do youtube", "extrair frames do video", "extrair frames desse video", "legenda automatica", "resumir video", "resumir esse video", "analisar video", "analisar o conteudo desse video", "o que acontece nesse video", "whisper", "yt-dlp", "transcription video", "extract frames from this video".
69
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow downloads public videos via user-supplied URLs and processes their captions or transcripts, representing low-risk untrusted content retrieval.
felvieira/claude-skills-fv
90329e3
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.