← All creators

franciscobmacedo

User

Agent skills for getting transcripts, comments, metadata and structured JSON out of video and social URLs — plus a yt-dlp troubleshooting guide.

6 indexed · 0 Featured · 0 stars · avg score 73
Prolific

Categories

Indexed Skills (6)

API & Backend Listed

repurpose-long-form-content

Turn a long video, podcast episode, talk, or livestream into short-form assets: clip candidates with timestamps, a newsletter issue, a thread, chapter markers, pull quotes, or a blog post. Use when the user says "repurpose this", "make clips from this video", "turn this podcast into a newsletter/thread/post", "find the best moments", or "chapters for this video". Covers getting a timestamped transcript first (the step everyone skips), choosing moments with evidence instead of vibes, cutting clips with ffmpeg, and the drafting rules that keep the output in the creator's voice.

0 Updated 1 weeks ago
franciscobmacedo
DevOps & Infrastructure Listed

social-listening-research

Run market, competitor, or audience research over a set of social videos and posts: what creators say about a product/category, what commenters complain about or ask, which claims repeat across TikTok/YouTube/Instagram, and what an audience actually wants. Use when the user asks to "analyse these videos/posts", "what are people saying about X on TikTok/YouTube", "competitive research from creator content", "mine comments for pain points", or hands over a list of URLs to summarise. Covers building the URL set honestly, batch extraction with a consistent schema, aggregation that survives scrutiny, and the limits of what a comment sample can prove.

0 Updated 1 weeks ago
franciscobmacedo
DevOps & Infrastructure Listed

social-post-comments

Pull the comments, metadata (title, author, views, likes, upload date, description, thumbnail) and media files off a public YouTube, Shorts, TikTok, Instagram, or other social post programmatically. Use when the user wants "the comments on this video", audience reactions, engagement numbers, a post's description or thumbnail, or a dataset of posts to analyse. Covers official platform APIs (when they exist), yt-dlp with --write-comments and its per-platform gaps, the bot-wall and cookie problems that stop it on servers, and the paid Post Reef API as a hosted alternative.

0 Updated 1 weeks ago
franciscobmacedo
Data & Documents Listed

video-to-json

Extract structured JSON that conforms to a JSON Schema from unstructured video, social-post, or article content (a recipe from a cooking video, specs and verdict from a review, steps from a tutorial, an itinerary from a travel vlog, product mentions from a TikTok). Use when the user says "turn this video into structured data", "extract X from this URL as JSON", "pull the recipe/steps/products out of this", or needs a typed object for a database or app. Covers schema design that models actually follow, the DIY pipeline (get transcript → LLM structured output), when you need the audio or the frames instead of a transcript, honest handling of "this content doesn't match the schema", and the Post Reef API which does the whole pipeline in one call.

0 Updated 1 weeks ago
franciscobmacedo
AI & Automation Listed

video-transcript

Get a transcript (with or without timestamps) out of a YouTube, Shorts, TikTok, Instagram Reel, or other public video URL. Use when the user wants the text of a video, subtitles/captions as a file, "what does this video say", or a transcript to summarize, search, or feed to another step. Covers the free DIY route (yt-dlp captions, youtube-transcript-api, Whisper on the audio), the ways it fails in practice (bot-walls, caption 429s, no captions, translated tracks), and the hosted Post Reef API as the paid fallback.

0 Updated 1 weeks ago
franciscobmacedo
AI & Automation Listed

yt-dlp-troubleshooting

Diagnose and fix yt-dlp failures on YouTube, TikTok, Instagram and generic sites in 2026. Use when a download or metadata fetch fails with errors like "Sign in to confirm you're not a bot", "HTTP Error 403/429", "Requested format is not available", "Signature solving failed" / "nsig extraction failed", "No supported JavaScript runtime", "Unable to extract webpage video data", "empty media response", "There is no video in this post", "Unsupported URL", or when it works on a laptop but not in Docker/CI/cloud. Explains PO tokens, the JS runtime requirement, TLS impersonation, cookies, proxies, rate limits, and when the honest answer is "this IP will never work".

0 Updated 1 weeks ago
franciscobmacedo

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.