← ClaudeAtlas

video-readlisted

Turn a short video (local file, folder of videos, or a TikTok / Instagram / YouTube / Loom / direct URL) into evidence-backed Markdown that Claude agents can use as knowledge - an INDEX, one claim card per video, a faithful article, and a timestamped transcript and on-screen-text archive. Use this skill whenever the user wants to extract knowledge, claims, steps or numbers from a video or reel, make notes from a video for an agent, check what a creator actually says versus shows on screen, or says things like "read this reel", "pull the knowledge out of this clip", "what does this video claim", or "turn these videos into something my agent can use" - even if they never say "skill". Not for editing videos, subtitling, summarizing without evidence, or analysing visual style.
stanleypdp/Claude-Video-Journalist · ★ 0 · Data & Documents · score 72
Install: claude install-skill stanleypdp/Claude-Video-Journalist
# video-read Produces the files a `claim-cards` consumer reads. Everything runs on the user's machine (ffmpeg, faster-whisper, rapidocr); the only paid step is **one Claude CLI call per new video**, and a video already seen (same SHA-256) costs nothing. ## What you get For a source `X` the output goes to `OUTPUT/X/` (details in `references/output-format.md`): ``` INDEX.md one row per video: id, profile, lang, status, thesis, domain, link to the card cards/<id>.md claim card (~600 tokens): thesis, reported numbers with `@s` locators, method, gaps articles/<id>.md faithful narration of speech and screen + a table of data shown on slides archive/<id>.tx.md transcript in [mm:ss] blocks (the evidence; open only to verify) archive/<id>.screen.md de-duplicated on-screen text (OCR) with first/last time seen archive/<id>.rejections.md what the code removed and why (diagnostics, not a source of facts) ``` ## Run it Check the environment once, then read. From this skill's `scripts/` folder: ```bash python scripts/preflight.py # ffmpeg, whisper, claude (yt-dlp only for URLs) python scripts/pipeline.py <file|folder|URL> # preflight -> dry run -> read -> coverage check ``` The same steps individually: `read.py <file|folder|URL> [--dry-run] [--recursive] [--output DIR] [--captions FILE] [--no-wait]`, `check.py <OUTPUT/X>`, `rebuild.py <OUTPUT/X>`, `python -m vjournalist index <OUTPUT/X>`, `tx.py <id> --at 53 --w