video-breakdown

video-breakdown is a skill for Claude Code, Codex from nataliacorrea03/claude-code-skills. It costs 120 tokens per session (836 once invoked), scanned A, original, MIT.

A video analysis workflow that combines selected video frames with a time-aligned transcript, which is the written version of spoken words.

In plain words
What is it for?
Use it for competitor reviews and analysis of YouTube, Loom, Instagram, or TikTok videos, as well as local files. It extracts scene-change frames and captions, then produces a content teardown.
Why use it?
It lets you examine what a video shows and says at the same moment instead of reviewing visuals or audio separately. This makes the video's hook, structure, and presentation easier to break down.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it for competitor reviews and analysis of YouTube, Loom, Instagram, or TikTok videos, as well as local files. It extracts scene-change frames and captions, then produces a content teardown.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nataliacorrea03/claude-code-skills/video-breakdown
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add nataliacorrea03/claude-code-skills --skill video-breakdown
Clone the repo
git clone --depth 1 https://github.com/nataliacorrea03/claude-code-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for video-breakdown

README.md
[![agentmods](https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/video-breakdown/github.svg)](https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/video-breakdown)
Your own site
<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/video-breakdown"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/video-breakdown/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for video-breakdown

Your own site · 80×15
<a href="https://agentmods.dev/skills/nataliacorrea03/claude-code-skills/video-breakdown"><img src="https://agentmods.dev/badge/skills/nataliacorrea03/claude-code-skills/video-breakdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.00836
Opus 5 $0.00060 $0.00418
Sonnet 5 $0.00024 $0.00167
Haiku 4.5 $0.00012 $0.00084

Measured 11d ago against content hash 9e11b1abbbb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

video-breakdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/grab.sh, scripts/vtt2txt.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/video-breakdown/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Breakdown

Reverse-engineer any video the way you actually watch one: visuals + audio at the same time. Built for competitor teardowns and ripping apart trending content in your niche.

How it works

No video model. The skill splits the video into the two things Claude reads natively — images (frames) and text (transcript) — with timestamps lined up, so Claude knows what's on screen the moment something is said.

  1. yt-dlp pulls the video + auto-captions from almost any site (YouTube, Loom, IG, TikTok) or a local file.
  2. ffmpeg rips frames at every scene change (falls back to interval sampling for static talking-heads), capped at ~80.
  3. Captions become a clean timestamped transcript.txt (no captions = on-screen text in frames still carries it).
  4. Claude reads the frames + transcript and writes the breakdown.

Run it

bash ~/.claude/skills/video-breakdown/scripts/grab.sh "<url-or-path>" [slug] [--start MM:SS] [--end MM:SS] [--every N]
  • slug — folder name (auto-derived if omitted)
  • --start / --end — only analyze a window
  • --every N — seconds between frames when falling back to interval sampling (default 3)

Output lands in ~/claude-watch/library/<slug>/:

  • frames/frame_*.jpg — the visuals
  • frames/times.txt — ffmpeg pts_time per frame (maps frame number → timestamp)
  • transcript.txt[MM:SS] line format
  • pacing.txt — cut-rhythm summary (cut count, first-cut time, avg gap, slow-open/static/fast flags). Heuristic from ffmpeg scene detection, not a motion read.
  • meta.txt — title, source, frame count

Then (Claude's job)

  1. Read transcript.txt fully.
  2. Read the frames. Use times.txt to know when each frame happens, so visuals align to the script.
  3. Produce the teardown. Default structure (adapt to what you asked for):
    • TLDR — one line on why this video works
    • Hook — first 0–3s, exact words + what's on screen
    • Structure — beat-by-beat with timestamps (acts, retention turns, CTA)
    • Visual playbook — cuts, text overlays, b-roll, motion, pacing
    • Why it's trending / what to steal — the transferable moves
    • If asked: graphics/motion prompts, script template, hook variations for a niche

Read the full file on GitHub · 50 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 50 lines · 120 tokens per session scan A 9e11b1abbbb8

Subscribe to this mod's changes

video-breakdown is a skill published in the GitHub repository nataliacorrea03/claude-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 836 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

presentation-creator

Builds decks with a story spine, house visual system, setting-specific density, and speaker notes. Use when asked to "create a presentation", "write a pitch deck", or "turn this doc into slides". Defaults to Marp; use an available presentation tool for editable PowerPoint. For product UI use ui-design.

mblode/agent-skills · 69 tokens

axiom-now-playing-musickit

MusicKit Now Playing integration patterns. Use when playing Apple Music content with ApplicationMusicPlayer and understanding automatic vs manual Now Playing info updates.

ComeOnOliver/skillshub · 35 tokens

axiom-now-playing-carplay

CarPlay Now Playing integration patterns. Use when implementing CarPlay audio controls, CPNowPlayingTemplate customization, or debugging CarPlay-specific issues.

ComeOnOliver/skillshub · 35 tokens

rc-video

Guias para trabalhar com vídeo. Use ao manipular arquivos com ffmpeg (cortar, transcodificar, extrair frames/áudio, legendar, comprimir, HLS), planejar conteúdo (roteiro, storyboard, Reels/Shorts/YouTube) ou integrar o VideoDB. Não use para edição em GUI ou streaming ao vivo.

rodolfochicone/rc-project · 77 tokens

image-finalize

Two-stage image generation workflow. First asks clarifying questions, then uses minimax for fast iterative drafts, then gemini-3-pro-image-preview for final polish. Trigger on image generation requests, editing/refining images, or when user wants to produce a final version.

LFTPadilla/agent-dev-kit · 58 tokens

youtube-toolkit

Download YouTube videos with yt-dlp and post-process them with ffmpeg — fetch best-quality video/audio, convert formats, extract audio, and burn in translated (e.g. Chinese) subtitles with a translator watermark. Covers cross-environment tool installation (macOS-focused) including the ffmpeg-full / libass gotcha.…

wquguru/skills · 79 tokens