Media Analysis

Measure deterministic facts about a media file (container, streams, video/audio format, silence, loudness, integrity, scene cuts, timing) with local ffprobe/ffmpeg and return a structured Observation. Use when a task needs to *know* something about a video or audio file before deciding anything: duration, resolution, fps, CFR/VFR, codecs, channel layout, where the silence is, how loud it is (LUFS / true peak), whether it decodes cleanly, where hard cuts are. Do not use it to edit, convert, normalise or export media (that is ffmpeg-skill) or to interpret the numbers (that is the agent). Python

9 stars 1 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add kajisho5/media-analysis-skill --skill media-analysis

Manual install

git clone --depth 1 https://github.com/kajisho5/media-analysis-skill.git /tmp/media-analysis-skill
mkdir -p ~/.claude/skills
cp -r /tmp/media-analysis-skill/. ~/.claude/skills/media-analysis

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# media-analysis (Skill)

`media-analysis-skill` is an observation Skill, not an agent. It measures; it never interprets, decides, plans or edits.

## Commands

```text
media-analysis probe <input> [--json]
media-analysis analyze <input> --kind <kind> [--kind <kind> ...] [--param key=value ...] [--json] [--dry-run]
                       [--asset-id ID] [--analysis-id ID] [--timeout S] [--max-analysis-calls N] [--max-total-seconds S]
                       [--cache-dir DIR] [--workspace DIR] [--allowed-input ROOT ...] [--round N]
media-analysis run <request.json | -> [--json] [--dry-run] [engine options]      # canonical machine interface
media-analysis doctor [--json] [--cache-dir DIR] [--workspace DIR]
media-analysis contract [--json] [--check FILE|-]
media-analysis conformance [--json]      # AI-video-production-OS SKILL_SPEC.md section 8 self-checks
```

Engine options: `--timeout S`, `--max-analysis-calls N`, `--max-total-seconds S`, `--cache-dir DIR`,
`--cache-policy use|bypass|only`, `--workspace DIR`, `--allowed-input ROOT`.

- With `--json`, stdout is exactly one response document (`media-analysis/response@1`) on success and on failure;
  stderr is diagnostics only. Without `--json`, stdout is human-readable text and errors go to stderr.
- Exit code 0 = every result ok; otherwise the first error's exit code (2..13, table in `contract --json` → `errors`).
- `--dry-run` validates the request and input path and prints the analyzer, required capabilities and the

Read the full skill on GitHub

Details

Skill name: media-analysis
Repository: kajisho5/media-analysis-skill
License: MIT
Repo updated: 31 October 2026

FAQ

What does the Media Analysis skill do?

How do I install the Media Analysis skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add kajisho5/media-analysis-skill --skill media-analysis. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Media Analysis popular?

It lives in kajisho5/media-analysis-skill, which has 9 GitHub stars and 1 forks.

Related skills

Reeljet

Xabilimon1/reeljet

Use when the user wants to create a short promo or demo video (Reels/TikTok/Shorts/landing hero) for an app, web, or SaaS from their own screen recordings and screenshots. Orchestrates creative direction, Higgsfield-generated motion/b-roll, local music, and deterministic ffmpeg assembly into master 16:9 + 9:16. Trigger: /reeljet.

Images, Video & Audio

Linear Style Illustration

yanliudesign/linear-style-illustration

Dark "Linear/AI-OS" style technical diagrams — near-black background, cyan × purple × lilac duotone, JetBrains Mono uppercase labels, pill-shaped SVG nodes, glowing hub/kernel layer. Use when the user wants a "Linear 风格 diagram", a dark tech/architecture diagram, a product flow / state machine / layered-stack / hub-and-spoke diagram for a deck or landing page, or references screenshots that look like a dark AI product OS deck. Outputs a self-contained HTML file with inline SVG, ready to drop into a slide deck or export as PNG. Keywords: Linear style diagram, dark tech diagram, kernel diagram,

Images, Video & Audio

Talking Head Editor

griffinwooldridge/talking-head-editor

Edit raw talking-head footage into a finished video with Claude. Tight cuts that never clip a word, studio-clean voice, reframing and punch-ins, word-timed captions, and cinematic motion graphics written as code, all rendered frame-exact with ffmpeg and HyperFrames. Use when someone hands you a raw recording (camera file, optional separate mic) and asks to "edit this video", "cut my talking head", "add motion graphics", "clean up the audio" or "make this look edited".

Images, Video & Audio

Imperium Brain

ceoimperiumprojects/imperium-brain

The Ultimate Startup OS for Claude Code. Routes to 18 domain skills across startup ops, competitive research, and content creation. Use when the user mentions anything related to: startups, strategy, fundraising, marketing, sales, product, finance, legal, engineering, competitive research, ecosystem mapping, LinkedIn posts, carousels, presentations, slides, brand identity, tone of voice, SOPs, runbooks, video creation, API discovery, images, visual media, stock photos, or any business/startup/content topic.

Images, Video & Audio

3d Brain Animations

SamedVossberg/3d-brain-animations

Render 3D still images and rotating turntable animations of brain regions from ANY BrainGlobe atlas (mouse, rat, human, zebrafish, etc.), with optional glow/bloom highlighting and a semi-transparent whole-brain shell for context. Use this WHENEVER the user wants to visualize, render, picture, or animate brain anatomy: any species, any region (hippocampus, CA1, dentate gyrus, cortex, thalamus, amygdala, ...), any color, a glowing/highlighted region, a rotating brain video, or a neuroanatomy figure for a paper/thesis/slide — even if they don't mention Blender or BrainGlobe. Handles requests like

Images, Video & Audio

Youtube Publisher

smixs/youtube-publisher

End-to-end video publishing pipeline: download from Google Drive, upload to YouTube, transcribe audio via Deepgram or Fireworks Whisper, generate title/description/timestamps, clean up temp files. Use when: "залей на YouTube", "опубликуй видео", "upload to YouTube", "видео из Drive на YouTube", "meet recording to YouTube", "транскрибируй и залей", "publish video", "upload recording". NOT for: video editing, adding intros/effects, non-Drive video sources, YouTube channel management, or live streaming.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.