video-remix SKILL.md skillA
video-remix from puntorigen/avatar-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add puntorigen/avatar-skills/video-remix@git:20260911.808c29bPins git:20260911.808c29b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- puntorigen/avatar-skills
- Path
video-remix/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260911.808c29b, committed Sep 11, 2026
- First version recorded
- Sep 11, 2026
- Size
- 13,048 bytes
- Repository stars
- 6
- License
- MIT
Analyze the visual + narrative + audio MOLD of one or more reference videos (reels/shorts/talking-head clips) — format/ratio, per-scene layout, character position + gaze, palette and color combinations, on-screen elements, action types, caption type/style, brand watermark/logo placement and how it appears/disappears, transitions, the intro->development->close arc, background music and voice-vs-music ducking, and how many distinct presenters speak — then REGENERATE a brand-new reel on NEW…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# video-remix — extract a video's mold, then remix it with new content `reel-discovery` finds a winning video and `pdf-remix` clones a PDF's mold. **video-remix does the same for a video**: it deconstructs a reference reel into a reusable **mold** (visual system + per-scene layout + audio/caption/watermark systems + narrative arc + how many presenters speak) and then rebuilds a new reel — new topic, new narration, freshly generated avatars/locations/voices/music — that follows the mold faithfully. It is a **generalized `reel-restyle`**: any reference video (not just an avatar's own reels), a much richer mold, multiple avatars, and it generates the avatars/locations/voices/music it needs. **Two phases, one skill (mirrors `pdf-remix`):** ``` ANALYZE reference.mp4 ─▶ blueprint.json + blueprint.md + content_template.json REMIX content.json ─▶ avatars/locations/voices/music ─▶ storyboard ─▶ final.mp4 ``` ## When to use - "Analyze this reel and make me a template I can reuse." - "Make a video like this one but about <topic>, with my avatar(s)." - "Copy the estructura / ritmo / captions / música of this reference for a new script." …
Read the whole file at its exact version.
How to install
mdr add puntorigen/avatar-skills/video-remix@sha256:0a91c2cba5b28a1cThe line at the top of this page pins the label git:20260911.808c29b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_bumejelju5i3p2s2)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 11, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260911.808c29b latest | 2026-09-11 | 808c29b | 13,048 B | A | view · diff |
| git:20260911.1afded8 | 2026-09-11 | 1afded8 | 12,076 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13048 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
puntorigen/avatar-skills · 6 stars · license MIT · pushed 2026-09-15 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bumejelju5i3p2s2 GET https://markdownregistry.com/api/v1/resolve?ref=puntorigen/avatar-skills/video-remix GET https://markdownregistry.com/api/v1/blob/0a91c2cba5b28a1c457a71996df736bef8a1f9c19cb6258e91d15d5a76efa7cc
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.