avatar-reel-composer SKILL.md skillA
avatar-reel-composer 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/avatar-reel-composer@git:20260717.a87eb1bPins git:20260717.a87eb1b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- puntorigen/avatar-skills
- Path
avatar-reel-composer/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260717.a87eb1b, committed Jul 17, 2026
- First version recorded
- Jul 9, 2026
- Size
- 48,134 bytes
- Repository stars
- 6
- License
- MIT
Turn a script + an existing avatar into a finished reel — 9:16 vertical (TikTok/Reels) or 16:9 landscape (YouTube), set via the storyboard `format`. Narrates the script once in the avatar's cloned voice, cuts it per scene by word-level alignment, generates lip-synced talking-head scenes (avatar-talking-video) and silent B-roll scenes (broll-generator) as voice-over, applies Ken Burns / zoom motion, and assembles with hard cuts under one master narration. Can weave in a GUEST/cameo scene…
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
# Avatar Reel Composer Orchestrates the sibling skills into one finished reel from a **script** + an **existing avatar**, replicating the structure of the avatar's analyzed reels. An optional **finishing pass** (`finish_reel.py`) adds burned-in word-timed subtitles + a music bed under the voice — flat by default, or a **structured volume envelope** (entrance / lift / settle / duck / resolve, anchored to scene boundaries) that makes the soundtrack do editing work. SFX stingers and dissolves are still deferred (see *Next phases*). ## When to use - The user has an avatar folder (e.g. `lolo/`) that already contains `videos/`, a trained voice in `voices/`, camera-angle images in `angles/`, and ideally a `talking_profile.json` (all produced by the upstream skills below). - They give you a **script** (what the avatar should say) and want a reel — 9:16 vertical (TikTok/Reels) or 16:9 landscape (YouTube), set via the storyboard's `format` — where the avatar's voice narrates continuously while the video cuts between talking-head shots and complementary B-roll — exactly like the original reels analyzed by `video-scene-analysis`. For 16:9, use the avatar's …
Read the whole file at its exact version.
How to install
mdr add puntorigen/avatar-skills/avatar-reel-composer@sha256:6c62c900c94c2daaThe line at the top of this page pins the label git:20260717.a87eb1b, 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_tsohud6ul2xk6t5i)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 9, 2026 and Jul 17, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260717.a87eb1b latest | 2026-07-17 | a87eb1b | 48,134 B | A | view · diff |
| git:20260713.037b8e1 | 2026-07-13 | 037b8e1 | 47,700 B | A | view · diff |
| git:20260709.ec45941 | 2026-07-09 | ec45941 | 43,781 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 (48134 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_tsohud6ul2xk6t5i GET https://markdownregistry.com/api/v1/resolve?ref=puntorigen/avatar-skills/avatar-reel-composer GET https://markdownregistry.com/api/v1/blob/6c62c900c94c2daaba0796959202c34a571874ca3ff5f87fb4c72fff8b19a07f
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.