align-video SKILL.md skillA
align-video from wanshuiyin/align-agentic-loop-image-generation is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wanshuiyin/align-agentic-loop-image-generation/align-video@git:20261001.f91dee0Pins git:20261001.f91dee0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wanshuiyin/align-agentic-loop-image-generation
- Path
skills/align-video/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261001.f91dee0, committed Oct 1, 2026
- First version recorded
- Oct 1, 2026
- Size
- 50,028 bytes
- Repository stars
- 49
- License
- MIT
ALIGN-video for Claude Code with independent Codex adversarial review. Create or revise a video through agent-authored code, rendering, editing and fresh-context audiovisual review, without image, video or music generation models. Use for reference-led animation, procedural films, motion design, explainers, construction replays, and continuing an existing coded-video project. Carries the work from reference study and animatic through a finished, reproducible film; supports explicitly requested…
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
# ALIGN-video — Claude makes the film, Codex challenges it > The loop runs inside this task: make → render → watch → review → decide → > revise. A changed film starts the next round. No scheduler is needed. You are the filmmaker and the programmer. Study the reference, decide what the audience should experience, and write the implementation that can produce it. The deliverable is a watchable film with its working source. The source gives you unusually direct control over geometry, drawing, motion, sound and editing; use that control to make better film decisions. Keep returning to what the render actually communicates. This extends ALIGN's reference-art loop into time. A picture's composition now includes the order in which information arrives, how long a viewer has to read it, and what the next shot makes the previous one mean. A convincing frame can belong to an inert sequence. A technically correct simulation can hide the action that matters. Work on the sequence early enough that changing it is still cheap. Use prose to carry the creative reasoning. Choose the renderer, languages, libraries and small utilities from the work at hand. Blender, browser graphics, …
Read the whole file at its exact version.
How to install
mdr add wanshuiyin/align-agentic-loop-image-generation/align-video@sha256:03cc2e3e536d5118The line at the top of this page pins the label git:20261001.f91dee0, 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_ztfpppycmoifcjnc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 1, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261001.f91dee0 latest | 2026-10-01 | f91dee0 | 50,028 B | A | view · diff |
| git:20261001.648fc1d | 2026-10-01 | 648fc1d | 49,911 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 (50028 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
wanshuiyin/align-agentic-loop-image-generation · 49 stars · license MIT · pushed 2026-10-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ztfpppycmoifcjnc GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/align-agentic-loop-image-generation/align-video GET https://markdownregistry.com/api/v1/blob/03cc2e3e536d511870b2a989795a787c1d4912e508b03c706d2af2748dfc533c
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.
More from wanshuiyin/align-agentic-loop-image-generation
Every file in wanshuiyin/align-agentic-loop-image-generation