creator-drop-talking SKILL.md skillA
creator-drop-talking from beatra-ai/beatra-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add beatra-ai/beatra-skills/creator-drop-talking@git:20261015.2337206Pins git:20261015.2337206 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- beatra-ai/beatra-skills
- Path
skills/creator-drop-talking/SKILL.md- Versions recorded
- 3
- Latest version
- git:20261015.2337206, committed Oct 15, 2026
- First version recorded
- Aug 28, 2026
- Size
- 9,508 bytes
- Repository stars
- 6
- License
- MIT-0
Turn a confirmed new-drop script and authorized stills into one drop talking clip per still. This product drop video studio writes a speakable launch talking clip and new-drop announcement for each photo, then animates a 2 to 15s talking teaser. Use it for creator drop videos and talking teasers that stay one photo, one clip.
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
# Creator Drop Talking Clips Turn a confirmed drop script and authorized stills into one talking teaser per still. Deliver 2 to 8 clips. Do not stitch them. ## Scope and adjacent routes Use this Skill when a creator or listing team wants short talking clips that announce a new drop from stills they can authorize. Route a generic presenter that is not a drop announcement to `talking-avatar-video`. Route a homestay welcome to `airbnb-welcome-avatar`. Route silent product motion to `product-video-studio`. Route an oral seeding brief that is not a still-driven talking teaser to `oral-seeding-video-maker`. ## Collect the drop Hard inputs are: - at least one accessible still the host Agent can inspect — a presenter portrait or a drop photo that will be the first frame; - confirmed drop facts the seller already wrote (what is new, when it lands, what the still actually shows); - likeness and voice rights when a face or a cloned voice will appear; - how many clips the pack should contain, or permission to use the default of 3. Reuse already-known language, SKU names, and a frozen `voice_id`. Ask only for a missing hard input. A count outside 2 to 8 is still …
Read the whole file at its exact version.
How to install
mdr add beatra-ai/beatra-skills/creator-drop-talking@sha256:66dbc4eb8f9790aaThe line at the top of this page pins the label git:20261015.2337206, 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_xv6igogwuqtse24y)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Aug 28, 2026 and Oct 15, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.2337206 latest | 2026-10-15 | 2337206 | 9,508 B | A | view · diff |
| git:20260906.8237016 | 2026-09-06 | 8237016 | 9,911 B | A | view · diff |
| git:20260828.7c66c9c | 2026-08-28 | 7c66c9c | 9,505 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 (9508 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
beatra-ai/beatra-skills · 6 stars · license MIT-0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xv6igogwuqtse24y GET https://markdownregistry.com/api/v1/resolve?ref=beatra-ai/beatra-skills/creator-drop-talking GET https://markdownregistry.com/api/v1/blob/66dbc4eb8f9790aad56a8742166036e39a1de14d68b608f92f169aa7f58fd5a3
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.