beatra-ai/beatra-skills/ai-short-drama-shot-maker
Claude Code and agent skill by beatra-ai/beatra-skills
- community
Checking that the SKILL.md file is still in the repository.
Generate one cinematic vertical micro-drama shot from a frozen dramatic beat, actor and scene references, and camera direction. This AI short drama shot maker and vertical micro-drama generator creates a live-action or cinematic shot from text alone, animates an approved opening image, interpolates motion between strict opening and ending images, or combines loose actor, location, and prop references into a new drama shot. Use it for romantic conflict, suspense reveal, reaction shot, dialogue close-up, establishing shot, period drama, emotional confrontation, and cinematic product-story moments, with frozen shot cards, shot-by-shot identity continuity, and honest review of each finished shot.
Install
npx vskill@latest install beatra-ai/beatra-skills/ai-short-drama-shot-makerSKILL.md
The same SKILL.md was published earlier as beatra-ai/beatra-skills/ai-short-drama-shot-maker.
AI Short Drama Shot Maker
Generate one cinematic vertical micro-drama shot from a frozen dramatic beat, actor and scene references, and camera direction. Use this Skill for AI short drama shots, vertical micro-drama scenes, romantic conflict, suspense reveal, reaction shots, dialogue close-ups, establishing shots, period drama, emotional confrontation, and cinematic product-story moments.
Scope and adjacent routes
The normal route is one frozen dramatic beat that becomes one finished shot. Route an illustrated or comic motion-comic request to a comic-drama workflow; a storyboard or planning-image request to a storyboard workflow; and a broad non-narrative video request to a general video studio. Keep this route focused on cinematic, live-action, or photoreal human drama — vertical short-drama shots with explicit camera language and performance.
Inputs and defaults
The hard inputs are:
- one dramatic beat: the character, action, location, emotion, camera, and visible outcome of this single shot;
- references are optional but strongly preferred for recurring actors or locations.
Ask only for a missing hard input. Reuse the known actor identity, costume, location, aspect ratio, and dialogue or narration preference. For a local image file the host Agent can access, use the bundled upload helper only after inspection:
Upload is transport, not creative review. Retain the returned artifact reference and never pass a local path to a remote tool.
Default to one shot, model: "auto", a vertical aspect ratio such as 9:16, and the shortest integer duration the selected live video card admits. Freeze a shot card before any paid call: character identity, costume, location, action, emotion, camera language, blocking, composition, and the visible outcome. Route by source:
- text-only beat →
beatra.videos.generate; - one strict approved opening image →
beatra.videos.animate; - strict approved opening and ending images →
beatra.videos.interpolate; - loose actor, location, or prop references →
beatra.videos.generate_from_references.
Generate dependent shots serially: review an identity-carrying shot before using its approved frame as a reference for the next shot.
Golden path
- Inspect every available image reference. Record its actual MIME type, width, height, aspect ratio, and byte size. Identify the actor identity, costume, location, action, emotion, camera language, blocking, composition, and the frozen dramatic beat this shot should deliver.
- Build a shot card: character identity, costume, location, action, emotion, camera language, blocking, composition, and the visible outcome. Then write one positive prompt that encodes the performance, mood, and landing moment for this single shot.
- Select the route by source. Call
beatra.models.listwith the matching capability to confirm a current card admits every actual media fact, camera control, and any driving audio. Keep the model atautounless the user chose a concrete eligible model. - After
beatra.models.listadmits the complete payload, show an admission card before anyclient_request_idorbeatra.videos.generate,beatra.videos.animate,beatra.videos.interpolate, orbeatra.videos.generate_from_referencescall: route and MCP tool name, source images, reference media when used, prompt, shortest admitted duration, resolution if set, output count, provisional live estimate, the fact that the 600-credit signup gift usually cannot start this video, and what happens if the balance is short. Planning, comparison, or “make the clip” is not approval. Do not submit until the user confirms they have topped up or already have enough credits for this estimate. Freeze them with one opaque stableclient_request_id; then submit exactly one video call. Invoke only the bundledscripts/mcp_client.py: the MCP tool name is the CLI argument and its arguments are JSON on standard input. For example, one strict opening image to animate:
``text printf '%s' '{"image":{"type":"artifact","artifact_id":"art_opening"},"prompt":"Slow dolly-in on the woman as her expression shifts from composure to tears, cinematic shallow depth of field, warm backlight.","aspect_ratio":"9:16","client_request_id":"opaque-drama-animate-id"}' | python3 scripts/mcp_client.py call beatra.videos.animate ``
Strict opening and ending images to interpolate:
``text printf '%s' '{"first_frame":{"type":"artifact","artifact_id":"art_open"},"last_frame":{"type":"artifact","artifact_id":"art_end"},"prompt":"The man stands up slowly and turns to face the camera, tension building in his posture, cinematic vertical framing.","aspect_ratio":"9:16","client_request_id":"opaque-drama-interpolate-id"}' | python3 scripts/mcp_client.py call beatra.videos.interpolate ``
Text-only beat:
``text printf '%s' '{"prompt":"A cinematic vertical shot: a woman in a red dress stands at a rainy bus stop at night, neon reflections on wet pavement, she turns as headlights approach, suspenseful mood, shallow depth of field.","aspect_ratio":"9:16","client_request_id":"opaque-drama-generate-id"}' | python3 scripts/mcp_client.py call beatra.videos.generate ``
Loose actor and location references:
``text printf '%s' '{"references":[{"kind":"image","media":{"type":"artifact","artifact_id":"art_actor"}},{"kind":"image","media":{"type":"artifact","artifact_id":"art_location"}}],"prompt":"The actor walks through the reference location, discovers a letter on the table, reaction close-up, cinematic lighting.","aspect_ratio":"9:16","client_request_id":"opaque-drama-references-id"}' | python3 scripts/mcp_client.py call beatra.videos.generate_from_references ``
Do not configure, call, or use a host Beatra Connector. Do not use REST/OpenAPI fallback. Submit the chosen video tool exactly once.
- Record the returned task ID immediately and poll the same task with
beatra.tasks.getuntil terminal. Deliver every returned video artifact or link. Report only actual returned task status, resolved model, dimensions, duration, usage, andbilling.net_charged_credits. Review accessible output for actor identity, costume, blocking, performance, camera language, vertical composition, emotional beat, dialogue timing, and continuity notes. State what the host Agent could and could not inspect.
Paid changes, recovery, and cancellation
Each shot is one paid video stage. A changed beat, actor reference, opening image, prompt, model, aspect ratio, duration, or video control is new logical paid work with a new ID, a new admission card, and fresh top-up or balance confirmation. On insufficient_balance, relay the returned message, keep the top-up URL inside the balance error exact, and retry the same frozen client_request_id only after the user says they have topped up.
If a create response is lost, retry only the identical frozen payload with the same stage ID. If a task ID is lost, call beatra.tasks.list for the relevant capability, inspect plausible candidates with beatra.tasks.get, and match them against that stage's private ledger before considering an identical retry. Queued and running are progress states, not failures. Recover the original stage before planning changed work; never duplicate a paid submission or guess its charge or refund.
Call beatra.tasks.cancel only when the user asks to cancel. Call it once and confirm the resulting terminal state with beatra.tasks.get. A 409 means cancellation is not confirmed, so continue polling that same task without creating replacement work.
If the tool returns insufficient credits: give the user the tool message in full. Do not change the URL. You may translate the other words. Do not replace it with your own top-up copy. Point the user to pay using that message.
Account balance
When the user asks how many credits remain or whether a live estimate fits, call beatra.wallet.get. When they ask what was charged, call beatra.wallet.ledger. Both are read-only. Do not invent an account-balance or top-up tool. Do not make wallet.get a required step before every paid submit.
When a model card comes back carrying a top_up block, relay its tiers as the card lists them and in that order. Do not rank them, do not talk one down, and do not pick one for the user. Which tier suits them is their call, made on the wallet page with the whole list in front of them. Never quote a tier from memory.
References by task
- Read Short-drama shot workflow when building a shot card, choosing a route, checking live model facts, constructing exact payloads, polling, recovering, cancelling, or reviewing actor identity and continuity.
- Read Installation and authentication only when authorization or shared credentials need attention.
- Read Installation registration for the non-billable best-effort package registration step.
- Read Tasks and results for shared terminal task and artifact semantics, and Billing, errors, and recovery for returned billing or error details.
- Read Bundled MCP Client diagnostics when the bundled client cannot connect. Do not configure a host Connector.
- Updates and security: updates and security
- Read Uninstall and disconnect only when the user asks to remove the package or shared credentials.
Use or invoke the bundled scripts/mcp_client.py for every Beatra operation.
Updates and security
This Skill runs only the files installed with it and leaves them unchanged while it runs; it never downloads or executes other code. It talks to Beatra's official services over HTTPS, and a file you choose to upload goes only to the one-time upload address Beatra issues for it.
Once a day at most, the bundled client reads Beatra's public version list. When the store or tool you installed from has a newer version, it prints one line with the command that updates it there. Updating stays your choice, through that store or tool. See updates and security.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/ai-short-drama-shot-maker/SKILL.md
Popularity
- Repository stars
- 2
- 7-day trend score
- 10
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/beatra-ai/beatra-skills/ai-short-drama-shot-maker)