muapi-award-ceremony-video

muapi-award-ceremony-video is a skill for Claude Code, Codex from SamurAIGPT/Generative-Media-Skills. It costs 63 tokens per session (1,898 once invoked), scanned B, original, MIT.

A workflow for generating a 15-second cinematic awards-ceremony video from photos of a host and winner.

In plain words
What is it for?
Use it to create a ceremony scene with an announcement, spotlight, walk to the podium, award presentation, and LED display.
Why use it?
It lays out the required inputs and sequence so the people, spoken name, and on-screen name stay consistent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create a ceremony scene with an announcement, spotlight, walk to the podium, award presentation, and LED display.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samuraigpt/generative-media-skills/award-ceremony-video
About the project

Generative-Media-Skills is a toolkit that lets AI agents generate, edit, and display images, videos, and audio through the muapi command-line interface. It is for users of Claude Code, Cursor, Gemini CLI, and OpenCode who need multimodal media-generation workflows. The catalogue entries are the skills that expose these media capabilities to coding agents.

SamurAIGPT/Generative-Media-Skills · 4,263 stars · on GitHub · muapi.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add SamurAIGPT/Generative-Media-Skills --skill award-ceremony-video
Clone the repo
git clone --depth 1 https://github.com/SamurAIGPT/Generative-Media-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for muapi-award-ceremony-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/award-ceremony-video/github.svg)](https://agentmods.dev/skills/samuraigpt/generative-media-skills/award-ceremony-video)
Your own site
<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/award-ceremony-video"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/award-ceremony-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for muapi-award-ceremony-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/award-ceremony-video"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/award-ceremony-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,898 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 87
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 87
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01898
Opus 5 $0.00032 $0.00949
Sonnet 5 $0.00013 $0.00380
Haiku 4.5 $0.00006 $0.00190

Measured 13d ago against content hash b676fbc9cdc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

muapi-award-ceremony-video scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` (passing `ima

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` (passing `ima
library/motion/award-ceremony-video/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Award Ceremony Video

Generate a 15-second cinematic awards-ceremony video — a host announces a winner from the stage, a spotlight finds them in the crowd, they walk up to the podium, receive the award, and the LED display reveals their name and "THE BEST ACTOR".

Inputs

Name Type Required Default Description
winner_image image_url yes A clear photo of the winner. Becomes @image_1 — their identity is strict-locked across the video.
host_image image_url yes A clear photo of the host. Becomes @image_2 — sole presenter on stage at the podium.
winner_name text no Olivia The name announced by the host and shown on the LED stage display under "THE BEST ACTOR".

Steps

Phase A — Confirm Inputs

If either {{winner_image}} or {{host_image}} is missing, ask the user to upload them. Confirm {{winner_name}} before generation — it appears spoken in the audio and rendered on the LED display.

Phase B — Generate the Ceremony Video

Submit the plan with ONE step using the Seedance 2.0 image-to-video fast variant (multi-reference). Pass the images in this exact order — order maps to @image_1 then @image_2:

  1. Award Ceremony Videomuapi video from-image (model=seedance-2-image-to-video-fast, or fall back to raw endpoint bytedance-seedance-2-0-reference-to-video-fast):
    • Reference images (in order): {{winner_image}}, {{host_image}}
    • Aspect ratio: 16:9
    • Duration: 15
    • Resolution: 720p
    • Generate audio: true
    • Prompt:
      **Style:** Ultra-realistic live awards ceremony scene. Multi-camera broadcast style — switches between polished TV broadcast angles and intimate handheld documentary coverage. Cinematic prestige feel — think Grammy Awards or Academy Awards production quality. Natural human reactions, no over-acting.
      
      **Audio:** Natural ceremony sound — elegant orchestral background music, host microphone voice projecting through venue speakers, crowd murmur, then erupting applause and cheers, chair movement, footsteps on stage, trophy/plaque handling sound, emotional crowd reaction.
      
      **Lighting:** Grand indoor awards venue. Dramatic stage lighting — warm golden spotlights on stage, cooler ambient lighting over audience seating. Broadcast camera lights. LED stage displays casting colored light. When winner is announced — a warm spotlight sweeps and locks onto the winner in the audience.
      
      **Setting:** Massive prestigious awards venue — Grammy or Academy Awards scale. Grand stage with towering LED displays, elegant podium, live orchestra pit. Thousands of formally dressed audience members seated in rows. Press cameras lining the aisles. Large overhead screens showing live broadcast feed. The venue radiates prestige and scale.
      
      **Main Character STRICT LOCK:**
      
      **@image_1 — THE WINNER "{{winner_name}}":** Use @image_1 as strict identity. The person dressed in formal awards show attire for the award ceremony. No sunglasses. No modifications to face or build. Seated in the audience among other formally dressed attendees.
      
      **@image_2 — THE HOST:** Use @image_2 as strict identity as the sole host on stage at the podium. Maintain exact face, build, and features. Dressed in formal awards show attire. No modifications to face or build allowed.
      
      **SCENE TIMELINE — 15 SECONDS**
      
      **0–3s — THE ANNOUNCEMENT:**
      **Broadcast close-up** directly on @image_2's face — tight, cinematic, high production quality. @image_2 stands at the podium microphone under a warm golden spotlight. Expression is composed, charismatic, building suspense deliberately. The person holds the envelope or card, glances down at it one final time, then looks straight into camera. A beat of silence. The person leans into the microphone and says slowly: *"And the winner is..."* Camera holds tight on @image_2's face — lips, expression, the tension of the moment. Crowd murmur audible in background.
      
      **3–6s — THE WINNER:**
      Hard **broadcast cut** to audience — low-angle TV camera shot pushing through seated rows. Camera finds @image_1 seated among other guests, relaxed, not expecting it. @image_2's voice continues booming through the venue speakers: *"...{{winner_name}}"* Spotlight snaps onto @image_1 from above. The person's expression shifts — genuine shock, eyes wide, mouth slightly open, then breaks into a real overwhelmed smile. The person looks left and right at the people beside in disbelief. The crowd erupts into applause and cheers. People around the person stand, clapping, patting their shoulders.
      
      **6–9s — RISING AND WALKING:**
      @image_1 straightens up, composes themselves, stands from their seat. **Handheld documentary camera** picks the person up immediately — tracking from the aisle as the person moves forward toward the stage. Camera moves with the person — slightly shaky, intimate, real. Applause continues thundering through the venue. Overhead broadcast screens cut to the person's face live. The person walks with composure — attire clean, posture upright, expression warm and slightly emotional.
      
      **9–12s — REACHING THE STAGE:**
      Handheld camera follows @image_1 up the stage steps. Bright stage spotlights hit the person fully as they ascend. @image_2 steps forward from the podium smiling warmly, holding the award plaque with both hands. @image_1 reaches the podium. @image_2 presents the plaque — @image_1 receives it with both hands, looks down at it for a brief genuine moment. The two share a natural smile and brief handshake. Behind them on the massive **LED stage display**: a large portrait of @image_1's face, the person's name in bold elegant typography — **"{{winner_name}}"** — and beneath it: **"THE BEST ACTOR."** The display glows and pulses with celebratory graphics.
      
      **12–15s — THE MOMENT:**
      Camera settles into a **wide broadcast shot** of the full stage — @image_1 standing at the podium, award plaque in hand, @image_2 standing beside the person, LED wall blazing behind them both with @image_1's name and face. Spotlights lock on @image_1. Applause fills the entire venue — standing ovation building across the audience. @image_1 raises the plaque slightly, looks out at the crowd, smile composed and genuine. @image_2 leads the applause from the stage beside the person. Final frame holds — the full stage, the glowing LED display, the roaring crowd, and @image_1 standing at the center of it all. No fade to black.
      

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 88 lines · 63 tokens per session scan B b676fbc9cdc4

Subscribe to this mod's changes

muapi-award-ceremony-video is a skill published in the GitHub repository SamurAIGPT/Generative-Media-Skills (4,263 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 1,898 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mlops-automation

Automate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking on a SQL backend. Use when adding a task runner, git hooks, CI/CD, or experiment tracking to a working package.

MLOps-Courses/mlops-coding-skills · 58 tokens

mlops-validation

Add the validation layers that gate a merge — ty typing, Ruff linting, pytest coverage, structured logging, and the trivy, pip-audit, and gitleaks scans. Use when hardening code quality or wiring the mise run check task.

MLOps-Courses/mlops-coding-skills · 55 tokens

mlops-prototyping

Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.

MLOps-Courses/mlops-coding-skills · 50 tokens

mlops-collaboration

Prepare a project for public collaboration — license, code of conduct, docs, branch rulesets, templates, and git-cliff releases. Use when open-sourcing a repository, onboarding contributors, or cutting a tagged release.

MLOps-Courses/mlops-coding-skills · 50 tokens

mlops-observability

Make an ML system a glass box with reproducible runs, MLflow dataset lineage, drift monitoring, alerting, and SHAP explanations. Use when a deployed model needs traceability, monitoring, alerting, or explanation.

MLOps-Courses/mlops-coding-skills · 51 tokens

mlops-industrialization

Convert notebook prototypes into a distributable Python package with a src layout, a domain/io/application split, and validated OmegaConf plus Pydantic configuration. Use when moving code out of notebooks or designing entrypoints.

MLOps-Courses/mlops-coding-skills · 48 tokens