Borrowing it
Nothing to install: this file belongs to HomenShum/NodeBenchAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HomenShum/NodeBenchAI/main/.claude/skills/demo-video-quality-loop/SKILL.mdgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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.
[](https://agentmods.dev/skills/homenshum/nodebenchai/demo-video-quality-loop)<a href="https://agentmods.dev/skills/homenshum/nodebenchai/demo-video-quality-loop"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/demo-video-quality-loop/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.
<a href="https://agentmods.dev/skills/homenshum/nodebenchai/demo-video-quality-loop"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/demo-video-quality-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
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 →
- high Tool Misuse · line 186 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 68 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 127 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 82 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 130 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02968 |
| Opus 5.5 | $0.00000 | $0.01187 |
| Sonnet 5.5 | $0.00000 | $0.00594 |
| Haiku 4.5 | $0.00000 | $0.00297 |
Grade A, and why
demo-video-quality-loop scanned grade A with 0 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Video Quality Loop
Autonomous self-improving pipeline for creating top-market demo videos using Remotion + Gemini video understanding.
When to use
- User says "improve the demo video", "run the video loop", "judge the video"
- After rendering a new version of the demo video
- When targeting a specific quality grade (S/A/B/C)
- When preparing for a launch, demo day, or investor meeting
Architecture
Storyboard (storyboard.ts)
|
v
Remotion Renderer (SceneView.tsx + NodeBenchDemo.tsx)
|
v
MP4 Output (out/nodebench-demo-v2.mp4)
|
v
Gemini Video Understanding Judge (scripts/judge-demo-video.ts)
|
v
10-Dimension Score + Actionable Suggestions
|
v
Fix storyboard/renderer based on suggestions
|
v
Re-render → Re-judge → Loop until target grade
The 10 Scoring Dimensions
| Dimension | What it measures | Weight |
|---|---|---|
| Pacing | Scene duration feel, momentum, energy curve | High |
| Visual Clarity | Text readability, element sharpness, contrast | High |
| Info Density | Balance of detail vs. overwhelm per scene | Medium |
| Transitions | Smoothness, variety, content-appropriate cuts | Medium |
| Narration Sync | Voice-visual alignment, timing of highlights | High |
| Interactions | Cursor naturalness, streaming text, wipes, zooms | High |
| Montage | Rapid-cut energy, label readability, breadth coverage | Medium |
| Opening Hook | First 5 seconds grab attention, "wow" factor | Critical |
| Emotional Arc | Build-up, hero moment, crescendo, resolution | High |
| Call to Action | Clear next step, memorable stats, URL visible | Medium |
Grade Scale
| Score | Grade | Meaning |
|---|---|---|
| 90-100 | S | Viral-quality. Screenshot-worthy. Would trend on Twitter. |
| 80-89 | A | Professional. Comparable to Linear/Cursor/Arc demos. |
| 70-79 | B+ | Good but missing energy or hook. Needs polish. |
| 60-69 | B | Functional demo. Won't inspire sharing. |
| 50-59 | C | Below market standard. Needs structural rework. |
| <50 | D/F | Fundamentally broken. Start over. |
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.
- 1mo ago First seen · 278 lines · 0 tokens per session scan A f99d4e28f772
demo-video-quality-loop is a skill published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,968 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
create-tech-design
Only use when the user explicitly invokes this skill by name.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…