Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate AI videos using varg SDK React engine. Use when creating videos, animations, talking characters, slideshows, or social media content. Always run onboarding first to check API keys.
.claude/skills/varghq-varg-video-generation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 1% | 0% |
This rule helps you generate AI videos using the varg SDK's React engine. It provides:
Before generating videos, ensure the user has the required API keys configured.
Run this command to check existing configuration:
bashcat .env 2>/dev/null | grep -E "^(FAL_KEY|ELEVENLABS_API_KEY|REPLICATE_API_TOKEN|GROQ_API_KEY)=" || echo "No API keys found in .env"
This is the minimum requirement for video generation.
| Detail | Value | |--------|-------| | Provider | Fal.ai | | Get it | https://fal.ai/dashboard/keys | | Free tier | Yes (limited credits) | | Used for | Image generation (Flux), Video generation (Wan 2.5, Kling) |
If user doesn't have FAL_KEY:
.env file in project root| Feature | Required Key | Provider | Get It | |---------|-------------|----------|--------| | Music generation | ELEVENLABS_API_KEY | ElevenLabs | https://elevenlabs.io/app/settings/api-keys | | Voice/Speech | ELEVENLABS_API_KEY | ElevenLabs | https://elevenlabs.io/app/settings/api-keys | | Lipsync | REPLICATE_API_TOKEN | Replicate | https://replicate.com/account/api-tokens | | Transcription | GROQ_API_KEY | Groq | https://console.groq.com/keys |
When keys are missing, inform user what features are unavailable.
bashbunx vargai render video.tsx
| Component | Purpose | Required Key | |-----------|---------|--------------| | <Render> | Root container | - | | <Clip> | Sequential segment | - | | <Image> | AI image | FAL | | <Video> | AI video | FAL | | <Music> | Background music | ElevenLabs | | <Speech> | Text-to-speech | ElevenLabs |
tsxconst character = Image({ prompt: "blue robot" }); // Reuse same reference for consistent appearance <Video prompt={{ text: "waving", images: [character] }} /> <Video prompt={{ text: "dancing", images: [character] }} />
tsx<Clip transition={{ name: "fade", duration: 0.5 }}> // Options: fade, crossfade, wipeleft, cube, slideup, etc.
9:16 - TikTok, Reels, Shorts (vertical)16:9 - YouTube (horizontal)1:1 - Instagram (square)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | pass→pass | 4,173 | 1,745 | -58% | 1 | 1 | 0% | 632 | 971 | +54% | 0 | 0 | — |
case-01 | fail→fail | 16,982 | 2,439 | -86% | 1 | 1 | 0% | 3,249 | 1,187 | -63% | 0 | 0 | — |
case-02 | fail→fail | 6,765 | 3,065 | -55% | 1 | 1 | 0% | 1,048 | 1,086 | +4% | 0 | 0 | — |
case-03 | fail→fail | 13,761 | 7,924 | -42% | 1 | 1 | 0% | 2,613 | 2,163 | -17% | 0 | 0 | — |
case-04 | fail→pass | 10,021 | 7,249 | -28% | 1 | 1 | 0% | 1,714 | 2,105 | +23% | 0 | 0 | — |
case-05 | fail→pass | 10,765 | 3,304 | -69% | 1 | 1 | 0% | 1,717 | 1,223 | -29% | 0 | 0 | — |
case-06 | fail→pass | 7,729 | 2,246 | -71% | 1 | 1 | 0% | 1,244 | 1,034 | -17% | 0 | 0 | — |
case-07 | fail→pass | 15,075 | 7,984 | -47% | 1 | 1 | 0% | 2,483 | 2,238 | -10% | 0 | 0 | — |
case-08 | fail→pass | 7,054 | 3,497 | -50% | 1 | 1 | 0% | 1,333 | 1,344 | +1% | 0 | 0 | — |
case-09 | pass→pass | 5,928 | 2,564 | -57% | 1 | 1 | 0% | 950 | 1,166 | +23% | 0 | 0 | — |
case-11 | pass→pass | 5,115 | 1,216 | -76% | 1 | 1 | 0% | 748 | 896 | +20% | 0 | 0 | — |
case-12 | pass→pass | 15,347 | 2,091 | -86% | 1 | 1 | 0% | 2,584 | 1,079 | -58% | 0 | 0 | — |
case-13 | fail→pass | 11,563 | 2,054 | -82% | 1 | 1 | 0% | 1,751 | 1,063 | -39% | 0 | 0 | — |
case-14 | fail→pass | 7,044 | 1,908 | -73% | 1 | 1 | 0% | 1,237 | 1,041 | -16% | 0 | 0 | — |
case-15 | fail→pass | 10,034 | 2,153 | -79% | 1 | 1 | 0% | 1,563 | 1,084 | -31% | 0 | 0 | — |
case-16 | pass→pass | 11,378 | 2,595 | -77% | 1 | 1 | 0% | 1,910 | 1,118 | -41% | 0 | 0 | — |
case-17 | fail→pass | 11,325 | 2,247 | -80% | 1 | 1 | 0% | 1,868 | 1,078 | -42% | 0 | 0 | — |
case-18 | fail→pass | 21,727 | 1,916 | -91% | 1 | 1 | 0% | 3,473 | 1,057 | -70% | 0 | 0 | — |
case-19 | fail→pass | 10,760 | 2,664 | -75% | 1 | 1 | 0% | 1,833 | 1,146 | -37% | 0 | 0 | — |
case-20 | pass→pass | 17,123 | 4,527 | -74% | 1 | 1 | 0% | 2,450 | 1,363 | -44% | 0 | 0 | — |
case-21 | pass→pass | 11,516 | 7,073 | -39% | 1 | 1 | 0% | 1,962 | 1,954 | -0% | 0 | 0 | — |
case-22 | pass→pass | 11,926 | 8,241 | -31% | 1 | 1 | 0% | 2,405 | 2,388 | -1% | 0 | 0 | — |
case-23 | pass→pass | 12,590 | 11,699 | -7% | 1 | 1 | 0% | 2,508 | 3,089 | +23% | 0 | 0 | — |
case-24 | pass→pass | 5,667 | 3,178 | -44% | 1 | 1 | 0% | 1,006 | 1,340 | +33% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +46 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.