Social Media Video Creator

Muapi social media video

by SamurAIGPT · MIT license · ★ 4,317 on GitHub · v1.0.0 · updated Sep 8

Muapi social media video cover

Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and…

---
slug: muapi-social-media-video
name: muapi-social-media-video
version: "1.0.0"
description: Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.
acceptLicenseTerms: true
---

# Social Media Video Creator

**End-to-end pipeline: Brand Files → Storyboard → Reference Images → Seedance 2.0 Video.**

Reads your brand identity, ICP, and messaging documents to produce on-brand social video — fully optimized for Seedance 2.0's instructional prompt grammar and your target platform.

---

## Agent Execution Protocol

Overview

End-to-end pipeline: Brand Files → Storyboard → Reference Images → Seedance 2.0 Video.

The SKILL.md below is the copy AgentAlley read and checked. The repo has changed it since; the other files are from commit 5519622.

Manual install (npx, ZIP)
Claude Codenpx skills add SamurAIGPT/Generative-Media-Skills --skill muapi-social-media-video -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/SamurAIGPT/Generative-Media-Skills/tar.gz/5519622e885a \ | tar -xz -C ~/.claude/skills --strip-components=3 Generative-Media-Skills-5519622e885a/.opencode/skills/muapi-social-media-video
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/73ddc1cfdbe06a5d89a1/muapi-social-media-video.zip" -OutFile "$env:TEMP\muapi-social-media-video.zip"; Expand-Archive "$env:TEMP\muapi-social-media-video.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md11.2 KB
Read the files here
SamurAIGPT/55196221 file
Shared references1SKILL.md reads these from elsewhere in the repo. Not in the ZIP.Get them on GitHub ↗
SKILL.md
Show the full text277 lines

Social Media Video Creator

End-to-end pipeline: Brand Files → Storyboard → Reference Images → Seedance 2.0 Video.

Reads your brand identity, ICP, and messaging documents to produce on-brand social video — fully optimized for Seedance 2.0's instructional prompt grammar and your target platform.


Agent Execution Protocol

Step 1 — Read Brand Files

Before writing anything, the agent MUST read all available brand files. Look for them in the working directory or any brand/ subdirectory:

File What to extract
brand-identity.md Visual style, color palette, tone, logo/product aesthetics, brand personality
ICP.md Target audience — who they are, their pain points, what motivates them
messaging.md Core value props, hooks, CTAs, campaign themes, taglines

If a file is missing, proceed with what's available and note the gap.


Step 2 — Write the Social Post + Storyboard

Use brand context to produce:

Social Post Copy (for caption/copy):

  • Hook line (first 1–2 sentences — must stop the scroll)
  • Body (3–5 sentences: problem → solution → proof → CTA)
  • Hashtags (5–8 relevant tags)
  • CTA (one clear action)

Storyboard (match duration to platform spec):

0–3s:  [Opening scene — hook/visual surprise — camera move]
3–7s:  [Core message — product/subject in action — camera move]
7–10s: [Resolution — brand moment — CTA text on screen]
10–15s: [Logo/tagline hold — background music fade]

Tone must match brand personality. If brand is playful → upbeat transitions, bright grade. If brand is premium → slow reveals, dark luxury aesthetic, moody lighting.


Step 3 — Craft the Seedance 2.0 Director Prompt

Transform the storyboard into a technical Director Brief for Seedance 2.0.

Rules:

  1. Never use vague descriptors ("beautiful", "amazing", "8k"). Use technical cinematography language.
  2. Always specify camera movement, lens type, and lighting physically.
  3. For 10s+ videos, use timecode segments: 0–3s: [...] 3–7s: [...] 7–10s: [...]
  4. Integrate @image1, @image2 reference tags if images are provided.
  5. Always include sound direction (even brief) — Seedance generates audio.
  6. Lead with composition, end with texture and micro-motion.

Director Brief Template:

[SCENE] {environment, lighting, time of day}
[SUBJECT] {product/character/subject with specific detail}
[ACTION] {what happens — fluid, continuous, physically plausible}
[CAMERA] {movement + lens + framing}
[STYLE] {color grade, mood, film reference if helpful}
[SOUND] {music tone, sound effects, ambient}
0–Xs: {if multi-beat}

Step 4 — Generate Reference Images (If Needed)

When to generate reference images:

Scenario Mode Images Needed
Product showcase i2v 1 product shot as first frame
Scene transition first-last 2 images — opening and closing frame
Brand character i2v 1 character reference
Pure concept t2v None — text only
Mood/style anchor i2v 1 style reference image

Image generation — best models by use case:

Use Case Recommended Model Why
Photorealistic product/scene google-imagen4-ultra Highest realism, great lighting
Concept art / stylized flux-kontext-pro-t2i Creative fidelity, style adherence
Fastest turnaround google-imagen4-fast Speed with good quality
Highly detailed/editorial hidream-i1-full Fine detail, editorial quality
Character with identity ideogram-v3-t2i Strong text + character rendering

Reference image prompt format: Write a clean, technical image prompt (not a Seedance prompt). Include:

  • Subject description + key product/brand visual elements
  • Lighting (studio, golden hour, etc.)
  • Shot framing (medium shot, product close-up, etc.)
  • Mood/color palette matching brand identity
  • NO motion language (this is for a still frame)

Execute image generation:

bash core/media/generate-image.sh \
  --model google-imagen4-ultra \
  --prompt "your image prompt" \
  --aspect-ratio 9:16 \
  --view

Step 5 — Generate the Video

Choose mode, tier, and camera based on content type and available assets.

Mode selection:

Situation Mode Command
No reference images t2v default
1 image (first frame) i2v --mode i2v --file ref.jpg
Start + end frames first-last --mode first-last --tier global --file start.jpg --file end.jpg
Multi-ref blend i2v up to 9 images

Invoke the script:

bash library/social/social-media-video/scripts/run-social-video.sh \
  --prompt "your director brief here" \
  --platform instagram \
  --camera drone \
  [--mode t2v|i2v|first-last] \
  [--file ref_image.jpg] \
  [--gen-ref "reference image prompt"] \
  [--tier global] \
  [--quality high] \
  [--view]

Platform Specs

Platform Format Aspect Duration Notes
Instagram Reels Vertical 9:16 10–15s Hook in first 1s
Instagram Feed Square 1:1 10s Static-feel works well
TikTok Vertical 9:16 10–15s High energy, fast cuts
YouTube Shorts Vertical 9:16 15s Max quality
LinkedIn Landscape 16:9 10–15s Professional tone
Twitter/X Landscape 16:9 10s Punchy, direct
YouTube (long) Landscape 16:9 15s Cinematic, slow builds
Pinterest Portrait 4:3 10s Lifestyle-forward

Tier note: Use --tier global or --tier vip for 1:1 and 21:9 formats. Chinese tier supports only 16:9, 9:16, 4:3, 3:4.


Camera Language Reference

Standard Camera Intents (--camera / --intent flags)
Intent Movement Best For
reveal Slow crane up, wide establishing Product launches, brand reveals
epic Dolly in + orbit, low hero angle Brand manifesto, emotional story
product Static macro orbit, precision reveal E-commerce, product demo
narrative Tracking shot, Steadicam Testimonials, story-driven
tense Handheld jitter, dutch angle High-energy, urgency
comedy Reactive handheld, punchy zooms Lighthearted brand content
Specialty Camera Intents (New)
Intent Description Best For
fpv First-person subjective POV — immersive GoPro-style, continuous forward motion, peripheral detail close-ups Action brands, travel, sports, tech demos
drone Aerial cinematic flythrough — smooth gimbal-stabilized, sweeping laterals, descend from high altitude into scene Real estate, luxury, outdoor brands, epic reveals
flythrough Ground-level architectural flythrough — continuous dolly through space, seamless portal transitions Architecture, interior design, venue showcases

FPV Prompt Enrichment:

Immersive first-person POV shot. Camera glides forward through [scene] at eye level.
Slight natural motion stabilization with GoPro-style wide angle.
Peripheral detail rushing past — [details]. Smooth continuous forward motion.
No cuts throughout. [Subject] visible in foreground periphery.

Drone Flythrough Prompt Enrichment:

Cinematic aerial drone shot. Camera descends from 200m altitude toward [subject/scene],
sweeping lateral arc as it descends. Gimbal-stabilized smooth motion.
Golden hour atmosphere, long shadows across [terrain/scene].
Final frame settles into medium establishing shot.
Aerial cinematography, DJI Inspire aesthetic.

Prompt Quality Checklist

Before finalizing the Seedance prompt, verify:

  • Scene environment is physically specific (not "nice background")
  • Camera movement named explicitly (dolly in, orbit, drone flythrough, FPV, etc.)
  • Lighting described technically (volumetric god rays, rim lighting, soft diffused, etc.)
  • Subject/product described with visual specifics from brand-identity.md
  • Sound direction included (even one line)
  • Timecodes used for 10s+ videos
  • @image1 etc. referenced if images are provided
  • Brand CTA or tagline included in final seconds
  • No vague adjectives ("amazing", "beautiful", "stunning") — replaced with technical terms

Example: Full Workflow

User: "Make an Instagram Reel for our cold brew coffee brand, drone shot, premium feel"

Step 1 — Brand read: Read brand-identity.md (minimalist packaging, dark roast, black + gold palette), ICP.md (urban professionals 25–40, values quality), messaging.md ("Precision Brewed. Zero Compromise.")

Step 2 — Storyboard:

0–2s:  Drone descends over rooftop terrace at sunrise, fog below.
2–5s:  Drone swoops down toward coffee cup on white marble, steam rising.
5–9s:  Close-up orbit of bottle, specular gold highlights, ice cubes.
9–11s: Product settles, black screen fades in: "Zero Compromise." + logo
Sound: Minimal lounge beat, coffee pour sound effect at 5s.

Step 3 — Seedance Director Prompt:

0–2s: Cinematic aerial drone shot. Camera descends at 30° angle toward a rooftop terrace at sunrise.
Golden hour atmosphere, San Francisco bay fog below horizon. Gimbal-stabilized smooth descent.
2–5s: Drone rapidly closes toward a glass of cold brew coffee on white marble.
Steam curling upward. Macro lens approach. Caustic light patterns on wet glass surface.
5–9s: Slow precision orbit around cold brew bottle. Black matte label with gold embossed text catching
specular highlights. Ice cubes with subsurface light scattering. Commercial macro aesthetic.
9–11s: Static product hero shot. Letterbox crop, deep focus, black fade in from sides.
Sound: Minimal ambient beat, single piano note, coffee liquid sound effect at 5s mark.
Maintain cinematic color grade — deep blacks, warm gold midtones throughout.

Step 4 — Generate reference: google-imagen4-ultra → cold brew bottle product shot (9:16)

Step 5 — Generate video:

bash library/social/social-media-video/scripts/run-social-video.sh \
  --prompt "0–2s: Cinematic aerial drone shot..." \
  --platform instagram \
  --camera drone \
  --mode i2v \
  --file media_outputs/coldbrew_ref.jpg \
  --duration 11 \
  --tier global \
  --view

Common Mistakes to Avoid

  1. Reading brand files and ignoring them — the storyboard must visually match the brand palette and tone.
  2. Generic prompts — "a nice video of a product" produces generic output. Every token must direct.
  3. Wrong tier for aspect ratio — 1:1 and 21:9 require --tier global or --tier vip.
  4. Forgetting sound — Seedance generates audio. Direct it, or you get random results.
  5. FPV with static subject — FPV requires continuous motion in the scene. Pair with movement-rich environments.
  6. Drone without establishing shot — drone works best when it resolves INTO something (a product, a scene, a subject).
  7. Too many scene changes in 5s — match complexity to duration. 5s = 1 beat. 15s = 3–4 beats.
1---
2slug: muapi-social-media-video
3name: muapi-social-media-video
4version: "1.0.0"
5description: Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.
6acceptLicenseTerms: true
7---
8 
9# Social Media Video Creator
10 
11**End-to-end pipeline: Brand Files → Storyboard → Reference Images → Seedance 2.0 Video.**
12 
13Reads your brand identity, ICP, and messaging documents to produce on-brand social video — fully optimized for Seedance 2.0's instructional prompt grammar and your target platform.
14 
15---
16 
17## Agent Execution Protocol
18 
19### Step 1 — Read Brand Files
20 
21Before writing anything, the agent MUST read all available brand files. Look for them in the working directory or any `brand/` subdirectory:
22 
23| File | What to extract |
24|:---|:---|
25| `brand-identity.md` | Visual style, color palette, tone, logo/product aesthetics, brand personality |
26| `ICP.md` | Target audience — who they are, their pain points, what motivates them |
27| `messaging.md` | Core value props, hooks, CTAs, campaign themes, taglines |
28 
29If a file is missing, proceed with what's available and note the gap.
30 
31---
32 
33### Step 2 — Write the Social Post + Storyboard
34 
35Use brand context to produce:
36 
37**Social Post Copy** (for caption/copy):
38- Hook line (first 1–2 sentences — must stop the scroll)
39- Body (3–5 sentences: problem → solution → proof → CTA)
40- Hashtags (5–8 relevant tags)
41- CTA (one clear action)
42 
43**Storyboard** (match duration to platform spec):
44```
450–3s: [Opening scene — hook/visual surprise — camera move]
463–7s: [Core message — product/subject in action — camera move]
477–10s: [Resolution — brand moment — CTA text on screen]
4810–15s: [Logo/tagline hold — background music fade]
49```
50 
51Tone must match brand personality. If brand is playful → upbeat transitions, bright grade.
52If brand is premium → slow reveals, dark luxury aesthetic, moody lighting.
53 
54---
55 
56### Step 3 — Craft the Seedance 2.0 Director Prompt
57 
58Transform the storyboard into a **technical Director Brief** for Seedance 2.0.
59 
60**Rules:**
611. Never use vague descriptors ("beautiful", "amazing", "8k"). Use technical cinematography language.
622. Always specify camera movement, lens type, and lighting physically.
633. For 10s+ videos, use timecode segments: `0–3s: [...] 3–7s: [...] 7–10s: [...]`
644. Integrate `@image1`, `@image2` reference tags if images are provided.
655. Always include sound direction (even brief) — Seedance generates audio.
666. Lead with composition, end with texture and micro-motion.
67 
68**Director Brief Template:**
69```
70[SCENE] {environment, lighting, time of day}
71[SUBJECT] {product/character/subject with specific detail}
72[ACTION] {what happens — fluid, continuous, physically plausible}
73[CAMERA] {movement + lens + framing}
74[STYLE] {color grade, mood, film reference if helpful}
75[SOUND] {music tone, sound effects, ambient}
760–Xs: {if multi-beat}
77```
78 
79---
80 
81### Step 4 — Generate Reference Images (If Needed)
82 
83**When to generate reference images:**
84 
85| Scenario | Mode | Images Needed |
86|:---|:---|:---|
87| Product showcase | `i2v` | 1 product shot as first frame |
88| Scene transition | `first-last` | 2 images — opening and closing frame |
89| Brand character | `i2v` | 1 character reference |
90| Pure concept | `t2v` | None — text only |
91| Mood/style anchor | `i2v` | 1 style reference image |
92 
93**Image generation — best models by use case:**
94 
95| Use Case | Recommended Model | Why |
96|:---|:---|:---|
97| Photorealistic product/scene | `google-imagen4-ultra` | Highest realism, great lighting |
98| Concept art / stylized | `flux-kontext-pro-t2i` | Creative fidelity, style adherence |
99| Fastest turnaround | `google-imagen4-fast` | Speed with good quality |
100| Highly detailed/editorial | `hidream-i1-full` | Fine detail, editorial quality |
101| Character with identity | `ideogram-v3-t2i` | Strong text + character rendering |
102 
103**Reference image prompt format:**
104Write a clean, technical image prompt (not a Seedance prompt). Include:
105- Subject description + key product/brand visual elements
106- Lighting (studio, golden hour, etc.)
107- Shot framing (medium shot, product close-up, etc.)
108- Mood/color palette matching brand identity
109- NO motion language (this is for a still frame)
110 
111Execute image generation:
112```bash
113bash core/media/generate-image.sh \
114 --model google-imagen4-ultra \
115 --prompt "your image prompt" \
116 --aspect-ratio 9:16 \
117 --view
118```
119 
120---
121 
122### Step 5 — Generate the Video
123 
124Choose mode, tier, and camera based on content type and available assets.
125 
126**Mode selection:**
127 
128| Situation | Mode | Command |
129|:---|:---|:---|
130| No reference images | `t2v` | default |
131| 1 image (first frame) | `i2v` | `--mode i2v --file ref.jpg` |
132| Start + end frames | `first-last` | `--mode first-last --tier global --file start.jpg --file end.jpg` |
133| Multi-ref blend | `i2v` | up to 9 images |
134 
135**Invoke the script:**
136```bash
137bash library/social/social-media-video/scripts/run-social-video.sh \
138 --prompt "your director brief here" \
139 --platform instagram \
140 --camera drone \
141 [--mode t2v|i2v|first-last] \
142 [--file ref_image.jpg] \
143 [--gen-ref "reference image prompt"] \
144 [--tier global] \
145 [--quality high] \
146 [--view]
147```
148 
149---
150 
151## Platform Specs
152 
153| Platform | Format | Aspect | Duration | Notes |
154|:---|:---|:---|:---|:---|
155| Instagram Reels | Vertical | 9:16 | 10–15s | Hook in first 1s |
156| Instagram Feed | Square | 1:1 | 10s | Static-feel works well |
157| TikTok | Vertical | 9:16 | 10–15s | High energy, fast cuts |
158| YouTube Shorts | Vertical | 9:16 | 15s | Max quality |
159| LinkedIn | Landscape | 16:9 | 10–15s | Professional tone |
160| Twitter/X | Landscape | 16:9 | 10s | Punchy, direct |
161| YouTube (long) | Landscape | 16:9 | 15s | Cinematic, slow builds |
162| Pinterest | Portrait | 4:3 | 10s | Lifestyle-forward |
163 
164> **Tier note:** Use `--tier global` or `--tier vip` for `1:1` and `21:9` formats. Chinese tier supports only 16:9, 9:16, 4:3, 3:4.
165 
166---
167 
168## Camera Language Reference
169 
170### Standard Camera Intents (--camera / --intent flags)
171 
172| Intent | Movement | Best For |
173|:---|:---|:---|
174| `reveal` | Slow crane up, wide establishing | Product launches, brand reveals |
175| `epic` | Dolly in + orbit, low hero angle | Brand manifesto, emotional story |
176| `product` | Static macro orbit, precision reveal | E-commerce, product demo |
177| `narrative` | Tracking shot, Steadicam | Testimonials, story-driven |
178| `tense` | Handheld jitter, dutch angle | High-energy, urgency |
179| `comedy` | Reactive handheld, punchy zooms | Lighthearted brand content |
180 
181### Specialty Camera Intents (New)
182 
183| Intent | Description | Best For |
184|:---|:---|:---|
185| `fpv` | First-person subjective POV — immersive GoPro-style, continuous forward motion, peripheral detail close-ups | Action brands, travel, sports, tech demos |
186| `drone` | Aerial cinematic flythrough — smooth gimbal-stabilized, sweeping laterals, descend from high altitude into scene | Real estate, luxury, outdoor brands, epic reveals |
187| `flythrough` | Ground-level architectural flythrough — continuous dolly through space, seamless portal transitions | Architecture, interior design, venue showcases |
188 
189**FPV Prompt Enrichment:**
190```
191Immersive first-person POV shot. Camera glides forward through [scene] at eye level.
192Slight natural motion stabilization with GoPro-style wide angle.
193Peripheral detail rushing past — [details]. Smooth continuous forward motion.
194No cuts throughout. [Subject] visible in foreground periphery.
195```
196 
197**Drone Flythrough Prompt Enrichment:**
198```
199Cinematic aerial drone shot. Camera descends from 200m altitude toward [subject/scene],
200sweeping lateral arc as it descends. Gimbal-stabilized smooth motion.
201Golden hour atmosphere, long shadows across [terrain/scene].
202Final frame settles into medium establishing shot.
203Aerial cinematography, DJI Inspire aesthetic.
204```
205 
206---
207 
208## Prompt Quality Checklist
209 
210Before finalizing the Seedance prompt, verify:
211 
212- [ ] Scene environment is physically specific (not "nice background")
213- [ ] Camera movement named explicitly (dolly in, orbit, drone flythrough, FPV, etc.)
214- [ ] Lighting described technically (volumetric god rays, rim lighting, soft diffused, etc.)
215- [ ] Subject/product described with visual specifics from brand-identity.md
216- [ ] Sound direction included (even one line)
217- [ ] Timecodes used for 10s+ videos
218- [ ] `@image1` etc. referenced if images are provided
219- [ ] Brand CTA or tagline included in final seconds
220- [ ] No vague adjectives ("amazing", "beautiful", "stunning") — replaced with technical terms
221 
222---
223 
224## Example: Full Workflow
225 
226**User**: "Make an Instagram Reel for our cold brew coffee brand, drone shot, premium feel"
227 
228**Step 1 — Brand read**: Read `brand-identity.md` (minimalist packaging, dark roast, black + gold palette), `ICP.md` (urban professionals 25–40, values quality), `messaging.md` ("Precision Brewed. Zero Compromise.")
229 
230**Step 2 — Storyboard**:
231```
2320–2s: Drone descends over rooftop terrace at sunrise, fog below.
2332–5s: Drone swoops down toward coffee cup on white marble, steam rising.
2345–9s: Close-up orbit of bottle, specular gold highlights, ice cubes.
2359–11s: Product settles, black screen fades in: "Zero Compromise." + logo
236Sound: Minimal lounge beat, coffee pour sound effect at 5s.
237```
238 
239**Step 3 — Seedance Director Prompt**:
240```
2410–2s: Cinematic aerial drone shot. Camera descends at 30° angle toward a rooftop terrace at sunrise.
242Golden hour atmosphere, San Francisco bay fog below horizon. Gimbal-stabilized smooth descent.
2432–5s: Drone rapidly closes toward a glass of cold brew coffee on white marble.
244Steam curling upward. Macro lens approach. Caustic light patterns on wet glass surface.
2455–9s: Slow precision orbit around cold brew bottle. Black matte label with gold embossed text catching
246specular highlights. Ice cubes with subsurface light scattering. Commercial macro aesthetic.
2479–11s: Static product hero shot. Letterbox crop, deep focus, black fade in from sides.
248Sound: Minimal ambient beat, single piano note, coffee liquid sound effect at 5s mark.
249Maintain cinematic color grade — deep blacks, warm gold midtones throughout.
250```
251 
252**Step 4 — Generate reference**: `google-imagen4-ultra` → cold brew bottle product shot (9:16)
253 
254**Step 5 — Generate video**:
255```bash
256bash library/social/social-media-video/scripts/run-social-video.sh \
257 --prompt "0–2s: Cinematic aerial drone shot..." \
258 --platform instagram \
259 --camera drone \
260 --mode i2v \
261 --file media_outputs/coldbrew_ref.jpg \
262 --duration 11 \
263 --tier global \
264 --view
265```
266 
267---
268 
269## Common Mistakes to Avoid
270 
2711. **Reading brand files and ignoring them** — the storyboard must visually match the brand palette and tone.
2722. **Generic prompts** — "a nice video of a product" produces generic output. Every token must direct.
2733. **Wrong tier for aspect ratio** — 1:1 and 21:9 require `--tier global` or `--tier vip`.
2744. **Forgetting sound** — Seedance generates audio. Direct it, or you get random results.
2755. **FPV with static subject** — FPV requires continuous motion in the scene. Pair with movement-rich environments.
2766. **Drone without establishing shot** — drone works best when it resolves INTO something (a product, a scene, a subject).
2777. **Too many scene changes in 5s** — match complexity to duration. 5s = 1 beat. 15s = 3–4 beats.
View all files on GitHub →

Details

Version
1.0.0
Updated
Sep 8, 2026
License
MIT
Stars on the repo
★ 4,317
Checked
Source
SamurAIGPT/Generative-Media-Skills ↗
Creator
SamurAIGPT · 16 listings
View creator

Similar skills

See all →
SkillScroll Experience Builderdavila7/claude-code-templates · by davila7Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences. Makes websites feel like experiences, not just pages. Use when: scroll animation, parallax, scroll storytelling, interactive story, cinematic website.★ 32.3k GitHub starsSkillProduct Photography VariantsAgriciDaniel/claude-ads · by AgriciDanielGenerate rights-cleared paid-ad product photography variants from an authorized source image and validated brand profile. Triggers on: product photo, product photography, virtual photoshoot, photoshoot, enhance product image, studio shot, lifestyle shot, lifestyle product image, floating product image, ingredient shot.★ 9.5k GitHub starsSkillCinematic Video DirectorSamurAIGPT/Generative-Media-Skills · by SamurAIGPTDirect high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai★ 4.3k GitHub starsSkillProduct Video MakerSamurAIGPT/Generative-Media-Skills · by SamurAIGPTCreate a high-end cinematic product video advertisement starting from a simple product photo.★ 4.3k GitHub starsSkillLinkedIn Pinned Comment Writercharlie947/social-media-skills · by charlie947Write deadpan LinkedIn pinned comments AND matching image generation prompts in the user’s voice. Use when the user asks for a pinned comment, pin comment, or first comment for a LinkedIn post. ALWAYS produce the image prompt FIRST, then caption it with the 4-line comment. Output both together unless told otherwise.★ 3.7k GitHub starsSkillImmersive Web Designerwondelai/skills · by wondelaiCreate award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard landing page into a memorable digital experience. Covers dramatic typography, purposeful motion, scroll-based composition, and performance-optimized animation. For foundational UI, see refactoring-ui. For type selection, see web-typography.★ 2.2k GitHub stars

More from SamurAIGPT

SkillHigh-Converting Ad CreativeSamurAIGPT/Generative-Media-Skills · by SamurAIGPTGenerate a high-converting ad creative set — hero image, ad copy variations, and platform-optimized crops for Meta, Google Display, and LinkedIn.★ 4.3k GitHub starsSkillAI Video Clipping ToolSamurAIGPT/Generative-Media-Skills · by SamurAIGPTTurn a long video into N viral-ready short clips with a single managed API call. Wraps muapi.ai's `/ai-clipping` endpoint, which handles transcription, highlight ranking through a virality framework (hook / emotional peak / opinion bomb / revelation / conflict / quotable / story peak / practical value), overlap dedupe, and vertical face-tracking auto-crop server-side. No local Whisper, no local LLM, no GPU.★ 4.3k GitHub starsSkillAI Fight Scene GeneratorSamurAIGPT/Generative-Media-Skills · by SamurAIGPTGenerate a high-cut-density action / fight scene by first composing a 16-cell storyboard image, then driving Seedance 2.0 image-to-video off that storyboard. Stacks GPT-Image-2 (character sheet + storyboard), Nano-Banana-2 (environment concept), and Seedance 2.0 i2v.★ 4.3k GitHub starsSkillChibi Collage CreatorSamurAIGPT/Generative-Media-Skills · by SamurAIGPTTurn a real lifestyle photo into a polished "chibi clone sticker diary" image — the original person stays photorealistic, surrounded by 5–8 kawaii chibi mini-clones, scrapbook doodles, and handwritten-style captions that match the scene.★ 4.3k GitHub starsSkillCinematic Video DirectorSamurAIGPT/Generative-Media-Skills · by SamurAIGPTDirect high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai★ 4.3k GitHub starsSkillInstagram Post CreatorSamurAIGPT/Generative-Media-Skills · by SamurAIGPTCreate a polished, on-brand Instagram post — square or portrait hero image with matching caption and hashtags.★ 4.3k GitHub stars