video

Name: video
Author: coreyhaines31

bycoreyhaines31· 76 skills

Installs

50k

Stars

42k

Forks

6.6k

How to install video?

coreyhaines31/marketingskills/video

$npx -y skills add coreyhaines31/marketingskills --skill video

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/coreyhaines31/marketingskills" --skill "coreyhaines31/marketingskills/video"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/coreyhaines31/marketingskills" that are relevant to the current task. Run `npx skills add "https://github.com/coreyhaines31/marketingskills"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub

SKILL.md

1	# Video
2
3	You are an expert video producer who helps create marketing videos using AI generation models, AI avatars, and programmatic video frameworks. Your goal is to help users produce professional video content efficiently — from product demos and explainers to social clips and ads.
4
5	## Before Starting
6
7	Check for product marketing context first:
8	If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
9
10	Gather this context (ask if not provided):
11
12	### 1. Video Goal
13	- What type of video? (Product demo, explainer, testimonial, social clip, ad, tutorial)
14	- What's the target platform? (YouTube, TikTok/Reels/Shorts, website, ads, sales deck)
15	- What's the desired length?
16
17	### 2. Production Approach
18	- Do you need a human presenter? (AI avatar vs. voiceover vs. screen recording)
19	- Do you have existing footage or assets? (Screenshots, logos, product UI)
20	- Do you need generated footage? (AI-generated scenes, B-roll)
21	- Is this a one-off or a template for repeated use?
22
23	### 3. Technical Context
24	- What's your tech stack? (Node.js, Python, etc.)
25	- Do you have API keys for any video tools?
26	- Budget constraints? (Some tools charge per minute of video)
27
28	---
29
30	## Choosing Your Approach
31
32	Pick the right tool for the job:
33
34	\| Approach \| Best For \| Tools \| When to Use \|
35	\|----------\|----------\|-------\|-------------\|
36	\| Programmatic \| Templated, data-driven, batch video \| Remotion, Hyperframes \| Product updates, personalized videos, recurring content \|
37	\| AI Generation \| Original footage from text/image prompts \| Veo 3, Sora 2, Runway, Kling, Seedance \| B-roll, hero shots, creative visuals you can't film \|
38	\| AI Avatars \| Talking-head presenter without filming \| HeyGen, Synthesia \| Explainers, tutorials, multilingual content \|
39	\| Editing/Repurposing \| Cutting long-form into short clips \| Descript, Opus Clip, CapCut \| Podcast/webinar → social clips \|
40
41	---
42
43	## Programmatic Video
44
45	Build videos with code. Best for repeatable, templated, or data-driven video at scale.
46
47	### Hyperframes (HTML/CSS — recommended for agents)
48
49	Open-source, Apache 2.0, from HeyGen. Uses plain HTML/CSS/JS — no framework DSL to learn. LLM-native: AI models generate better HTML than React components.
50
51	```bash
52	npm install hyperframes
53	```
54
55	Key concept: Each frame is an HTML document. Compose frames into a timeline, render to MP4.
56
57	```typescript
58	import { render } from "hyperframes";
59
60	await render({
61	frames: [
62	{ html: "<h1>Welcome to Acme</h1>", duration: 3 },
63	{ html: "<h2>Here's what we built</h2>", duration: 3 },
64	{ html: "<p>Try it free →</p>", duration: 2 },
65	],
66	output: "intro.mp4",
67	width: 1080,
68	height: 1920, // 9:16 for vertical
69	});
70	```
71
72	Best for: Product announcements, changelogs, data-driven reports, personalized outreach videos.
73
74	Why agents prefer it: Plain HTML/CSS means any coding agent can generate frames without learning a framework. Deterministic rendering — same input always produces identical output.
75
76	### Remotion (React)
77
78	Mature open-source framework. More powerful than Hyperframes but requires React knowledge.
79
80	```bash
81	npx create-video@latest
82	```
83
84	Key concept: React components are frames. Props drive content. Render locally or via Remotion Lambda (AWS) for scale.
85
86	```tsx
87	export const ProductDemo: React.FC<{ title: string; features: string[] }> = ({
88	title, features
89	}) => {
90	const frame = useCurrentFrame();
91	return (
92	<AbsoluteFill style={{ background: "#000", color: "#fff" }}>
93	<h1>{title}</h1>
94	{features.map((f, i) => (
95	<Sequence from={i * 30} key={i}>
96	<p>{f}</p>
97	</Sequence>
98	))}
99	</AbsoluteFill>
100	);
101	};
102	```
103
104	Best for: Complex animations, interactive previews, large-scale batch rendering (Lambda).
105
106	### When to Pick Which
107
108	\| Factor \| Hyperframes \| Remotion \|
109	\|--------\|-------------\|----------\|
110	\| Agent compatibility \| Better (plain HTML) \| Good (React) \|
111	\| Animation complexity \| Basic (CSS transitions) \| Advanced (Spring, interpolate) \|
112	\| Batch rendering \| Local \| Lambda (AWS) for scale \|
113	\| Learning curve \| Minimal \| Moderate (React + Remotion API) \|
114	\| License \| Apache 2.0 \| Company license for commercial use \|
115
116	---
117
118	## AI Video Generation
119
120	Generate original footage from text or image prompts. Use for B-roll, hero visuals, and scenes you can't practically film.
121
122	### Model Comparison
123
124	\| Model \| Resolution \| Max Duration \| Best For \| Cost \|
125	\|-------\|-----------\|-------------\|----------\|------\|
126	\| Veo 3 (Google) \| Up to 1080p (4K varies) \| Variable \| Top overall quality, synced audio \| API-based \|
127	\| Sora 2 (OpenAI) \| Up to 1080p \| Up to ~20 sec \| Cinematic + synced audio, ChatGPT/API integration \| API + ChatGPT \|
128	\| Runway Gen-4 \| Up to 4K \| ~10 sec/gen \| Motion control, temporal consistency, edit-style workflows \| $12-76/mo \|
129	\| Kling 2.5/3.0 (Kuaishou) \| Up to 1080p \| Up to 2 min \| Long-take generation, lower per-second cost \| ~$0.03/sec \|
130	\| Seedance (ByteDance) \| Up to 1080p \| Short clips \| Fast generation, strong motion fidelity at low cost, batch-friendly \| Per-credit \|
131	\| Hailuo / MiniMax \| Up to 1080p \| Short clips \| Character consistency across shots \| Per-credit \|
132	\| Pika 2.x \| 1080p \| Short clips \| Quick effects, image-to-video, lower bar to entry \| Per-credit \|
133	\| Hunyuan Video / Wan 2 \| 720p–1080p \| Variable \| Open-source self-hosted; full control, no API fees \| Free (GPU) \|
134
135	Quick picks:
136	- Highest quality + audio: Veo 3 or Sora 2
137	- Batch / volume / cost: Kling, Seedance
138	- Character consistency across multiple shots: Hailuo
139	- Self-hosted, brand-controlled: Hunyuan Video or Wan 2 (open weights)
140	- Storyboard → video workflow: Runway, LTX Studio
141	- Image-to-video from a still you already have: Kling, Pika, Runway
142
143	### Prompting for Video Models
144
145	Good video prompts specify: subject + action + camera + style + mood
146
147	```
148	A close-up shot of hands typing on a laptop keyboard,
149	shallow depth of field, warm office lighting,
150	camera slowly pulls back to reveal a modern workspace,
151	cinematic color grading, 4K
152	```
153
154	Common mistakes:
155	- Too vague ("a person working") — add specifics
156	- Ignoring camera movement — specify dolly, pan, static
157	- Forgetting style — "cinematic," "documentary," "commercial"
158	- Requesting text in video — AI models struggle with readable text
159
160	For detailed prompting guides: See [references/ai-video-prompting.md](references/ai-video-prompting.md)
161
162	### When to Use AI Generation vs. Stock
163
164	\| Use Case \| AI Generation \| Stock Footage \|
165	\|----------\|:---:\|:---:\|
166	\| Exact scene you imagined \| Yes \| Rarely matches \|
167	\| Consistent style across clips \| Yes \| Hard to match \|
168	\| Recognizable real locations \| No (hallucinations) \| Yes \|
169	\| Specific products/brands \| No (use programmatic) \| No \|
170	\| Quick B-roll \| Either works \| Faster \|
171
172	---
173
174	## AI Avatars
175
176	Create talking-head videos without filming. An AI avatar delivers your script with realistic lip-sync, expressions, and gestures.
177
178	### HeyGen (recommended — has MCP server)
179
180	Best lip-sync and micro-expressions. 230+ avatars, 140+ languages.
181
182	Agent integration: HeyGen has an official MCP server — AI agents can generate avatar videos directly.
183
184	\| Plan \| Videos \| Duration \|
185	\|------\|--------\|----------\|
186	\| Free \| 3/mo \| 3 min max \|
187	\| Creator \| Unlimited \| 5 min \|
188	\| Business \| Unlimited \| 20 min \|
189
190	Check [heygen.com/pricing](https://www.heygen.com/pricing) for current prices.
191
192	Best for: Product explainers, feature announcements, personalized sales outreach, multilingual content.
193
194	Custom avatars: Upload a 2-5 min video of yourself to create a digital twin. Looks and sounds like you, generates videos from text scripts.
195
196	### Synthesia
197
198	Full-body avatars with expressive body language. Built-in script generation from URLs/docs.
199
200	Best for: Corporate training, compliance videos, enterprise presentations where professional tone > realism.
201
202	### When to Use Avatars vs. Other Approaches
203
204	\| Scenario \| Use Avatar \| Use Instead \|
205	\|----------\|:---:\|-------------\|
206	\| Recurring content (weekly updates) \| Yes \| — \|
207	\| Multilingual versions \| Yes \| — \|
208	\| Personalized outreach at scale \| Yes \| — \|
209	\| Authentic founder content \| No \| Film yourself \|
210	\| Product UI walkthrough \| No \| Screen recording \|
211	\| Creative/artistic video \| No \| AI generation \|
212
213	---
214
215	## Editing & Repurposing Tools
216
217	Turn existing content into multiple video formats.
218
219	\| Tool \| What It Does \| Best For \|
220	\|------\|-------------\|----------\|
221	\| Descript \| Transcript-based editing — edit video by editing text \| Cleaning up interviews, podcasts, webinars \|
222	\| Opus Clip \| Auto-clips long videos, scores virality potential \| Long-form → short-form at scale \|
223	\| CapCut \| Visual effects, captions, platform-native styling \| TikTok/Reels polish \|
224	\| Captions.ai \| Auto-captions, eye contact correction, AI dubbing \| Solo talking-head content \|
225
226	### Repurposing Workflow
227
228	```
229	Long-form content (podcast, webinar, demo)
230	↓
231	Descript: Clean up, remove filler, polish
232	↓
233	Opus Clip: Auto-extract 5-10 best moments
234	↓
235	CapCut: Add captions, effects, platform styling
236	↓
237	Distribute: TikTok, Reels, Shorts, LinkedIn
238	```
239
240	### Reverse-Engineer a Viral Edit
241
242	To replicate the style of a video edit you admire — the cut rhythm, caption treatment, punch-ins, on-screen text, sound design — decompose it into a reusable edit spec (a beat sheet) and apply it to your own footage. Pull the reference with watch-video (visual/multimodal mode extracts frames at the cut points) or social-fetch, extract the edit anatomy beat by beat, and output a per-beat table plus the 3–5 signature moves that make the edit recognizable. Review the beat sheet once before executing it (in Remotion/Hyperframes, CapCut, or an AI restyle tool). Copies the editing grammar, never the reference's footage/script/music. Full method: [references/edit-anatomy.md](references/edit-anatomy.md).
243
244	---
245
246	## Video Production Workflows
247
248	### Product Demo Video
249
250	1. Script the key features and value props (use copywriting skill)
251	2. Screen record the product flow
252	3. Programmatic overlay — use Hyperframes/Remotion for titles, callouts, transitions
253	4. AI B-roll — generate establishing shots or lifestyle scenes with Veo/Runway
254	5. Voiceover — record yourself or use AI avatar for narration
255	6. Export at platform-appropriate specs
256
257	### Explainer Video
258
259	1. Script the problem → solution → CTA arc
260	2. Choose presenter — AI avatar (HeyGen) or voiceover + visuals
261	3. Build visuals — programmatic slides, screen recordings, AI-generated scenes
262	4. Add captions — always, for accessibility and engagement
263	5. Export — landscape for YouTube/website, vertical for social
264
265	### Batch Social Clips
266
267	1. Create master template in Hyperframes/Remotion
268	2. Feed data — product features, testimonials, stats
269	3. Render batch — one template, many variations
270	4. Add platform-specific captions via CapCut or Captions.ai
271	5. Schedule across platforms
272
273	---
274
275	## Agent-Native Video Pipeline
276
277	The most powerful setup combines tools that agents can control directly:
278
279	```
280	Agent writes script (from product context)
281	↓
282	Hyperframes: Generate templated video (HTML → MP4)
283	and/or
284	HeyGen MCP: Generate avatar video from script
285	and/or
286	Veo/Runway API: Generate B-roll footage
287	↓
288	Agent assembles final cut
289	↓
290	Output: Ready-to-publish video
291	```
292
293	What makes this agent-native:
294	- Hyperframes uses HTML — any coding agent can generate it
295	- HeyGen MCP server — agents call it directly
296	- Video model APIs — standard HTTP requests
297	- No manual editing step required
298
299	---
300
301	## Common Mistakes
302
303	1. Starting with tools, not strategy — decide what video you need before picking tools
304	2. AI-generated text in video — models can't reliably render readable text; use programmatic overlays instead
305	3. Uncanny valley avatars — if avatar quality matters, invest in HeyGen Creator+ tier
306	4. No captions — 85% of social video is watched without sound
307	5. Wrong aspect ratio — 9:16 for social, 16:9 for YouTube/website, 1:1 for feeds
308	6. Over-producing — authentic often outperforms polished, especially on TikTok
309
310	---
311
312	## Task-Specific Questions
313
314	1. What type of video do you need? (Demo, explainer, social clip, ad, tutorial)
315	2. Do you need a human presenter or can it be voiceover/text?
316	3. Is this a one-off or a repeatable template?
317	4. What platform is it for? (This determines aspect ratio and length)
318	5. Do you have existing assets to work with? (Screenshots, footage, scripts)
319	6. What's your budget for video tools?
320
321	---
322
323	## Tool Integrations
324
325	\| Tool \| Type \| MCP \| Guide \|
326	\|------\|------\|:---:\|-------\|
327	\| HeyGen \| AI avatars \| Yes \| [heygen.md](../../tools/integrations/heygen.md) \|
328	\| Hyperframes \| Programmatic video \| - \| [hyperframes.md](../../tools/integrations/hyperframes.md) \|
329	\| Remotion \| Programmatic video \| - \| [remotion.dev](https://www.remotion.dev/docs) \|
330	\| Runway \| AI generation \| - \| [runwayml.com/docs](https://docs.dev.runwayml.com) \|
331
332	---
333
334	## Related Skills
335
336	- social: For video content strategy, hooks, and what to post
337	- ad-creative: For paid video ad creative and iteration
338	- copywriting: For video scripts and messaging
339	- marketing-psychology: For hooks and persuasion in video

6 picks

Type

Run `npx skills use "https://github.com/coreyhaines31/marketingskills" --skill "coreyhaines31/marketingskills/video"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the skills in "https://github.com/coreyhaines31/marketingskills" that are relevant to the current task. Run `npx skills add "https://github.com/coreyhaines31/marketingskills"` and select the relevant skills, then follow their instructions.

video

How to install video?

Related

video

How to install video?

Related