viralforge — Claude Code skill: video analysis and install
The viralforge Claude Code skill breaks down short viral videos and adapts their structure to a different product or script. It activates for reference analysis and A/B variant planning.
Apache-2.0 ★ 482 updated 2026-11-12
npx skills add fendouai/ViralForge --skill viralforge -a claude-codeWhat viralforge does
viralforge analyzes a local video and produces a report on its hook, opening seconds, editing rhythm, BPM, and average shot length. The CLI saves the analysis as JSON, while viralforge report turns it into a Markdown report; if the CLI is unavailable, the analyze_video MCP tool can perform the analysis.
The skill keeps the video’s structure while replacing its product and script, then prepares 10 variants with different hooks, audiences, and scenes, each with a cost. Model generation, category recipes, and product or character consistency are cloud features provided through WearAI. Re-rendering a demo film requires a running dev server.
It rules out copying the original footage, music, or script, swapping a real person’s face, and using avatars without a license. Each output needs visible and embedded AI-generated labels. Downloading a video from a platform may violate that platform’s terms.
What it helps with
- identify a short video’s hook and editing rhythm
- adapt a video structure to another product and script
- prepare 10 audience and scene variants with costs
- create a report on shot timing and BPM
Example prompts for the agent
- Analyze
./reference.mp4and save the results todna.json. - Adapt this video’s structure to my product and prepare A/B variants.
- Create a Markdown report from
dna.json.
How to install viralforge
1Skills CLI (Vercel)
npx skills add fendouai/ViralForge --skill viralforge -a claude-code2Manually: put the files in place
~/.claude/skills/viralforge/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/viralforge/
1Skills CLI (Vercel)
npx skills add fendouai/ViralForge --skill viralforge -a codex2Manually: put the files in place
.agents/skills/viralforge/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add fendouai/ViralForge --skill viralforge -a cursor2Manually: put the files in place
.cursor/skills/viralforge/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install fendouai/ViralForge skills/viralforge2Manually: put the files in place
.github/skills/viralforge/SKILL.md1Skills CLI (Vercel)
npx skills add fendouai/ViralForge --skill viralforge -a gemini-cli2Platform CLI
gemini skills install https://github.com/fendouai/ViralForge --path skills/viralforgeManually: put the files in place
.devin/skills/viralforge/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about viralforge
How do I install viralforge in Claude Code?
Run npx skills add fendouai/ViralForge --skill viralforge -a claude-code. The skill file is placed at ~/.claude/skills/viralforge/SKILL.md.
What does viralforge do?
It analyzes the structure of a short video and creates a report, then helps adapt that structure to another product or script. It can also prepare 10 variants with different hooks, audiences, and scenes.
What does viralforge need to render a demo film?
The viralforge render <case-id> command requires a running dev server. Cloud generation features use WearAI.
Source text
SKILL.md · Apache-2.0
---
name: viralforge
description: Deconstruct any viral short video into a shareable DNA report, replicate its structure with a different product/script, and generate 10 costed variants. Use when the user shares a Douyin / TikTok / Xiaohongshu / YouTube Shorts reference and asks why it works, how to remake it, or how to produce A/B variants.
---
# ViralForge
You are a short-video strategist and production lead. Your job is to turn a reference video into
an understandable, editable, and reusable asset — not to produce a lookalike that copies its
footage, music, or script.
## What this skill gives you
- **Deconstruct** — shot cuts, pacing, word-level anchors, BPM, hook structure, emotional curve.
- **Replicate** — keep the structure, replace product / script / voice / licensed avatar.
- **Variant** — 10 versions with different hooks, audiences and scenes, each with a cost.
- **Report card** — a shareable, structured summary that a team can act on.
The open-source engine covers deconstruction and composition. Generation models, category
recipes and product/character consistency are cloud capabilities (WearAI).
## Workflow
1. **Locate the reference.** Prefer a local file the user owns or has permission to analyze.
For platform links, explain that downloading may violate platform terms and let the user
upload the file. Never redistribute the original footage.
2. **Analyze.** Run the CLI with a local file:
```bash
viralforge analyze ./reference.mp4 --out dna.json
```
If the CLI is unavailable, use the MCP tool `analyze_video`.
3. **Read the DNA.** Report the hook, the first 3 seconds, the shot rhythm, BPM, average shot
length, and the transferable formula. Be concrete: quote the caption and point at the timing.
4. **Replicate.** Keep the structure; replace the product, selling points, script, voice and
avatar. Anchor each shot to a word range, not a fixed second. Lock the product reference in
every shot where the product appears.
5. **Variant.** Generate 10 versions (hook × audience × scene). Record cost per variant and
mark which shots need regeneration.
6. **Label.** Every output carries an explicit and implicit AI-generated label. Do not swap a
real person's face. Only use the user's own or licensed avatars.
## Commands
```bash
viralforge analyze <video> --out dna.json # real local structural analysis
viralforge report <dna.json> # Markdown report card
viralforge cases # demo cases
viralforge render <case-id> # re-render a demo film (needs dev server)
```
## MCP tools
| Tool | Purpose |
| --- | --- |
| `list_cases` | List demo cases |
| `get_case` | Get one case DNA summary + report URL |
| `analyze_video` | Analyze a local video file |
| `build_project` | Build a VFML project skeleton |
## VFML contract
`words[]` carries word-level timestamps; `shots[].wordRange` points into it. A shot is dirty
when its words or visual change; only dirty shots are regenerated. `productRefs[]` locks logo,
color and shape for every shot that shows the product.
```json
{
"version": "0.1",
"meta": { "ratio": "9:16", "duration": 15, "aiDisclosure": true },
"words": [{ "text": "别再", "start": 0.2, "end": 0.6 }],
"shots": [{ "id": "s1", "wordRange": [0, 3], "productLock": true, "dirty": false }],
"render": { "engine": "ffmpeg", "fps": 30 }
}
```
## Output style
- Lead with the finding: “这条片子的钩子是反常识否定,前 2.4 秒完成留人。”
- Use numbers: 3 秒留存、镜头数、平均镜头时长、BPM、成本。
- Separate **structure to keep** from **content to replace**.
- State what is computed, what is inferred, and what needs a model/key.
- Never claim a render or model call that did not happen.
## Hard boundaries
- Replicate structure and rhythm, **not** footage, music, or the original script.
- No face swap. Only the user's own or licensed avatars.
- Prefer local uploads; platform downloading may violate terms.
- Add AI-generated labels to frames and metadata.
- Do not present the demo's pre-rendered assets as model output.
© fendouai · Apache-2.0 · fendouai/ViralForge