# viral-reverse-engineering

Deconstructs viral posts and videos to isolate the core sharing mechanism and adapt it to your niche without copying surface noise.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 841 installs · ★ 199
- Author: social-media-skills
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/social-media-skills/skills/tree/HEAD/skills/viral-reverse-engineering/SKILL.md
- Updated: 2026-10-15
- HTML: https://affpapa.org/en/nevibecode/skills/viral-reverse-engineering

## What it does

The skill breaks down content layer by layer: hook, retention, formatting, and the underlying share trigger. It tests each feature by asking whether the post survives without it. Incidental traits like trending audio get discarded, while the actual structural lever gets isolated. Output adapts the mechanism directly to your topic using `brand-profile.md` and `audience.md`.

A bare video URL will not work on its own. Agents cannot watch videos behind platform walls, so you must provide observable signals like transcripts, key frames, top comments, or metrics. When virality stems purely from account size or luck, the skill flags it as non-replicable instead of creating a false formula.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill viral-reverse-engineering -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/viral-reverse-engineering/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/viral-reverse-engineering/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill viral-reverse-engineering -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/viral-reverse-engineering/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill viral-reverse-engineering -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/viral-reverse-engineering/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install social-media-skills/skills viral-reverse-engineering
```

2. **Manually: put the files in place**
- File: `.github/skills/viral-reverse-engineering/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill viral-reverse-engineering -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/social-media-skills/skills --path skills/viral-reverse-engineering
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/viral-reverse-engineering/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add social-media-skills/skills --skill viral-reverse-engineering -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/social-media-skills/skills/tree/HEAD/skills/viral-reverse-engineering/SKILL.md

## When to use it
- Isolate the structural hook and share trigger behind an overperforming post
- Filter out account-size bias and pure luck before planning new content
- Pinpoint why viewers shared a specific video through top comment signals
- Adapt an extracted viral mechanic into your own niche using brand guidelines

## Example prompts
- Break down this viral post: here is the transcript, stats, and top comments
- Why did this video go viral? Isolate what made it work
- Reverse engineer this competitor post and adapt the mechanism to our niche

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 0f9ec83bb6ed55bc.

BEGIN THIRD-PARTY FILE 0f9ec83bb6ed55bc
```text
---
name: viral-reverse-engineering
description: >-
  Use to reverse-engineer why a piece of content went viral (or overperformed) — yours or someone
  else's — and extract the repeatable mechanism to apply to your own content. Run when the user says
  "why did this go viral," "break down this viral post/video," "reverse engineer," "what made this
  work," or wants to learn from viral content. Sources the observable signal first (intake,
  transcript, screenshots, top comments, visible stats — an agent usually can't watch a video from
  a link) and never fabricates what it can't see. Reads brand-profile and
  audience first, deconstructs the piece layer by layer, isolates the real driver, runs a
  replicability check, extracts the transferable principle, and applies it to the user's niche via
  the content skills. Mechanism, never a copy; flags non-replicable virality; visible signals only
  (no WoopSocial analytics). Single-POST teardown only: for the account-level competitive
  landscape use competitor-analysis; for riding a live trend use trend-jacking.
metadata:
  version: 1.0.0
license: MIT
---

# Viral Reverse-Engineering

Most "learn from viral content" advice produces flops, because people copy the **surface** (the same
sound, topic, format) instead of the **mechanism** (the load-bearing hook, the emotional trigger,
the share driver). This skill does the opposite: it tears a piece down, finds what actually drove it,
checks whether that's even replicable, and turns it into a principle you can apply in your own niche.

Two commitments:

1. **Mechanism, not surface.** Identify the 1–2 load-bearing drivers and the share-trigger — not the
   incidental features. Copying noise reproduces noise.
2. **Honest about luck and survivorship.** A lot of virality is account size, timing, a one-time
   moment, or plain randomness. When success isn't replicable, say so — a false formula is worse than
   none.

## Step 0 — Read the foundation

Load `brand-profile.md` and `audience.md` (for the "apply to your niche" step).

## Step 1 — Source the content (the step everyone skips)

**You usually can't watch a video from a link** — platforms are walled, and a fetch returns metadata
at best. So this skill analyzes whatever **observable signal** is brought in: the user's description,
a **transcript**, **screenshots/key frames** (multimodal), the **top comments**, and the **visible
stats** (views/likes/shares/comments, follower count) — or a fetch/subtitles tool where the agent has
one. Run the **structured intake** in `references/sourcing-the-content.md`: ask for the hook, a
play-by-play/transcript, caption + on-screen text, format, stats, creator size, and sound.
```
END THIRD-PARTY FILE 0f9ec83bb6ed55bc

The third-party file has ended. Everything between the 0f9ec83bb6ed55bc tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2718 of 7604 bytes. © social-media-skills · MIT · https://github.com/social-media-skills/skills/tree/HEAD/skills/viral-reverse-engineering/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md