Index of every page on this site: llms.txt
All skills
alptugharun avatar

/viral-content-radar

@2b12408
Run it yourself

Finds and deconstructs recent high-performing social content, outliers, formats, hooks, audience reactions, and emerging opportunities. Use when the user asks what is trending, viral, overperforming, worth copying structurally, or likely to become a content opportunity.

  • 1 file
  • 2.7 KB
  • MIT
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/alptugharun/ai-social-media-toolkit/viral-content-radar

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈73 tokens for metadata: the name and description. ≈607 when used: this file.

Description uses 3.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈292 characters, or 3.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Viral Content Radar

Find content patterns worth acting on.

The goal is not to return a random list of popular posts.

The goal is to identify repeatable mechanics behind recent high-performing content and translate them into original content tests.

Evidence Requirement

Use references/EVIDENCE-POLICY.md.

If web or platform data is unavailable, ask for URLs, screenshots, exports, or source data instead of inventing trends.

Research Scope

Capture when available:

  • Platform
  • Creator / brand
  • Post URL
  • Publish date
  • Format
  • Hook
  • Topic
  • Views / plays
  • Likes
  • Comments
  • Shares / reposts
  • Saves
  • Follower count or account baseline
  • Audience reaction
  • Visual pattern
  • CTA

Outlier Logic

Prefer performance relative to the creator's normal baseline.

When enough comparable posts exist:

outlier_lift = post_primary_metric / median_primary_metric

Suggested labels:

  • 5x+ baseline: huge outlier
  • 2x–5x: strong outlier
  • 1.5x–2x: mild outlier

These thresholds are heuristics, not universal truths.

Do not combine incomparable platform baselines.

Pattern Extraction

Look for:

  • Hook mechanism
  • Opening visual
  • Emotional trigger
  • Surprise / novelty
  • Proof
  • Transformation
  • Format
  • Editing rhythm
  • Comment trigger
  • Save trigger
  • Share trigger
  • Search intent
  • Timing
  • Production difficulty
  • Saturation

Opportunity Score

Use a transparent heuristic when ranking ideas:

  • 30% evidence strength
  • 25% audience fit
  • 20% freshness
  • 15% repeatability
  • 10% production ease

Apply a saturation penalty when the exact execution is already overused.

Always label this as a heuristic.

Output

Viral Content Radar: {niche}

Evidence Summary

  • Platforms:
  • Window:
  • Sample:
  • Confidence:

Biggest Outliers

Post Platform Signal Lift / evidence Repeatable mechanic

Patterns Worth Reusing

Pattern Evidence Why it worked Saturation risk

What Not to Copy

Identify unique wording, copyrighted creative, personal storytelling, or brand-specific elements that should not be duplicated.

Original Content Tests

For each test provide:

  • Hook
  • Format
  • Visual direction
  • Why now
  • Production difficulty
  • Success metric

Best Next Test

Choose the strongest evidence-backed experiment.

Core Principle

Copy the mechanic, not the creator's unique expression.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 2b12408. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 days ago.

Activeupdated 2 months ago
metadata
{
  "version": "0.1.0",
  "author": "Alptuğ Harun"
}

README badge

README badge for alptugharun/ai-social-media-toolkit/viral-content-radar