Index of every page on this site: llms.txt
All skills
Run it yourself

Converts evidence-backed trend signals, outlier posts, audience language, and competitor patterns into original platform-native content tests without copying a source's unique expression. Use after trend research, creator teardown, comment mining, or outlier analysis.

  • 2 files
  • 5.5 KB
  • MIT
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/alptugharun/ai-social-media-toolkit/signal-to-content

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈72 tokens for metadata: the name and description. ≈837 when used: this file. ≈487 more on demand in 1 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 ≈288 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.

Signal to Content

Turn evidence into original content.

This skill sits between research and production.

It should not produce a generic brainstorm from a trend name.

It should explain what worked, separate the reusable mechanic from the source's unique expression, score the opportunity, and create platform-native tests for the user's brand.

Inputs

Accept any combination of:

  • trend brief
  • outlier table
  • creator teardown
  • comments / audience language
  • transcripts
  • competitor research
  • Pinterest keyword clusters
  • article / news source
  • user-provided examples

Use creator context when available.

Step 1 — Extract the Signal

For every source identify:

  • observed performance signal
  • hook mechanism
  • format
  • audience problem / desire
  • emotional trigger
  • proof mechanism
  • visual pattern
  • CTA pattern
  • timing / freshness
  • saturation

Do not confuse unique wording with a reusable mechanism.

Step 2 — Separate Mechanic from Expression

Create two columns:

Reusable Mechanic

Examples:

  • before / after contrast
  • myth vs evidence
  • rapid checklist
  • visual transformation
  • first-person experiment
  • comparison
  • reveal
  • contrarian question
  • searchable tutorial

Source-Specific Expression

Examples:

  • exact sentence
  • proprietary brand asset
  • personal story
  • distinctive graphic
  • copyrighted footage
  • unique joke / character

Do not copy source-specific expression unless the user owns it or has permission.

Step 3 — Score the Opportunity

Use the toolkit's transparent heuristic:

Base Score

  • Evidence strength: 30%
  • Audience fit: 25%
  • Freshness: 20%
  • Repeatability: 15%
  • Production ease: 10%

Then subtract a saturation penalty of up to 15 points.

Inputs should be 0–100.

This is a prioritization heuristic, not a validated prediction model.

The companion tool is:

tools/signal2content_score.py

Step 4 — Create Original Tests

For each high-priority signal create original executions.

Possible outputs:

  • Reels / Shorts
  • Pinterest Pins
  • Instagram carousel
  • LinkedIn post
  • Article angle
  • Newsletter
  • visual-series brief

For every execution provide:

  • Hook
  • Core idea
  • Format
  • Visual direction
  • Why it fits the audience
  • What changed from the source pattern
  • CTA
  • KPI

Step 5 — Build the Content Ladder

A strong signal can become a sequence:

Signal → Fast Test → Winner → Series → Evergreen Asset → Website / Lead Magnet

Do not scale a concept before the first test provides evidence.

Output

Signal to Content Brief

Research Input

  • Sources:
  • Platforms:
  • Window:
  • Confidence:

Opportunity Table

Signal Reusable mechanic Evidence Fit Freshness Saturation Score

Source-Specific Elements Not to Copy

  • ...

Original Content Tests

Test 1

  • Platform:
  • Hook:
  • Format:
  • Visual:
  • Angle:
  • Transformation from source:
  • CTA:
  • KPI:

Content Ladder

  • Fast test:
  • Follow-up:
  • Series:
  • Evergreen asset:

Review Gate

  • Evidence is real and cited when available
  • Source-specific expression was not copied
  • The execution fits creator context
  • Platform constraints are respected
  • KPI matches the objective

Core Principle

Borrow the pattern. Rebuild the expression. Improve the system.

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/signal-to-content