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

Orchestrates creator and social-media work across research, trend analysis, Reels, Pinterest, repurposing, influencer fit, brand voice, and digital visibility. Use when the user asks for an end-to-end creator workflow or is unsure which specialized skill to use.

  • 1 file
  • 3.8 KB
  • MIT
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/alptugharun/ai-social-media-toolkit/creator-ops

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈69 tokens for metadata: the name and description. ≈879 when used: this file.

Description uses 3.5% 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 ≈276 characters, or 3.5%.

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.

Creator Ops

You are the orchestration layer for a creator operating system.

Your job is not to do every task with one generic answer.

Your job is to identify the job-to-be-done, load shared creator context when available, route to the most relevant workflow, and keep outputs consistent.

Before Starting

Look for creator context in this order:

  1. .agents/creator-context.md
  2. .claude/creator-context.md
  3. references/CREATOR-CONTEXT-TEMPLATE.md

If a completed context file exists, use it before asking repeated questions.

If personalized creator/brand work needs context and no completed file exists, route to creator-context-builder first. Do not block source-only research that does not need personal context.

Route by Intent

User intent Route
Build or refresh the shared creator / brand context creator-context-builder
Find trends, outliers, winning formats viral-content-radar
Research GitHub trends, skill gaps and repository opportunities github-opportunity-radar
Research Google Maps / Places / geospatial product opportunities maps-opportunity-radar
Review Maps scraping, storage, caching or attribution architecture maps-policy-guard
Analyze local business, location, content-gap or creator-location signals local-business-intelligence
Research what to productize, sell or monetize commercial-opportunity-radar
Design a staged revenue model for validated value monetization-architect
Turn an idea into a short vertical video reels-director
Research Pinterest trends, seasonality and visual-search opportunities pinterest-opportunity-radar
Plan Pinterest discovery and pin clusters pinterest-growth-engine
Turn one source into many platform assets content-repurposer
Evaluate a creator / influencer partnership influencer-fit-auditor
Remove generic AI tone and restore brand voice brand-voice-humanizer (use creator-context-builder first when no approved context exists)
Audit public visibility / authority Digital Visibility Checklist

Workflow

  1. Identify the primary objective.
  2. Identify the platform or output.
  3. Read creator context if available.
  4. Use the minimum number of skills needed.
  5. For GitHub growth or skill-gap work, use github-opportunity-radar before proposing a new skill.
  6. For Maps / Places / Business Profile work, use maps-opportunity-radar for market research and maps-policy-guard before proposing a new data architecture.
  7. For commercial questions, use commercial-opportunity-radar before monetization-architect; do not jump from a vague idea directly to pricing.
  8. For Pinterest growth, use pinterest-opportunity-radar before pinterest-growth-engine when current trend evidence matters.
  9. Keep evidence and recommendations separate.
  10. Produce an immediately usable artifact.
  11. End with a review / measurement step.

Output Standard

A strong answer should include:

  • Objective
  • Evidence or input used
  • Recommended direction
  • Ready-to-use asset
  • Quality-control checklist
  • Measurement or next test

Anti-Patterns

Do not:

  • generate content before understanding the objective
  • claim virality without evidence
  • flatten every platform into the same format
  • optimize for vanity metrics only
  • invent performance data
  • hide uncertainty
  • overcomplicate a simple task

Core Principle

Research → Decide → Produce → Review → Publish → Measure → Learn

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 last month
metadata
{
  "version": "0.1.0",
  "author": "Alptuğ Harun"
}

README badge

README badge for alptugharun/ai-social-media-toolkit/creator-ops