Creative strategist
Skill foxgeeek/adskills/.claude/skills/linkedin-ads/creative-strategist
Claude Code Skills framework for multi-platform ad operations — Meta, Google, LinkedIn Ads from the terminal / Framework de Claude Code Skills pra gestão de tráfego multi-plataforma
npx -y skills add foxgeeek/adskills --skill creative-strategistAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Analyze LinkedIn creative format performance (single image, carousel, video, document, lead gen) and suggest next formats to test. Aggregates by format across all creatives in a campaign. Triggers on prompts about which format to double down on, lead gen performance, or creative testing strategy.
SKILL.md
1.4 KB, 278 tokens by cl100k_base, as published. Nobody here has run it
LinkedIn Ads — Creative Strategist
When to use
- "Qual formato tá performando melhor no LinkedIn?"
- "Double down ou pausa formato X?"
- "What creative format should I test next?"
Inputs
--account— account ref--campaign— required campaign ID--lookback— days (default 30)
Logic
- Fetch creative-level insights pivoted by
CREATIVE - Aggregate by creative
format - Compute per-format: creatives count, impressions, clicks, CTR, spend, leads, CPL
- Sort by clicks (volume indicator)
- Suggest:
- Double down on best format if CTR > 1% AND leads > 0
- Pause worst format if spend > $100 AND leads = 0
- Test second format if only one format in flight
Output
- Format-level table with all metrics
- Suggestions block (bullet list)
- HTML + markdown report
Invocation
adskills linkedin creatives --account acme --campaign 1234567890 --lookback 30
Guardrails
- Read-only
- Does not count formats with zero impressions (noise filter)
- Suggestions are heuristic — always validate with domain knowledge of the offer