From ads-visual-fs
Activates when analyzing a competitor ad for transferable creative strategies — extracting layout architecture, visual metaphor, color psychology, typography approach, imagery style, emotional appeal, messaging strategy, and attention mechanics, then mapping each to FS brand equivalents. This is a shared analysis capability, not a user-facing workflow.
npx claudepluginhub jeffrey94/jeffrey-skills --plugin ads-visual-fsThis skill uses the workspace's default tool permissions.
Structured creative strategy extraction from competitor ad visuals. Used by the Competitor Reference workflow.
Analyzes competitor brands using positioning, messaging, voice, and visual frameworks. Scores competitors, benchmarks against your brand, and identifies market positioning gaps.
Researches brands from URL or description to generate Brand DNA docs analyzing identity, visuals, typography, colors, photography, packaging, and ad styles. Saves to brands/{brand}/brand-dna.md.
Deconstructs video ad creatives using a framework for hooks, persuasion tactics, structure, pacing, target audience, and CTAs to derive marketing insights.
Share bugs, ideas, or general feedback.
Structured creative strategy extraction from competitor ad visuals. Used by the Competitor Reference workflow.
This skill provides domain expertise when you need to analyze a competitor ad for transferable creative strategies. You perform this analysis directly using your multimodal capabilities — do NOT call any MCP tool.
Key difference from marketing-analysis: This does NOT extract FS-specific attributes. It extracts creative strategies (layout, metaphor, emotion, attention flow) from competitor ads and maps each to FS brand equivalents.
Analyze each dimension, then provide an FS Translation showing how to adapt it:
For detailed schemas, example outputs, and edge cases, see references/analysis-dimensions.md.
Present each dimension as:
| Dimension | Competitor Pattern | FS Translation |
|---|---|---|
| Layout Architecture | ... | ... |
| Visual Metaphor | ... | ... |
| ... | ... | ... |
Always flag uncertainties and assumptions separately.
After presenting analysis, always ask the user to confirm or edit the analysis before it is used downstream. This is critical — never proceed automatically.