Plan and prompt-engineer AI-generated visuals (images, diagrams, video) for whitepapers, blog posts, and long-form content. Six skills cover project onboarding, visual ideation, prompt generation, project listing, fal-ai execution, and style reference.
npx claudepluginhub danielrosehill/claude-code-plugins --plugin visual-communicationsUse when the user wants to convert a chosen visual concept into an optimised text-to-image, image-to-image, or video prompt.
Use when the user wants to brainstorm visual ideas for a project's source content.
Use when the user wants to see all visual-communications projects with their status.
Use when the user wants to set up a new visual-communications project for content enhancement.
Use when the user wants to execute a saved prompt against the official fal-ai MCP server and save the resulting image or video into the project's visuals directory.
Use when the user wants to look up resolution guidelines per platform or style modifier vocabulary for visual generation.
Claude Code plugin for planning and prompt-engineering AI-generated visuals (images, diagrams, video) for whitepapers, blog posts, technical documents, and other long-form content.
Originally a workspace template (Claude-Visual-Communications-Space); now packaged as a plugin so it can be installed into any project. Project state lives under the plugin data-storage path, not the host repo.
claude plugins install visual-communications@danielrosehill
| Skill | Purpose |
|---|---|
onboard-visual-project | Set up a new visual project — name, type, target platform, source material, audience, style. |
ideate-visuals | Brainstorm 5–8 visuals (hero, explanatory, conceptual, data, spot, interactive, video) for a project's source content. |
generate-visual-prompt | Convert a chosen visual concept into a model-optimised prompt (Flux / SDXL / video) with 2–3 variations and negative prompts. |
list-visual-projects | Show all projects in the plugin data store with status (source / ideation / prompts / visuals). |
run-fal-generation | Execute a saved prompt via the fal-ai MCP and save outputs to the project's visuals/ directory. |
visual-style-reference | Lookup resolution guidelines per platform and style-modifier vocabulary (professional / technical / editorial / friendly). |
Projects are stored under:
${CLAUDE_PLUGIN_DATA:-$HOME/.local/share/claude-plugins}/visual-communications/projects/<name>/
source/
visuals/
prompts/
project.yaml
ideation.md # produced by ideate-visuals
run-fal-generation. Install with:
claude mcp add --transport http fal-ai https://mcp.fal.ai/mcp \
--header "Authorization: Bearer $FAL_KEY"
onboard-visual-project → scaffolds projects/<name>/
ideate-visuals → projects/<name>/ideation.md
generate-visual-prompt → projects/<name>/prompts/<slug>.yaml
run-fal-generation → projects/<name>/visuals/<file>
MIT — Daniel Rosehill.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Share bugs, ideas, or general feedback.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Frontend design skill for UI/UX implementation
Creative skill for generating algorithmic and generative art. Produces visual designs using mathematical patterns, fractals, and procedural generation.
Humanise text and remove AI writing patterns. Detects and fixes 24 AI tell-tales including inflated language, promotional tone, AI vocabulary, filler phrases, sycophantic tone, and formulaic structure.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim