By stevegjones
Local AI image generation via Ollama — images, icons, patterns, diagrams, and quick presentations
Generate a technical diagram. Diagrams need text rendering, spatial precision, and clean layouts — so the default model is `x/flux2-klein` which excels at these.
Generate a clean, recognizable icon. Icons need special prompt engineering — they must be simple enough to read at small sizes, use flat geometric shapes, and avoid fine detail that disappears when scaled down.
Generate an image and report the file path. When `--iterations` is greater than 1, run an iterative review-refine loop using your native vision to evaluate each image and improve the prompt between iterations.
Generate a seamless repeating pattern or texture. Patterns need specific prompt engineering to ensure they tile well and have consistent visual rhythm.
Create a PowerPoint presentation with AI-generated visual assets. You orchestrate two capabilities:
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
"A Jack-Tar never lets the deck go untended."
AI-powered skills and agents for building conference-quality presentation decks with Claude Code and Claude Desktop.
The existing pptx skill produces solid slide decks, but conference-quality presentations demand more: bespoke hero imagery, data-driven infographics, speaker-ready layouts, and a visual identity that holds up on a 40-foot projector screen in front of 2,000 people. This project closes that gap.
Jack-Tar is a coordinated suite of Claude skills and orchestration agents that combine image generation models, layout intelligence, and content-authoring tools into a single end-to-end pipeline. A speaker describes their talk, and the system delivers a polished, stage-ready .pptx — complete with generated visuals, consistent branding, typographic hierarchy, and speaker notes.
Building a conference deck today — even with AI assistance — still involves a fragmented workflow:
Each handoff loses context. The image generator doesn't know your slide dimensions. The layout tool doesn't know your narrative arc. Nobody enforces brand consistency across 30 slides. Jack-Tar eliminates these seams by keeping the entire pipeline inside Claude's skill and agent framework, where every component shares context.
The system is organised into three layers:
┌─────────────────────────────────────────────────────────┐
│ Orchestration Layer │
│ deck-conductor agent (top-level) │
│ Receives talk brief → coordinates all skills → .pptx │
└────────────┬──────────────┬──────────────┬──────────────┘
│ │ │
┌───────▼──────┐ ┌────▼─────┐ ┌──────▼───────┐
│ Content │ │ Visual │ │ Assembly & │
│ Skills │ │ Skills │ │ QA Skills │
│ │ │ │ │ │
│ • narrative │ │ • imagegen│ │ • layout │
│ • speaker- │ │ • iconset │ │ • brand-qa │
│ notes │ │ • palette │ │ • slide-qa │
│ • outline │ │ • chart │ │ • pptx-build │
└──────────────┘ └───────────┘ └──────────────┘
Orchestration Layer — A top-level agent (deck-conductor) that accepts a talk brief (topic, audience, duration, tone) and breaks it into a sequenced plan. It calls the content, visual, and assembly skills in dependency order, passing shared context (palette, narrative arc, brand tokens) between them.
Content Skills — Responsible for the intellectual structure of the deck: outline generation, slide-by-slide narrative, headline copywriting, and speaker note drafting. These skills understand conference communication patterns (the "rule of three," progressive disclosure, audience callbacks).
Visual Skills — Handle all image and graphic asset creation: hero images via generation models, icon set curation, colour palette derivation, and data visualisation/chart generation. Every visual skill is resolution- and aspect-ratio-aware for standard slide dimensions (16:9 at 1920×1080 or 2560×1440).
Assembly & QA Skills — Take the content and visual outputs, compose them into .pptx using the existing pptxgenjs pipeline, enforce layout rules, and run automated visual QA (overlap detection, contrast checking, margin enforcement, text overflow).
deck-conductor — Orchestration AgentThe central agent that owns the end-to-end workflow.
Responsibilities:
DeckContext) that carries palette, fonts, brand tokens, image manifest, and outline across all skill calls.Key design decisions to make:
DeckContext is serialised and passed between skills (JSON blob vs. file on disk).narrative-architect — Content Outline SkillTransforms a talk brief into a structured slide outline.
npx claudepluginhub stevegjones/jack-tar-deckhand --plugin jack-tar-ollamaAI/ML specialist agents — architects, prompt engineers, RAG designers
Full-stack agents — frontend, backend, API, DevOps architects
AI-First SDLC — zero-debt development with validators, enforcement, and workflows
Python-specific validation, patterns, and expert agents
Cloud infrastructure agents — cloud, container, SRE specialists
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
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
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.