Gemini

dmux-workflows is a guide for orchestrating parallel AI agent sessions with dmux in tmux panes. It helps split research, implementation, testing, and docs across Claude Code, Codex, OpenCode, and similar harnesses so you can manage multi-agent development with less context bottlenecking.

brainstorming is a pre-implementation skill that explores context, asks clarifying questions one at a time, and requires design approval before any code. Includes an optional visual companion and strong support for Requirements Planning.

writing-plans helps turn a spec or requirements doc into a detailed implementation plan with file-level guidance, task sequencing, testing steps, and a review prompt before coding starts.

using-superpowers is a session-start skill from obra/superpowers that forces skill lookup before any reply, helping agents discover and activate the right workflow first.

gemini-automation helps Claude run Gemini workflows through Composio Rube MCP. Learn setup requirements, connection checks, RUBE_SEARCH_TOOLS discovery, and safe usage before executing current tool schemas.

karpathy-coder helps AI coding agents expose assumptions, avoid over-abstraction, keep diffs surgical, and define verifiable goals. Includes SKILL.md, references, expected JSON outputs, and Python checks for assumptions, complexity, diff noise, and goal verification.

engineering-skills is an index for the engineering-team bundle in alirezarezvani/claude-skills. Use it for Skill Discovery to choose one specialist SKILL.md across architecture, frontend, backend, QA, DevOps, security, AI/ML, data, and tools—without bulk-loading the bundle.

content-strategy helps teams plan a content marketing program with clear pillars, buyer-stage mapping, prioritization, and a practical publishing roadmap. Use it to install context, review key files, and turn vague goals into actionable strategy.

Use the copy-editing skill to improve existing marketing copy with a Seven Sweeps workflow. Learn install steps, recommended files, usage prompts, and how to preserve voice while tightening wording, proof, clarity, and copy-editing for Proofreading.

ai-seo helps teams improve AI answer visibility across ChatGPT, Perplexity, Google AI Overviews, Claude, and Gemini. Use it to diagnose indexing, bot access, extractability, and citation readiness, then build a practical content plan with the repo’s platform and content-pattern references.

mama is a narration-style variant of the pua skill that keeps the same core rules but switches to a Chinese nagging-mom voice. Use it to install a reusable trigger pattern for persistent troubleshooting, debugging, and Prompt Writing workflows, with inherited escalation, checklists, and stronger follow-through.

baoyu-danger-gemini-web is a Gemini Web client wrapper for text, image generation, reference-image vision, and multi-turn chat. It runs from the local skill repo with bun or npx, uses scripts under `scripts/`, and requires a first-use consent check before install and usage.

Use the gemini-interactions-api skill to build Gemini API code for chat, multimodal prompts, streaming, structured output, tool use, and image generation. It also helps with migration from older generateContent patterns and provides practical guidance for API Development in Python and TypeScript.

gemini-live-api-dev is a practical skill for building real-time, bidirectional apps with the Gemini Live API. It covers WebSocket streaming, VAD, native audio, function calling, session management, ephemeral tokens, and SDK guidance for google-genai and @google/genai.

vertex-ai-api-dev is a practical guide for API development with Gemini API on Google Cloud Vertex AI using the Gen AI SDK. It helps teams work with enterprise auth, model access, text and multimodal generation, function calling, structured JSON, embeddings, Live API, caching, batch prediction, and tuning.

Use gemini-api-dev for API Development to build current Gemini API integrations with multimodal inputs, function calling, structured outputs, and SDK-specific setup. The gemini-api-dev skill helps you choose current models, avoid legacy defaults, and follow a practical gemini-api-dev guide for Python, JavaScript/TypeScript, Java, and Go.

nanobanana is a Python CLI skill for Google Gemini 3 Pro Image that supports text-to-image, image editing, aspect ratios, 2K/4K output, and batch generation with simple local scripts.

The web-content skill helps create web pages for SEO and AI discovery. Use it for landing pages, homepages, category pages, guides, and product pages when you need cleaner structure, direct answers, and content that is easier for search engines and AI systems to cite.

gemini-review is a Gemini-powered code review skill for large repositories and PRs. It uses Gemini 2.5 Pro and 1M-token context to review code with less chunking, better cross-file reasoning, and CI/CD-friendly feedback.

scientific-schematics turns natural-language prompts into publication-quality scientific diagrams with smart iterative refinement. It uses Nano Banana 2 for generation and Gemini 3.1 Pro Preview for review, regenerating only when output falls below the threshold for your document type. Built for neural network architectures, system diagrams, flowcharts, biological pathways, and other complex scientific visuals.

generate-image is a skill for generating or editing images with AI models like FLUX.2 Pro and Gemini 3.1 Flash Image Preview through OpenRouter. Use it for photos, illustrations, concept art, visual assets, and image edits when you want a repeatable workflow instead of a one-off prompt. For diagrams, flowcharts, and schematics, use scientific-schematics instead.

code-review is a mandatory review workflow for code changes before commits and deploys. It helps teams run a structured /code-review step, choose an engine, and get actionable feedback instead of a generic pass. Ideal for pre-merge checks, release candidates, and high-stakes refactors.

ai-models is a reference skill for choosing current AI models by task, cost, latency, and quality. It helps skill authors and builders make fast, defensible model choices for chat, coding, vision, embeddings, voice, and image generation.

The agentic-development skill helps you build AI agents for multi-step orchestration with Pydantic AI in Python or Claude Agent SDK in Node.js. Use it to choose a framework, define tools, and shape typed, production-ready agent workflows.