Browse Skills

Deep Research orchestrates a multi-agent workflow that splits a research goal into parallel sub-tasks, gathers evidence with Codex CLI subprocesses, and merges the results into a verified report. Use it for systematic web or document research, competitor analysis, and long-form evidence synthesis.

GPT Image generates or edits images with OpenAI GPT Image models from prompts and input images. Use it when you want to create artwork, logos, or modified images with gpt-image-2 or related models.

MiniMax Image generates images from text prompts through the MiniMax Image API helper. Use it when you need image-01, image-01-live, or other MiniMax image generation from a local prompt.

Motion Designer creates detailed scene-by-scene video specifications for Remotion, including timing, audio, transitions, and animation notes. Use it when planning motion graphics or when asked to create or spec out a video.

Nanobanana Image generates, edits, and composites images with the bundled Gemini CLI wrapper. Use it for reference-image composition, grounded visuals, style transfer, mockups, and other AI image tasks.

Remotion Best Practices covers domain-specific guidance for building videos in React with Remotion. Use it when working on compositions, timing, audio, captions, transitions, or rendering workflows.

Remotion Render renders React/Remotion TSX code into MP4 video through inference.sh. Use it for programmatic video generation, motion graphics, animated React scenes, and other code-driven video exports.

Agent Development explains how to create Claude Code agents, including frontmatter, triggering descriptions, tools, model choice, and system prompt structure. Use it when you need guidance on subagent design or best practices for agent files.

Build An MCPB packages a local MCP server with its runtime so it can be installed as one file and run without Node or Python already installed. Use it for filesystem, desktop, localhost, or OS-level tools that need to run on the user's machine.

Build MCP Server guides you through designing and building an MCP server for Claude. It helps choose the right deployment model, auth approach, and tool pattern before scaffolding code.

Claude Automation Recommender analyzes a codebase and suggests Claude Code hooks, subagents, skills, plugins, and MCP servers. Use it when setting up Claude Code for a project or improving existing Claude workflows.

Claude Md Improver audits CLAUDE.md files across a repository and reports gaps in commands, structure, and project context. It then updates those files with targeted improvements after approval.