By nim-video
Generate images and videos and run templated creative workflows with Nim — model discovery, direct generation, and reference-driven editing through the Nim MCP.
Use when creating product or lifestyle b-roll videos from a user brief with optional product, character, and location reference images, especially when the output should be generated with Nim Seedance. Handles brief intake, missing-input checks, reference mapping, Seedance prompt drafting, approval checkpoints, Nim upload/generation, and iteration.
Generate or edit images and videos with Nim. Use when the user says "generate an image", "make a picture / poster / logo / wallpaper", "edit / restyle / remix this image", "make a video", "animate this photo", "image-to-video", "turn this into a clip", "give me variations / options", or asks for any visual asset from a prompt or a reference. Discovers the right Nim model with models_explore, follows its generationContract exactly, uploads references with media_upload, and submits with generate_image / generate_video. Supports text-to-image, image editing, text-to-video, and image-to-video. NOT for: code, text/chat answers, or audio-only tasks.
Author a production-ready Seedance 2 hook video for short-form UGC (TikTok / Reels / Shorts) and generate it through the Nim MCP. Use when the user wants a talking-head "hook" ad/UGC clip from a product brief, asks to "make a hook video", "generate a UGC hook", "spoken hook ad", or "Seedance hook". The agent acts as the prompt-writing LLM: it intakes the brief, proposes 5 spoken hook options, collects character/product/location reference images, assembles the Seedance brief, rewrites it into a final Seedance prompt, and generates the video on Nim Seedance 2. NOT for: long scripts, code, text-only answers, or audio-only tasks.
Use when generating believable editorial young-adult human portraits or fashion/UGC character images with Nim, especially Gen-Z fashion casting, model/person look development, aesthetic human references, or prompt-driven human generation. Asks for age or age range, sex/gender presentation, ethnicity/look, and additional notes; defaults to Nano Banana Pro in 9:16, but supports user-specified models such as GPT Image 2 by discovering the live Nim model contract.
External network access
Connects to servers outside your machine
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.
Turn your coding agent into a creative studio. Nim is the AI engine for visual generation and ideation — discover the right model, generate images and video, edit from references, and run templated creative workflows, all from your agent through the Nim MCP.
Works with Claude Code, Codex, and Cursor today; the same SKILL.md skills
are designed to extend to more agents.
claude plugin marketplace add nim-video/skills
claude plugin install nim@nim
The plugin bundles the Nim MCP server automatically — on first generation you'll be prompted to authenticate with Nim.
codex plugin marketplace add nim-video/skills
Then enable the nim plugin from the /plugins picker. The bundled MCP server is
registered on install; you'll complete Nim authentication on first use.
Prefer to wire the MCP server yourself (no plugin)? Add it directly:
# ~/.codex/config.toml [mcp_servers.nim] url = "https://mcp.nim.video/mcp"
Install Nim from the Cursor plugin marketplace (Settings → Plugins). The bundled Nim MCP server is registered with the plugin; you'll authenticate with Nim on first use.
Prefer to wire the MCP server yourself (no plugin)? Add it directly in Cursor's MCP settings:
{ "mcpServers": { "Nim": { "url": "https://mcp.nim.video/mcp" } } }
| Skill | Invoke | What it does |
|---|---|---|
nim-generate | /nim:nim-generate | Generate and edit images and video — text-to-image, image editing, text-to-video, and image-to-video. Discovers the right model, follows its contract, handles references, and returns the result. |
nim-b-roll-seedance | /nim:nim-b-roll-seedance | Create staged product/lifestyle b-roll videos from a brief and references. Builds concise creative direction, handles reference roles internally, and generates with Seedance 2 through Nim. |
nim-hookgen-seedance | /nim:nim-hookgen-seedance | Write and generate talking-head "hook" UGC ad clips for short-form (TikTok / Reels / Shorts). Proposes spoken hook options, maps character/product/location references, and generates with Seedance 2 through Nim. |
nim-human-generation | /nim:nim-human-generation | Generate believable editorial young-adult human portraits and fashion/UGC character images. Intakes age, gender presentation, and look; defaults to Nano Banana Pro in 9:16 and supports user-specified models. |
The skill drives model discovery (models_explore), generation (generate_image /
generate_video), reference uploads (media_upload), and status polling
(get_generation_status) through the Nim MCP.
MIT — see LICENSE.
npx claudepluginhub nim-video/skills --plugin nimHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Plugin that includes the Figma MCP server and Skills for common workflows
AI-powered development tools for code review, research, design, and workflow automation.
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.
Memory compression system for Claude Code - persist context across sessions