SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
paperbanana-skill
Generate publication-quality methodology diagrams, statistical plots, and presentation slides using a multi-agent pipeline and configurable VLM/image providers.
skills
Generate and edit images (text→image, image→image, advanced edits) using TensorsLab models with automatic prompt enhancement and local output saving.
xiaotianfotos
Multi-engine AI creative toolchain: TTS, ASR, image generation (ComfyUI), and subtitle/video cut tooling.
free-imagegen
A fully local text-to-image pipeline that renders structured SVGs and exports PNGs—designed for thumbnails, text covers, infographics, and article-to-image work
claude-code-plugins-plus-skills
Production checklist and SDK patterns for integrating Runway (AI video/image generation) into production workflows.
skills
Generate themed photo packs from a single reference image while preserving the exact facial identity and enforcing identity-lock guardrails.
openakita
Run Google Gemini 3.1 Flash Image Preview via inference.sh CLI: text-to-image, image editing, multi-image input, and Google Search grounding.
xhs-skill
Create Xiaohongshu (XHS) notes with written content and rendered image cards; supports multiple styles, batch creation, and publishing workflows.
skills
Control Dreamina (即梦) image and video generation via the dreamina CLI; check account, submit async generation jobs, and query results safely.
skills
Create podcasts, explainer videos, TTS, and AI images using ListenHub scripts; run the provided shell scripts to generate, check status, and download outputs.
clawra
Edit a fixed reference image with Grok Imagine and send AI-edited selfies to messaging channels (Discord, Telegram, WhatsApp, Slack) via OpenClaw.
openclaw-master-skills
Provides agents a funded identity (wallet, email) plus paid API tools: web search, image/video/music generation, SMS/voice, email, and an LLM gateway — useful w
gpt-image
Generate and edit raster images via a CLI-first workflow, with an explicit Codex path for native generation.
codex-image
Generate images via the Codex CLI using OAuth (no API key). Handles argument parsing, save paths, and error messages for gpt-image-2 generation.
comfyui-expert
Guided conversational interview that extracts a user's creative vision and synthesizes model-specific image prompts, negatives, recommended settings, and a pipe
comfygen
Run ComfyUI workflows on RunPod serverless GPUs: manage endpoints, resolve and download models, submit workflows, and fetch outputs via the comfy-gen CLI.
10x-chat
Automates browser sessions to chat with multiple web AI providers (ChatGPT, Gemini, Claude, Grok, Perplexity, NotebookLM) for cross-validation, image generation
photo-studio-skill
Generate professional AI-enhanced portraits, couple/family photos and posters using Seedream 4.5 with scenario-driven workflows and templates.
awesome-omni-skill
Generate AI-driven cover image prompts and a self-contained interactive HTML page that converts Xiaohongshu copy into image-generation prompts (Nano Banana Pro
comfyui_skills_openclaw
Run and manage ComfyUI image-generation workflows via a CLI from AI agents—import, execute, check dependencies, and retrieve outputs across servers.
bananahub-skill
Multi-provider image workflow that normalizes and optimizes non-English prompts, generates and edits images across Gemini/OpenAI providers, and manages reusable
ultimate-ai-media-generator-skill
Create and monitor image and video generation tasks using the CyberBara API: list models, upload references, quote credits, submit tasks, poll for results, and
