Image

Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to 20 inputs), the schema, and when to route to GPT Image 2 edit / Flux Kontext / Nano Banana 2 t2i instead. Calls `runcomfy run google/nano-banana-2/edit` through the local RunComfy CLI. Triggers on "nano banana edit", "edit with nano banana", "image edit nano banana", or any explicit ask to edit with this model.

Edit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper edits without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/edit` through the local RunComfy CLI. Triggers on "image edit", "edit image", "image-to-image", "i2i", "swap background", "remove object", "rewrite headline", or any explicit ask to edit a single or batch of images.

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Use when the user explicitly asks for Super Review Council, super-review-council, 超级审查会, or a heavy multi-agent review council workflow; or when a loaded coordinator workflow explicitly invokes this skill as a bounded child review pass. Do not trigger for plain review, built-in codex review, Guardian auto_review, normal maintenance, commits, shipping, CI checks, old skill-name mentions, or mere path mentions.

🧠 A powerful collection of agent skills to interact with the @Openapi® API marketplace — company data, official documents, KYC/risk, e-signatures, invoicing, SMS, PEC, and more

End-to-end credit risk modeling workflow for application, behavior, collection, and anti-fraud risk models. Use when building, validating, comparing, or documenting scorecards, logistic regression, LightGBM, XGBoost/CatBoost/random forest, or other machine-learning credit models; when computing IV/WOE, KS, AUC, PSI, lift, score bands, OOT validation, feature importance, scorecard points, reject/approval strategies, or model development validation reports.

Automate Google Photos tasks via Rube MCP (Composio): upload media, manage albums, search photos, batch add items, create and update albums. Always search tools first for current schemas.

Automate Dreamstudio tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate All Images AI tasks via Rube MCP (Composio). Always search tools first for current schemas.

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

Automate Replicate AI model operations -- run predictions, upload files, inspect model schemas, list versions, and manage prediction history via the Composio MCP integration.

Automate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio MCP integration.

Automate Imgbb tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Imagekit IO tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Html To Image tasks via Rube MCP (Composio). Always search tools first for current schemas.

Generate stylish Xiaohongshu (RedNote) cover images based on themes via simple API integration for AI agents.

Provide model engineering skills for training, tuning, and modifying large language and vision models using PyTorch, Hugging Face, and related tools.

Print text, images, and QR codes to a Bluetooth thermal printer. Use `inkjet print` for output, `inkjet scan` to discover printers, and SKILL.md for agentic control with OpenClaw, GitHub Copilot, etc.

Image generation skill for AI coding agents. Go CLI wrapping Google Gemini's native image generation API.

Slightly less YOLO version of pi-coding-agent in Docker container sandbox

Claude Skills

Watercolor Art Generator — AI-powered watercolor art generator ai

🛠️ Claude Code / OpenClaw Skill — Turn support tickets, logs, screenshots into sanitized engineering issue packs. 17 PII redaction patterns, log parsing, stack trace extraction (Python/Java/JS/Go), error code classification, timeline. 客服工单脱敏 | 隐私数据脱敏 | 日志解析 | 堆栈提取 | 错误码分类 | 中英双语Skill | 支持转研发问题包生成器