flux-kontext
🎯Skillfrom prime-skills/runcomfy-agent-skills
Installation
npx vibeindex add prime-skills/runcomfy-agent-skills --skill flux-kontextnpx skills add prime-skills/runcomfy-agent-skills --skill flux-kontext~/.claude/skills/flux-kontext/SKILL.md
|A Claude Code skill that enables precise single-image editing using Black Forest Labs's Flux 1 Kontext Pro model through the RunComfy CLI, with built-in prompting patterns for high-fidelity local edits.
Overview
Flux Kontext Pro is a Claude Code skill that connects to the RunComfy Model API to perform precise, single-reference image edits using Black Forest Labs' Flux 1 Kontext Pro model. The skill bundles documented prompting patterns so that edits produce stronger results than naive prompting against the same model. It calls runcomfy run blackforestlabs/flux-1-kontext/pro/edit through the local RunComfy CLI, accepting a single source image URL and a declarative edit instruction.
The skill includes built-in routing guidance: it knows when to use Kontext (single-image precise local edits, identity preservation, brand-asset swaps) versus when to suggest alternatives like Nano Banana Edit (multi-image batch edits), GPT Image 2 edit (multilingual text editing), or Flux 2 Klein (generation from scratch without a source image).
Key Features
- Single-shot precise local editing with high source identity preservation through explicit preservation-led prompting
- Built-in prompting best practices: declarative single-instruction format, preservation-first phrasing, and anti-pattern warnings to avoid prompt drift
- Model routing intelligence: automatically suggests the right model based on the editing task (Kontext for single-ref edits, Nano Banana for multi-image, GPT Image 2 for text, Flux 2 Klein for generation)
- Reproducible results via optional seed parameter for variant comparisons
- Secure execution: no shell injection surface from prompt content, owner-only token storage, and a 2 GiB download cap per output file
- CI/container support through
RUNCOMFY_TOKENenvironment variable as an alternative to interactive login
Who is this for?
- Designers and creative professionals who need precise, repeatable single-image edits (swapping objects, changing text on labels, adding accessories) without leaving their Claude Code workflow
- Brand and marketing teams performing targeted asset modifications like logo color swaps, label text replacements, or product shot adjustments
- Developers building image-editing pipelines who want a CLI-driven, scriptable interface to a high-quality image edit model with clear input schemas and exit codes
Same repository
prime-skills/runcomfy-agent-skills(25 items)
SKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that automatically selects the best model (Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, or Lucy Edit Restyle) based on what the user wants to do, from general restyling and background swaps to precise motion transfer and outfit changes.
A smart intent-routing skill that animates still images on RunComfy by selecting the optimal model: HappyHorse 1.0 I2V for general portrait and product animation with native audio, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition with image, video, and audio references.
A skill for generating images with Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family on RunComfy, optimized for rapid iteration, batch ideation, in-image typography rendering, and optional web-grounded context with support for resolutions from 0.5K to 4K.
A smart intent-routing skill for image editing on RunComfy that selects the optimal model from Nano Banana Edit (batch up to 20 images), GPT Image 2 Edit (multilingual text rewrite, multi-ref composition), Flux Kontext Pro (single-shot precise local edit), or Z-Image Turbo Inpaint (mask-driven region edit) based on user intent.
A skill for generating text-to-video with Wan 2.7, Wan-AI's flagship motion model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via custom audio tracks, smooth transition physics, prompt expansion control, and up to 1080p output at 15 seconds duration.
A Claude Code skill for generating text-to-video clips with HappyHorse 1.0 via the RunComfy CLI. HappyHorse 1.0 is currently ranked #1 on the Artificial Analysis Video Arena, producing native 1080p video with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for generating video with Kling 3.0 via the RunComfy CLI. Covers all six Kling 3.0 endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video), with native synchronized audio and multi-shot character consistency.
A Claude Code skill that generates custom OpenAI Codex Pets from a single reference image via the RunComfy CLI. It produces a Codex-compatible spritesheet (1536x1872, 8 columns x 9 rows) and pet.json manifest using GPT Image 2 and ImageMagick, without requiring Codex Pro or an OPENAI_API_KEY.
A Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.
A Claude Code skill that acts as a smart router for AI image generation and editing across 11+ models on the RunComfy platform. Supports text-to-image and image-to-image modes with models including FLUX 2, GPT Image 2, Seedream 5, Nano Banana 2, and more.