RunComfy Agent Skills
Run 29 AI generation models via Claude with the RunComfy CLI
What You Can Do
Access 29 production-ready Claude agent skills that wrap RunComfy's AI models for image generation, video creation, audio synthesis, and avatar videos. Skills include music generation (ACE Step with inpaint/outpaint), AI avatars and lip-sync (OmniHuman, Seedance, HappyHorse), image editing (inpainting, outpainting, face-swap, relight), video generation and extension, and upscaling. All skills are CLI-driven via the runcomfy command, with built-in schema validation, error handling, and examples for each model.
Features
ACE Step for tag-driven music composition, inpainting, and outpainting. Cost-effective alternative to ElevenLabs Music (27x cheaper at $0.0002/s), supports 50+ languages and structured lyrics with section markers.
Route across OmniHuman (audio-driven full-body), Wan 2-7 (with audio_url field), HappyHorse (in-pass audio), and Seedance v2 (multi-modal cinematic). Pick the right model for UGC, dubbed video, or styled characters.
Multiple image models including Flux 2, GPT Image 2, Nano Banana 2, and specialized editors for inpainting, outpainting, face-swap, and relight. Support for text-to-image, image-to-image, and style transfer workflows.
Generate videos from prompts or extend existing clips bidirectionally. Models like HappyHorse, Seedance, and specialized outpainting endpoints for seamless video composition and looping content.
Face-swap, relight, and character animation tools. Edit facial expressions, lighting, and emotions in both images and videos while maintaining identity and quality.
Skills intelligently route user intent to the optimal model. Whether generating music, creating avatars, or editing images, each skill picks the right endpoint with documented prompting patterns.
CLI-driven, repeatable workflows optimized for cost-sensitive batches. Set seeds for reproducibility, control durations and resolutions, and iterate cheaply before final rendering.
Each skill ships with detailed schema tables, prompting tips, common patterns, comparison matrices, and troubleshooting guides. 29 skills with 100% coverage of model capabilities.
Example Output
Generate lo-fi hip-hop with ACE Step
runcomfy run acestep-ai/ace-step/text-to-audio \
--input '{
"tags": "lo-fi hip-hop, mellow, vinyl crackle, rhodes piano, soft drums, 75 BPM",
"lyrics": "[inst]",
"duration": 90
}' \
--output-dir ./out
Generates a 90-second royalty-free lo-fi track with vinyl character at $0.018. Seed for reproducibility or randomize for variations.
Create a talking-head presenter video
runcomfy run bytedance/omnihuman/api \
--input '{
"image_url": "https://your-cdn.example/presenter.jpg",
"audio_url": "https://your-cdn.example/voiceover.mp3"
}' \
--output-dir ./out
Feed one portrait image and one voiceover MP3, get back a video where the subject speaks naturally with synchronized mouth and gestures.
Extend a music track bidirectionally
runcomfy run acestep-ai/ace-step/audio-outpaint \
--input '{
"audio": "https://your-cdn.example/hook-30s.mp3",
"tags": "indie pop, electric guitar, drums, build-up before chorus, fade outro",
"extend_before_duration": 30,
"extend_after_duration": 60
}' \
--output-dir ./out
Transform a 30-second hook into a 2-minute arrangement by adding intro and outro sections in a single call.
What's Included
- 29 Production-Ready Skills: Fully implemented Claude agent skills that wrap 15+ AI models, from music to avatars to image editing, each with validated schemas and error handling.
- RunComfy CLI Integration: All skills use the open-source `runcomfy` CLI as the execution layer, with auto-polling, file management, and transparent error reporting via standardized exit codes.
- Model-Specific Documentation: Each skill includes detailed schema tables, prompting tips, common patterns, and comparison matrices to help users pick the right endpoint and parameters.
- Reproduction & Iteration Support: Seed fields for deterministic output, duration/resolution controls, and cost estimates per call. Designed for batch workflows and cost-sensitive iteration.
- Security & Privacy Guidance: Token storage best practices, input boundary documentation, and mitigation strategies for third-party content and steganography risks.
- Troubleshooting & Error Codes: Standardized exit codes (0 success, 64 bad args, 65 schema mismatch, 69 upstream error, 75 retryable, 77 auth), with links to troubleshooting guides.
Who It's For
- AI Engineers & Developers
- Content Creators & Video Producers
- Product Teams Building AI Features
- Automation & Data Science Teams
- AI Research & Prototyping Teams
Best For
- Batch Content Generation
- Creative Automation Workflows
- Multi-Modal AI Pipelines
- Cost-Sensitive Prototyping
- Reproducible AI Workflows
You might also like
Elevate your interface design from strategy to pixel-perfect execution. Shape layouts and user flows before coding, critique designs against established heuristics, audit for accessibility and performance gaps, and polish for production. Enhance with purposeful animation, strategic color, harmonious spacing, and delightful moments. Includes comprehensive guidance for websites, dashboards, apps, components, forms, onboarding, and design systems across web and native platforms.
by pbakausPresent users with an adaptive 24-question personality assessment that uses Bayesian active learning to efficiently map their psychological profile. The skill automatically maps user responses (1-7 scales or natural language) to archetype classifications based on a 5-color psychological model, tracks probability distributions in real-time, and delivers detailed personality insights including core strengths, weaknesses, and top archetype matches.
Access Vercel's official collection of agent skills for building and deploying modern web applications. Optimize React component architecture using composition patterns to avoid boolean prop proliferation and build scalable component libraries. Deploy applications to Vercel with flexible workflows supporting git integration, CLI authentication, and multiple fallback methods. Apply React and Next.js performance guidelines from Vercel Engineering to write efficient code and improve Core Web Vitals.
The Lark CLI is the official command-line interface for Lark (飞书), packed with 35+ AI agent skills and 200+ commands. Automate workflows across your entire Lark workspace: manage approvals and attendance, develop custom applications with Miaoda, query and analyze multi-dimensional base tables, handle documents and sheets, schedule meetings, send messages, manage mail and tasks, and integrate with external APIs. Built for both humans and AI agents with comprehensive business domain coverage.
This is a comprehensive engineering workflow system designed to guide you from an initial idea all the way to shipped code. It includes a main flow (idea → grill → spec → tickets → implement → review → ship), specialized skills for handling bugs, triage, and large architectural challenges, and foundational vocabulary skills for domain modeling and codebase design. Each skill works independently or as part of the larger workflow, giving you flexibility to adapt to your project's needs.
Generate batches of proven viral hooks across named-creator frameworks (MrBeast, Hormozi, Brunson, Koe, Welsh, Bush, Galloway). Write and audit short-form scripts with platform-specific pacing. Optimize Instagram Reels for sends-per-reach using Trial Reels testing. Craft captions and CTAs that match video payoff. Diagnose why openings flop and rewrite weak hooks against anti-patterns. The skills encode what patterns tend to lift retention in the first 1 to 3 seconds, then repurpose across platforms.
RigorPilot is a comprehensive skill suite for deep learning research, providing auditable repository analysis, README-first reproducibility workflows, bounded exploration with evidence-based ranking, and publication-ready scientific documentation. Each skill enforces rigor through documented assumptions, comparability tracking, and explicit decision checkpoints. Use these skills to understand ML repository internals, faithfully reproduce published results, systematically explore novel ideas with proper baselines, and generate standardized research artifacts.
Design and build animations using a proven decision sequence covering when to animate, which tools to use (CSS, WAAPI, Motion.dev), property selection, easing curves, and accessibility. Review existing animations and audit codebases for quality issues. Understand and name motion effects using a comprehensive vocabulary glossary. Learn from Emil Kowalski's opinionated motion design philosophy built on decades of interface engineering experience.