Skills

A collection of SDK and agent tools from the inference.sh skills ecosystem, providing AI agents with utility capabilities for interacting with 250+ models across image generation, video creation, LLMs, and web search.

A skill for setting up and using the inference.sh CLI (belt), which provides access to 250+ AI models for image generation, video creation, LLM calls, and web search through a unified command-line interface.

An agent skill from Matt Pocock's engineering toolkit that helps improve your codebase architecture. Part of a composable skill set designed to fix common AI coding agent failure modes through structured, experience-based workflows.

Assesses and automates upgrades of Azure workloads between plans, tiers, or SKUs. Handles plan/tier upgrades (e.g., Consumption to Flex Consumption), cross-service migrations (e.g., App Service to Container Apps), and SKU changes with phased assessment reports and idempotent scripts.

A skill that runs a grilling session to challenge your plan against an existing domain model, sharpen terminology by building a shared language in CONTEXT.md, and document architectural decisions in ADRs before coding begins.

Enforces test-driven development with a strict red-green-refactor loop using vertical slices (one test then one implementation at a time), emphasizing behavior verification through public interfaces rather than implementation-coupled testing.

A smart intent-routing skill for video editing on RunComfy that selects the best model based on the user's intent. Routes to Wan 2.7 Edit-Video for restyle and background swaps, Kling 2.6 Pro for precise motion transfer, or Lucy Edit for lightweight identity-stable restyle and outfit swaps.

A smart intent-routing skill for image-to-video generation on RunComfy that automatically selects the best model for the task. Routes to HappyHorse 1.0 I2V for general animations, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition from image, video, and audio references.

A smart intent-routing skill for image editing on RunComfy that selects the best model based on the editing task. Routes to Nano Banana Edit for batch edits up to 20 images, GPT Image 2 for multilingual text rewrite, Flux Kontext Pro for single-shot precise edits, or Z-Image Turbo for mask-driven inpainting.

Edit images with Black Forest Labs' Flux 1 Kontext Pro on RunComfy, specializing in single-reference precise local edits with high-fidelity source preservation. Ideal for targeted changes like adding objects or modifying details while keeping the rest of the image unchanged.

A RunComfy skill that generates images using Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family. Optimized for rapid iteration, social thumbnails, and in-image typography with configurable resolution tiers and safety tolerance.

A Claude Code skill that lets you share local folders, files, artifacts, logs, and project workspaces with humans or other agents via shareable links using the agentspace.so CLI.

Postgres performance optimization skill from Supabase with best practice rules across 8 categories. Includes query performance, connection management, RLS patterns, and schema design with SQL examples and EXPLAIN analysis.

Skill for the Lark/Feishu CLI that manages email including browsing, searching, reading, sending, replying, forwarding, and draft management.

Skill for the Lark/Feishu CLI that searches users by name, email, or phone and retrieves user profiles from the Lark platform.

Skill for the Lark/Feishu CLI that lets you explore and discover Lark's underlying APIs from the official documentation.

Lets AI agents take the SoulTrace personality test on behalf of users — 24 Likert-scale questions mapped to one of 25 archetypes in a 5-color psychological model using Bayesian active learning.

Skill for the Lark/Feishu CLI that provides a custom skill creation framework for building new Lark agent skills.

Architects and provisions enterprise Azure infrastructure from workload descriptions, generating Bicep or Terraform templates with WAF alignment. Covers networking, identity, security, compliance, and multi-resource topologies including landing zones, hub-spoke networks, and multi-region DR.

Generates structured, creative problem-solving frameworks with step-by-step ideation techniques, prioritization, and actionable innovation strategies.

A skill that turns the current conversation context and codebase understanding into a structured PRD (Product Requirements Document) and submits it as a GitHub issue, with modular architecture and user story generation.

Plans, creates, and configures production-ready Azure Kubernetes Service (AKS) clusters with a focus on Day-0 decisions that are hard to change later. Covers SKU selection, networking options, API server access, identity, security, and node pool configuration.

Comprehensive design intelligence skill with 50+ styles, 97 color palettes, 57 font pairings, and 99 UX guidelines across 9 tech stacks. Includes a CLI tool that generates complete design systems with reasoning-based recommendations.

Provides documentation-grounded guidance for writing, migrating, securing, and troubleshooting GitHub Actions workflows.

Edit images with Google Nano Banana 2 on RunComfy, supporting batch edits of up to 20 images per call with strong identity preservation. Features localized edits using spatial language, background swaps, and configurable resolution up to 4K.

Generate text-to-video with HappyHorse 1.0 on RunComfy, currently ranked #1 on Artificial Analysis Video Arena. Supports native 1080p with in-pass synchronized audio, multi-shot character consistency, and 6-language prompt support via the RunComfy CLI.

Generate text-to-video with Wan-AI's Wan 2.7 on RunComfy, featuring multi-reference conditioning and audio-driven lip-sync via custom audio tracks. Supports prompt expansion, negative prompts, and up to 1080p resolution through the RunComfy CLI.

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy, supporting multi-modal references including up to 9 images, 3 videos, and 3 audio tracks. Features native lip-synced audio generation and is ideal for brand-consistent multi-language narratives.

Edit images with OpenAI GPT Image 2 on RunComfy, excelling at multilingual in-image text editing across any script (Latin, kana, CJK, Cyrillic, Arabic) and multi-reference composition with up to 10 input images. Ideal for identity-preserving edits and layout-precise repositioning.

React composition patterns skill from Vercel Labs that helps avoid boolean prop proliferation through compound components, state lifting, and internal composition techniques.