Skills

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 that upgrades AI-generated frontend code quality with 3 control dials for design variance, motion intensity, and visual density, preventing generic "slop" aesthetics.

The foundation skill for the RunComfy platform, providing a single CLI to install, authenticate, and invoke hundreds of model endpoints including image generation, video, face-swap, lip-sync, and LoRA training.

A Claude Code skill for swapping faces in images and videos via RunComfy CLI, routing across multiple model endpoints including Wan 2-2 Animate, GPT Image 2 Edit, Flux Kontext, and Kling Motion Control based on use case.

CLI tool for the Hyperframes video rendering framework that provides commands to create, preview, lint, and render HTML-based video compositions to MP4.

A Claude Code skill for mask-driven image inpainting via the RunComfy CLI, enabling object removal, watermark cleanup, and region replacement by routing to Z-Image Turbo Inpainting and instruction-driven edit models.

A model-invoked productivity skill that interviews users relentlessly about a plan or design until every branch of the decision tree is resolved. It serves as the reusable interview loop behind the grill-me and grill-with-docs skills.

A Claude Code skill for lip-syncing faces to audio tracks using RunComfy CLI, routing across OmniHuman, Sync Labs, Kling lipsync, and Creatify endpoints for portrait-to-avatar or video mouth-sync workflows.

A Claude Code skill for extending images beyond their original canvas via the RunComfy CLI, supporting uncropping, aspect ratio changes, and canvas expansion by routing to Nano Banana 2 Edit, GPT Image 2 Edit, and FLUX Kontext Pro endpoints.

A Claude Code skill that changes the lighting of still images—adjusting direction, color temperature, intensity, and mood—via the RunComfy CLI, routing to Qwen Edit 2509's dedicated relight LoRA and identity-preserving edit endpoints.

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

Skill for authoring HTML-based video compositions with the Hyperframes framework, covering captions, TTS, audio-reactive animation, and transitions for AI agent-driven video creation.

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.

Unified Azure cost-management skill: queries historical costs, forecasts future spending, and optimizes resources across subscriptions, resource groups, and tags to reduce waste.

A smart music generation router for RunComfy that picks the right model based on your intent, supporting ElevenLabs (premium vocal tracks) and ACE Step (open-weights, ~27x cheaper), with inpainting and outpainting for editing existing tracks.

Generates, inpaints, and outpaints music using StepFun-AI's open-weights ACE Step model via the RunComfy CLI, with tag-driven composition, multilingual lyrics, and four endpoints at $0.0002-0.0003 per second of audio.

Composable, model-agnostic agent skills for real engineering workflows, featuring /grill-me for requirement alignment, /prototype for rapid iteration, and task management tools designed to fix common failure modes in AI coding agents.

A model-invoked engineering skill that actively builds and sharpens a project's domain model by challenging terms against the glossary, stress-testing with edge-case scenarios, and updating CONTEXT.md and ADRs inline.

A minimal Claude Code skill template providing a clean, stripped-down starting point for building custom skills without unnecessary complexity.

Hardens self-hosted OpenClaw deployments on Linux cloud servers with a 'deploy first, expose later' pattern — Podman, loopback binding, SSH tunneling or Tailscale, and token auth.

Walks through turning a cloud Linux server into a safely exposed web host — DNS, SSH hardening, firewalls, Nginx for static sites or reverse-proxied apps, HTTPS with Let's Encrypt, and optional BBR tuning.

Translates a repository's README into localized sibling files (e.g., `README.zh.md`), preserves GitHub-flavored Markdown and repo-specific tokens, and wires a shared language selector across all variants.

Skill for installing blocks and components into Hyperframes projects via the `hyperframes add` command, providing access to 50+ ready-to-use overlays, shader transitions, and data visualizations.

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

Drives the `tzst` CLI for `.tzst` / `.tar.zst` archives — creating, extracting, flattening, listing, and testing archives with compression levels, streaming mode, extraction filters, and JSON output.

A model-invoked engineering skill that provides shared discipline and vocabulary for designing deep modules: maximizing behavior behind small interfaces, placing code at clean seams, and ensuring testability through public APIs.

A model-invoked skill that guides coding agents through a disciplined diagnosis loop for hard bugs: reproduce, minimise, hypothesise, instrument, fix, and regression-test.

A reference skill that teaches the vocabulary and principles for writing predictable, well-structured agent skills. Part of Matt Pocock's "Skills For Real Engineers" collection.

Integrates Xget URL rewriting into Git, download tools, package managers, container builds, AI SDKs, and CI/CD pipelines to accelerate registry, package, container, and API downloads.

Uploads files to and downloads from an Xdrop server via the terminal, producing encrypted share links and decrypting them locally through bundled upload/download scripts.