Development skills

Analyses a git repository to map who owns security-sensitive code and computes the bus factor.

Writes a threat model grounded in the repository: trust boundaries, assets, attacker capabilities and mitigations.

Inspects Sentry issues and events and summarises recent production errors through the Sentry CLI, read-only.

Deploys applications and websites to Vercel, including preview deployments.

Bootstraps and develops WinUI 3 desktop applications with C# and the Windows App SDK.

Stages, commits, pushes and opens a GitHub pull request in one flow with the gh CLI.

Scaffolds a Codex plugin directory with its plugin.json and optional folders.

Guides the creation of Codex skills that add specialised knowledge, workflows or tool integrations.

Installs Codex skills from a curated list or a GitHub repo path.

Manages Cloud Run services, jobs and worker pools for HTTP apps, scheduled tasks and background processing.

Helps build AI applications with Genkit in Node.js and TypeScript: flows, tools, agents and fixes for common Genkit errors.

Covers Firebase CLI basics: installation, login, project creation and selection, and app config download.

Adds validation and guardrails to gcloud CLI operations across Google Cloud services, and trims their output.

Guides use of the Gemini API on Google Cloud's Agent Platform with the Google Gen AI SDK.

Generates a client service class for the Gemini Live API websocket endpoint in the language you choose.

Handles core GKE tasks: cluster provisioning, credentials, the Autopilot or Standard choice and workload deployment.

Uses the Hugging Face Hub CLI to download, upload and manage models, datasets, Spaces, buckets and jobs.

Builds Gradio web UIs and demos in Python: components, event listeners, layouts and chatbots.

Fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs, including GGUF conversion.

Helps select and run models locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA or ROCm.

Builds, deploys and maintains apps on Hugging Face Spaces with the Gradio, Docker or Static SDKs.

Trains and fine-tunes vision models for object detection, image classification and SAM segmentation.

Runs machine learning models directly in JavaScript and TypeScript with Transformers.js, for text, vision and audio tasks.

Builds, debugs and reviews TypeScript MCP servers and MCP Apps with mcp-use: tools, resources, prompts and authentication.