Agent skills for Devin Desktop

Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.

LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, or streaming with…

Demonstrate unbounded resource consumption against an LLM application — token floods, unbounded output, and cost/denial-of-wallet…

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests…

Analyzes and generates llms.txt files -- the emerging standard for helping AI systems understand website structure and content.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag).

Extracts procedural content from project docs into slash commands.

Reviews skills (D1-D11 + M1-M6 criteria) or .claude/commands for quality.

Bootstraps projects to production-ready structure.

Upgrades npm/yarn/pnpm dependencies with breaking change handling

Coordinates project structure migration to Clean Architecture

Scaffolds new React projects or restructures monoliths to component-based architecture.

Migrates mock data from Drizzle ORM schemas to C# MockData classes

Universal platform artifact cleaner: Replit, StackBlitz, CodeSandbox, Glitch

Sets up Docker, CI/CD, and environment configuration with auto-detection.

Configures environment variables and secrets protection.

Configures Husky, lint-staged, commitlint, and Python pre-commit hooks.

Sets up logging, error handling, CORS, health checks, and API docs.

Configures structured JSON logging with Serilog (.NET) or structlog (Python).

Configures global exception handling middleware.

Configures CORS policy for development and production environments.