Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and...
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than...
Execute the implementation planning workflow using the plan template to generate design artifacts.
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
Ask Google Gemini questions about code to understand implementations, architecture, patterns, and debugging. Use when the user asks how code works, where something is implemented, what patterns...
Perform comprehensive code reviews using Google Gemini CLI to identify bugs, security vulnerabilities, performance issues, and code quality problems. Use after code changes, before commits, during...
Execute development tasks using Google Gemini CLI for code generation, refactoring, and modifications. Use when the user needs to create code, add features, refactor, fix bugs, or generate tests....
Search the web using Google Gemini CLI with built-in Google Search grounding to find current documentation, best practices, solutions, and technical information. Use when the user needs to...
An AI Agent Engine built in Go. Features portable skills (SKILL.md), human-in-the-loop approvals, structured memory, and OpenAI-compatible tool calling. Single binary & Docker ready.
Use when creating, editing, evaluating, testing, or verifying ANY skill or skill-related file (SKILL.md, skill resources, skill scripts, or skill assets). If you're asked to evaluate or test a...
Generate feature specifications by analyzing existing source code.
Conducts a deep, multi-round interview to clarify ambiguous requirements and produces a structured specification document. Automatically discovers requirement files and asks probing, non-obvious...
Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.
Use when asked to show fetch the context of the current branch
Generate a custom checklist for the current feature based on user requirements.
This sop generates structured code task files from rough descriptions, ideas, or PDD implementation plans. It automatically detects the input type and creates properly formatted code task files...
Create or update a feature specification from a natural language feature description.
Use when writing tests for Ruby code in frameworks such as RSpec or Minitest.