vstorm-co/pydantic-deepagents

Build And Compile helps detect build systems, compile code, and resolve missing dependencies across languages. Use it when builds fail, libraries are missing, or link errors need fixing.

Code Review reviews Python code for security, correctness, and best practices. Use it to assess structure, error handling, type hints, and documentation before merging changes.

Code Review performs a systematic review for correctness, security, performance, style, and testing gaps. Use it to inspect changed code and report concrete issues with suggested fixes.

Data Formats helps inspect and parse binary, text, structured, and custom files. Use it when a file type is unknown, mixed, or needs format-specific handling.

Diagram Design helps create research diagrams with Excalidraw MCP tools. Use it for comparisons, process flows, timelines, architectures, and other structured research findings.

Environment Discovery guides an agent to inspect files, tools, and data formats before making changes. Use it when dropped into an unfamiliar workspace or when file contents, build tools, or dependencies are unknown.

Git Workflow covers commit formatting, branching, pull requests, and conflict resolution. Use it when working through standard Git changes safely in a team setting.

Performant Code helps you write efficient code for large inputs and tight limits. Use it when you need to avoid timeouts, reduce memory use, or choose faster data access and algorithm patterns.

Refactor improves code structure without changing external behavior. Use it to extract helpers, simplify conditionals, rename unclear code, and reorganize modules while keeping tests passing.

Skill Creator generates a new SKILL.md from conversation context and task patterns. Use it when you want to turn a repeatable workflow into a reusable Claude Code skill with instructions, examples, and optional templates.

Systematic Debugging provides a step-by-step loop to reproduce, isolate, diagnose, fix, and verify bugs. Use it when code fails, gives wrong output, times out, or behaves differently across environments.

Test Generator generates pytest test cases for Python functions and classes. Use it to cover happy paths, edge cases, errors, and async code.

Test Writer generates comprehensive tests for existing code. Use it to read a codebase, match its test framework, and write coverage for happy paths, edge cases, errors, and integration behavior.

Verification Strategy helps you confirm a task is complete by checking requirements, file outputs, commands, and test expectations before marking work done. Use it when you need to validate code or generated artifacts against exact instructions.