Loading...
Loading...
Found 359 Skills
Multi-perspective code analysis using three AI personas (RYAN, FLASH, SOCRATES) for comprehensive decision-making. Use when complex code decisions need analysis from multiple viewpoints, or when avoiding single-perspective blind spots is critical.
Check if the code you just wrote follows the frontend development guidelines.
Use the Claude Code CLI to consult Claude and delegate coding tasks for prototyping, debugging, and code review. Supports multi-turn sessions via SESSION_ID. Optimized for low-token, file/line-based handoff.
Designs intuitive Python library APIs following principles of simplicity, consistency, and discoverability. Handles API evolution, deprecation, breaking changes, and error handling. Use when designing new library APIs, reviewing existing APIs for improvements, or managing API versioning and deprecations.
Manage git worktrees for efficient multi-branch development. Use when you need to create worktrees for feature branches, organize worktree directories, clean up unused worktrees, or implement worktree-based workflows.
Core code quality principles for writing maintainable code. Use when reviewing code for design violations, assessing code quality, or applying architectural patterns like composition, immutability, and fail-fast.
Use when implementing well-scoped Python tasks with clear requirements, writing unit tests, and producing documented code for senior-developer review.
Manage Azure Repos including branches, pull requests, and code reviews. Use when working with Azure Repos or managing repository operations.
Build verification, error recovery, and application of review fixes. Use this when the user mentions build verification, error recovery, applying review fixes, test failures, lint errors, or CI breaks. Do NOT load this for: implementation work, reviews, setup, or new feature development.
Vibe Kanban orchestration platform for AI coding agents: workspaces, sessions, task management, code review, git worktrees, multi-agent support. Keywords: Vibe Kanban, AI agents, Claude Code, Codex, Gemini, kanban board, git worktree, code review, MCP server, workspaces, sessions.
Use when writing any code - enforces clean architecture with descriptive names, real implementations, no backward compatibility concerns, and no lint suppressions
Respond to PR review comments with critical evaluation. Use when addressing code review feedback, responding to bot review comments (Gemini Code Assist, CodeRabbit, etc.), or handling PR suggestions. Fetches comments, evaluates each against project context, applies valid fixes, declines invalid suggestions with reasoning, and posts responses.