Coding standards, frameworks, refactoring, and code review (16.3K skills)
Turn specifications and designs into working code using test-driven development: write failing tests, implement enough code to pass, then refactor. The workflow also covers error handling, performance improvements, documentation, and coordinated changes across components.
Create starter code and configurations for components, APIs, and projects using existing project conventions. Templates include relevant types, error handling, documentation, and testing scaffolds, with comments and extension points to guide customization.
Analyze slow development workflows and agent coordination using execution times, resource use, dependencies, and communication patterns. Identify bottlenecks, prioritize causes, and build an improvement plan covering parallel work, caching, or resource allocation.
Review a codebase for readability, performance, security, and architectural issues. The skill organizes findings into actionable recommendations, helping teams identify refactoring work, dependency risks, and areas that need better tests.
Organize complex work across specialized agents with claude-flow. Start and stop agents, check their status and metrics, and manage groups by role, using shared memory to coordinate tasks such as development, reviews, and security checks.
Coordinate multiple AI agents for feature development or refactoring across several files. The skill guides team setup, task assignment, status checks, and recording successful approaches for use in later work.
Manage GitHub pull requests from creation through review and merge. Using GitHub CLI, the skill prepares descriptions, coordinates reviewers, tracks automated checks, helps resolve conflicts, and selects merge approaches suited to the branch history.
Coordinate gossip protocols, where nodes pass information among peers, for distributed systems. The skill covers update propagation, state synchronization, conflicting changes, failure detection, and tuning communication so nodes eventually reach a consistent state.
Review source code for readability, complexity, duplication, and maintainability without changing files. Receive a structured report with prioritized issues, refactoring suggestions, positive findings, and estimates of technical debt—the work needed to address accumulated code problems.
Turn software development goals into manageable milestones with clear deliverables, dependencies, effort estimates, and success criteria. Use it to plan feature implementation, bug fixes, refactoring, performance improvements, and testing work.
Initialize a group of collaborating AI agents by choosing how they connect, allocating resources, and setting up communication. Establish shared-memory rules so agents record progress, share outputs, check dependencies, and signal completion.
Plan system architecture by comparing technical options, component relationships, and requirements such as performance, security, and growth. Produce architecture diagrams, data flow diagrams, decision records, and technology comparisons that explain the reasoning behind a proposed design.
Turn specifications and algorithm outlines into a system architecture. Define components, interfaces, data structures, and deployment plans, then document technology choices, security measures, failure handling, and plans for supporting increased usage.
Review GitHub pull requests with specialized AI agents that check security, performance, architecture, and coding conventions. Generate actionable comments with suggested fixes, and connect review findings to automated approval or change requests.
Coordinate groups of AI agents across multiple GitHub repositories. Analyze dependencies, organize shared updates and refactoring, run tests, and create linked pull requests so related projects can be changed together.
Create a Claude Code plugin scaffold with configuration, skills, commands, and agents. Generate supporting documentation, a record of architecture decisions, and a script that checks the plugin's structure, while connecting the required MCP tools.
Group related code files by analyzing a graph of their connections with ruvector. Review group assignments, community labels, and links between files to understand code organization and investigate files that stand apart.
Turn a feature idea into a structured specification before coding. Review requirements, system connections, constraints, and failure scenarios, define testable acceptance criteria, and save the specification in memory for later development phases.
Automatically repair source code against a failing test while preserving the test itself. Set a spending limit and attempt count, then receive verification results and usage costs based on rerunning the test command.
Build a Claude Code mod, a plugin that extends behavior through event hooks, from ruflo’s template. Sets up function hooks with a classic fallback, user options, status reporting, validation, and tests.
Develop features through a test-first workflow using mocks, or stand-ins for dependencies. Write a failing behavior test, implement the minimum code, refactor, and record observed results from final target and regression tests.
Automate GitHub tasks such as creating draft pull requests and inspecting automated checks. Confirms the target repository and branch before external changes, keeps actions within authorized scope, and reports the resulting URL or identifier.
Set up a coordinated team of three or more AI agents for development tasks spanning multiple files. Configure the team structure, assign specialized roles, and prepare parallel work with named agents and messaging.
Turn an approved specification into pseudocode, a plain outline of program logic, and an architecture defining module responsibilities and API inputs and outputs. After user confirmation, proceed with implementation and unit tests based on those designs.