Coding standards, frameworks, refactoring, and code review (17.8K skills)
Build and update Mastra application interfaces using existing components from @mastra/playground-ui. Follow shared visual styles, arrange layouts with Tailwind utilities, and connect themes and stylesheets while avoiding duplicated components or unsupported appearance overrides.
Investigate difficult bugs by adding temporary logs to the actual execution path and reproducing the reported behavior. Analyze JSONL logs, which store one structured event per line, then fix the cause, verify regression tests, and remove debugging artifacts.
Re-review a GitLab merge request after new commits, track the outcome of every previous finding, and inspect both new changes and the full proposal. Verify the current code, then publish a test report and review verdict.
Design instructions for agents that write, fix, review, or refactor code. Define behavior based on file access, select suitable tools, and set clear verification and completion rules for repository changes or copyable code output.
Write, review, and refactor styles using Tailwind CSS v4 conventions. Consult guidance on CSS configuration, renamed classes, built-in styling features, and behavior changes when updating older v3 code or creating new styles.
Coordinate multiple Mastra Code workers to investigate and fix GitHub issues in parallel. Keep each issue in a separate working directory, track progress in reports, review changes, and manage pull requests, reviewer feedback, and automated checks.
Reviews pull requests for bugs, error handling, code quality, and style consistency. Organizes feedback into an overview, must-fix issues with file locations, improvement suggestions, and positive notes so reviewers can distinguish urgent problems from refinements.
Turn a development goal into a focused ralph-loop command through conversation and codebase research. Define context, setup steps, ordered tasks, and testing criteria, then produce a complete command ready to copy.
Review a pull request in a Factory work session by investigating its purpose, history, implementation, tests, and security. Publish verification results and a review verdict, then record the outcome on the work card.
Combine code from local directories or GitHub into one structured file for AI analysis. Examine project structure, search for related code, and check estimated tokens, the units AI models use to process text.
Develop and maintain the WXT browser extension that adds a Repomix button to GitHub repository pages. The skill covers Chrome, Firefox, and Edge compatibility, extension scripts, translation files, and commands for building, linting, and testing.
Write Git commit messages that preserve why changes were made. The skill keeps Conventional Commits subject lines and adds structured body entries for user intent, decisions, rejected alternatives, constraints, and lessons supported by the session context.
Explore local or remote repositories with Repomix CLI to understand their structure, locate related code across files, and review file counts and estimated tokens, the units AI models use to process text.
Configure Crush with Bash or JSON files to choose AI providers and models, connect external tools, set permissions, and adjust behavior. Understand how project and global settings combine when customizing your working environment.
Add or edit skills bundled with Crush, following guidance on file placement, required metadata, compile-time embedding, and discovery tests. It also explains how built-in skills are loaded and how user skills override them.
Extract fields, filter records, and reshape JSON from API responses, configuration files, or logs using Crush’s built-in jq. Get help writing and debugging transformations, constructing new JSON, and formatting output for other commands.
Add or modify commands handled inside Crush's embedded shell before they reach the operating system. The guidance covers command routing, input and output streams, exit codes, and cancellation so commands work with pipes, redirection, and hook timeouts.
Create, configure, and troubleshoot Crush hooks, commands that run before tool execution. Use them to block or approve calls, rewrite tool input, or add context for the agent, with guidance on configuration and troubleshooting.
Turn recurring lessons in Claude's automatic memory into concise project rules. Choose a project-wide, file-specific, or personal rule location, include concrete commands, and clean up the original memory entry after confirmation.
Turns recurring workflows and proven debugging solutions into reusable skill packages. It creates SKILL.md, a readable overview, and optional supporting examples from a user description or saved project memory, with checks for completeness and portability.
Generate a starting project for a subscription web app with Next.js, including sign-in, database schemas, billing routes, and a dashboard. The workflow also covers staged validation and reference documents for customization and common setup problems.
Turn a written app specification into a runnable starter project using the requested technology stack. Generate implemented features, tests, configuration files, and setup instructions, then check the project for common omissions.
Track code changes in structured JSON records, including reasons, test results, progress, and approvals. Save remaining tasks and key decisions so another AI session can understand the work and continue from the recorded handoff.
Turn plain language requirements into SQL, investigate slow queries, document database structures, and prepare migration templates with rollback plans. Support everyday database development and ORM use, where libraries connect application code to database tables.