Coding standards, frameworks, refactoring, and code review (15.8K skills)
Investigate code errors through a structured process using reproduction steps, logs, and testable explanations. The workflow guides fault isolation, fixes, and follow-up checks, with common error patterns for Python, JavaScript/TypeScript, and Bash/Zsh.
Add datasets, models, and other components to machine learning projects using consistent registration and creation patterns. The skill guides file placement, configuration, and automatic module loading so new components fit the project's established architecture.
Build chat bots for multiple platforms using shared TypeScript logic with Chat SDK. The skill guides message handling, interactive cards, webhook connections, streamed AI replies, and adapters that connect platforms or store conversation state.
Build workflows with Vercel's Workflow DevKit that preserve progress and resume after restarts. Structure operations as persistent steps, wait for external events, retry temporary failures, and inspect runs to understand how a process is progressing.
Plan complex coding changes by exploring existing code, clarifying requirements, and tracing effects across the system. Produce a PLAN.md with recommended changes, affected files, and verification steps, then implement after the user approves.
Removes hosted demo restrictions from an Open Harness fork, including session and message caps and deletion blocks. Cleans up related helpers and tests while preserving unrelated authentication, session ownership checks, and sandbox behavior.
Write, review, and refactor React and Next.js code using Vercel's performance guidelines. Apply prioritized rules to reduce sequential data fetching, shrink downloaded code, improve server processing, and avoid unnecessary updates to the interface.
Review uncommitted changes, commits, branch differences, or pull requests in context. Identify bugs and concrete security weaknesses, explain when each issue occurs and how serious it is, and provide actionable feedback grounded in the surrounding code.
Build and review Tailwind CSS interfaces against consistent rules for typography, accessibility, layout, and animation. Get specific code fixes for violations, including keyboard interactions, loading states, error placement, and motion timing.
Prepare coding tasks for delegation to an authorized agent’s AI command-line tool. Set up and synchronize the workspace, write precise change requests, then review returned changes and run relevant checks before reporting completion.
Run AI coding command-line tools on behalf of worker agents using their prepared prompts and workspaces. Detect available tools, configure delegation, return results, and apply supported execution controls such as time budgets and permission settings.
Discover and call configured MCP server tools through the mcporter command line. Inspect the inputs each tool accepts, invoke external services, and create SKILL.md reference guides with usage examples for newly added servers.
Delegate Git operations to a Manager when a worker lacks credentials. The skill explains how to prepare command requests, receive results, and synchronize shared files, covering repository downloads, branches, commits, pushes, and other Git tasks.
Let a Manager carry out Git operations for Workers that lack credentials. Structured requests specify the workspace and commands, while the workflow covers shared-file synchronization, processing markers to prevent conflicting edits, and success or failure reports.
Call tools on configured MCP servers, which connect agents to external services, through the mcporter CLI. Inspect available tools and their inputs, retrieve API information, and check connections before deciding how to proceed.
Coordinate changes to shared task folders with .processing marker files that indicate ongoing work. Managers and Workers check these markers before editing, synchronize files through MinIO, and remove markers after completing their changes.
Manage GitHub pull requests, which propose code changes, and issues through a central MCP server. Create and update records, add comments, request reviewers, check changed files and automated checks, and merge pull requests.
Search GitHub, Stack Overflow, Hacker News, and HuggingFace for code examples, projects, technical answers, discussions, models, datasets, and Spaces. Filter supported searches and receive structured JSON results containing titles, links, and snippets.
Review a branch's commits, combine adjacent changes that belong together, and improve commit messages. A rebuilt history is prepared separately and replaces the original branch only after the user reviews and confirms the proposed changes.
Commit and push local changes, then create a pull request or update an existing one based on the branch state. The skill prepares commit messages and new pull request details from the changes being submitted.
Review local branches, pull requests, commits, or files and address issues. The skill selects a single-agent or multi-agent workflow based on the environment, with automatic fixes for lower-risk issues and confirmation for high-risk changes.
Commit local changes to the current Git branch with a message based on the project's conventions. When staged and unstaged changes coexist, choose which to include. The skill does not push changes or create pull requests.
Diagnose why the dotnet-msbuild binlog MCP server will not start or connect. Check the selected SDK, package sources, and launch logs, then identify a recovery that respects organizational policies and verify that the host discovers the server’s tools.
Use the new Process APIs in .NET 11 applications to run external commands, capture output and errors, and manage child processes. Guidance covers waiting for completion, reading output, and controlling whether processes survive their parent.