Coding standards, frameworks, refactoring, and code review (15.7K skills)
Prepare to work on an unfamiliar project by reading every source file in full. Large files are read in chunks, building a shared understanding of the codebase before development begins.
Create a phased implementation plan for a feature or complex development task. It investigates documentation and existing examples, identifies supported APIs, and records concrete tasks, references, and verification checks for each phase.
Carry out a phased implementation plan with subagents assigned to implementation, verification, pattern checks, and code review. Each phase must pass verification before changes are committed and pushed, with context prepared for the next phase.
Monitor a pull request through reviews and automated checks, verify reported issues against the code, and make focused fixes. Repeat testing and review checks until actionable comments and unresolved threads are cleared and the request is ready to merge.
Set up claude-mem in Cursor with a local or remote worker, the process that runs its work. Follow configuration steps for remote inference through cmem.ai or a local observer using the host's login.
Explore code through structural search: find functions and classes, view file outlines, and open only the implementations you need. It uses tree-sitter, a parser that identifies code structure, to limit how much source text is loaded.
Map a codebase into feature flowcharts, find duplicated logic, and propose a simpler shared architecture. Produce source-linked diagrams, an evidence-based duplication report, and prompts for handing each proposed system to /make-plan.
Organize a GitHub issue backlog by shared root cause, with one main tracking issue and design document per group. Route new reports into existing plans and prepare pull requests that address related bugs together with regression checks.
Build a narrative project history from records stored in claude-mem. The report traces architectural changes, breakthroughs, debugging efforts, and work patterns, with timeline statistics and estimates of token savings from reusing recorded knowledge.
Manage Orca worktrees, separate working directories, along with terminals, repositories, and its embedded browser through the CLI. Use it to hand work to another agent, manage artifacts, run automations, and share skills within Orca.
Collect pull requests between Ant Design versions and turn user-facing changes into Chinese and English changelog drafts. Filter internal changes, highlight release priorities, add contributor links, and update both changelog files after preview confirmation and format checks.
Review Ant Design GitHub issues and prepare responses, labels, and closure recommendations. It distinguishes bugs from feature requests, checks bot answers, and presents a complete plan for approval before making changes.
Write a single-line commit message for Ant Design by reading staged changes, the changes selected for the next commit. It summarizes the full commit intent and follows the style of recent repository commits.
Look up Ant Design React components in official documentation to find available settings, default values, and usage examples. Check subcomponents and methods, and consult type definitions in the antd package when TypeScript details are needed.
Update Ant Design projects, mainly from v4 to v5, by reviewing changed component APIs, replacing removed features, and migrating theme settings. The skill also guides use of the official tool for automated code changes.
Prepare Ant Design pull requests from all changes on a branch. It uses official templates, drafts an English title and a Chinese or English body, and asks for approval before creating the pull request.
Improve an AI agent's harness, the software that organizes its work, while keeping the model fixed. Test changes in a sandbox, measure their results, and retain variants that pass tests and demonstrate improvement.
Turn a feature request into a minimal implementation plan before coding. Identify which files need changes, explain why, define the smallest required interface, and flag broader effects or expanded permissions for the implementer.
Start using RuView by choosing a Docker demo, a source build, or a live ESP32 setup. The skill guides the next concrete step, distinguishing sample data playback from sensing an actual room with WiFi signals.
Set up radar sensing for contactless heart rate, breathing rate, presence, and distance measurements. It covers supported hardware, firmware, and combining radar with WiFi CSI, sensing data derived from wireless signals, for shared readings and 3D views.
Connect RuView sensing data to AI agents through tools for presence, breathing, and heart rate. Explore agent coordination and prototype storing agent state and decisions alongside sensing data in a shared RVF container.
Restructure claude-flow v3 into focused modules using Domain-Driven Design, which groups code by responsibility. Define module boundaries, event communication, and plugin interfaces to support a modular architecture with independently testable business logic.
Improve the MCP server that connects claude-flow v3 to tools. It guides connection reuse, faster tool lookup, request distribution, and communication changes, with monitoring to evaluate response times, errors, memory use, and cache performance.
Work with AI as a coding partner, choosing who writes code and who guides the work. Supports role switching, test generation, ongoing code review, debugging, and step-by-step explanations for learning.