AI Agents for Coding, Review, and Debugging
This collection is built for developers who want agent skills that improve day-to-day coding work: writing code, reviewing changes, debugging failures, improving tests, and tightening release workflows.
Search intent
Curated skills
GEO summary
Recommended skills for ai agents for coding
This list is selected from active public skills using category, platform, and workflow relevance signals.
raycast-extension-docs
Guidance for building, debugging, and publishing Raycast extensions using the Raycast documentation set. Use when Codex needs to create or modify Raycast extensions (React/TypeScript/Node), consult Raycast API reference or UI components, build AI extensions, handle manifest/lifecycle/preferences, troubleshoot issues, or prepare/publish extensions to the Raycast Store or Teams.
opentui
Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.
maestro
Intelligent skill knowledge gateway. Routes tasks to the right knowledge without loading all skills into context. MUST be consulted before any coding task — call the search_skills MCP tool to retrieve relevant expertise from 100+ indexed skills covering Swift, SwiftUI, concurrency, testing, architecture, performance, and security.
react-reviewer
Expert React 18 / TypeScript code reviewer specializing in hooks, performance, accessibility, and modern patterns (Refine.dev, Ant Design, React Query). Use for all React/TSX code changes. MUST BE USED for React projects.
core-dev
Use when any coding, development, analysis, debugging, or code-related task is detected. Triggers on: implementing features, fixing bugs, refactoring code, reviewing diffs, investigating errors, evaluating approaches, or making architecture decisions.
VibeCollab — Setup Instructions for AI Assistants
You are helping a user set up VibeCollab in their project.
python-code-review
Python code review guidelines (security, performance, bugs, style). Auto-loads when reviewing Python code or analyzing code quality.
typescript-style
TypeScript coding style enforcement (ESLint, type safety, React patterns). Auto-loads when writing or reviewing TypeScript/JavaScript code.
typescript-code-review
TypeScript and React code review guidelines (type safety, React patterns, performance). Auto-loads when reviewing TypeScript/React code.
Why ai agents for coding matter
Context for who these skills help, what they unlock, and why this slice of the directory deserves its own landing page.
Coding skills tend to be strongest when they combine repository context, guardrails, and a clear execution loop. That makes them useful for engineers, technical leads, and AI-assisted development environments.
Many of the best skills here are not only for code generation. They also help with refactoring, CI checks, code review discipline, issue triage, and architecture hygiene.
How to choose the right skill
Use these rules to narrow your shortlist before you start installing or adapting a workflow.
- Pick skills based on your current workflow stage: implementation, debugging, testing, or review.
- If your team uses a specific editor or coding agent, prioritize matching platform support first.
- Use cross-tool skills when you want the same workflow available across several agent environments.
Related categories
Use the taxonomy pages when you want wider coverage beyond this curated guide.
Coding & Development
Code review, refactoring, testing, and debugging skills.
DevOps & Infrastructure
CI/CD, deployment, Docker, Kubernetes, and cloud infrastructure.
Security
Security advisories, vulnerability triage, and hardening.
Workflow & Productivity
Git, PRs, releases, task automation, and daily workflows.
FAQ
Short answers to common questions about this set of AI agent skills.
Are these only for generating code?
No. Many of the strongest coding skills support debugging, test writing, code review, linting, refactors, and repository operations.
Which platforms are represented?
The selection favors skills that work with Claude Code, Cursor, Codex, and cross-tool agent setups.