Skills
Browse AI Coding Agent Skills
Find reusable skills for Claude Code, Codex, Cursor, opencode, Gemini CLI, and other coding agents. Start with the 31 built-in AI DevKit skills, or search 4,694 skills from public registries and copy the install command.
Built-in AI DevKit skills
Start with workflow, debugging, testing, review, memory, documentation, and multi-agent skills that ship with AI DevKit. Learn how skills work
npx ai-devkit@latest skill add --built-in- Recommended
Dev Lifecycle
Orchestrate requirements, design, planning, implementation, testing, and review. - Workflow
Dev Commit
Create safe, verified commits from only the intended changes. - Workflow
Dev Worktree
Set up or resume the right workspace before feature work. - Workflow
Brainstorm
Generate, challenge, and narrow ideas, from a simple baseline to three strong picks. - Workflow
Dev Requirements
Capture and review requirements before design or implementation. - Workflow
Dev Design
Validate architecture and design trade-offs against requirements. - Workflow
Dev Planning
Create and reconcile implementation plans from requirements and design. - Workflow
Dev Implementation
Execute planned implementation and check it against the approved design. - Workflow
Dev Testing
Add and validate test coverage for feature work. - Workflow
Dev Review
Run a final pre-push review across design, implementation, tests, and risk. - Workflow
Dev PR
Publish a reviewed feature branch for code review. - Workflow
Task
Record lifecycle and debugging progress on a durable task the next agent can pick up.
- Debugging
Structured Debug
Guide debugging with expected behavior, reproduction, root cause analysis, and validation. - Testing
TDD
Apply test-driven development by writing a failing test before production code. - Verification
Verify
Require fresh terminal evidence before an agent claims work is complete. - Verification
Retro
Turn friction from finished work into durable fixes, automation first. - Verification
Smoke Check
Map the flows a change affects and smoke-test them end to end in a sandbox. - Refactoring
Simplify Implementation
Analyze and simplify complex code paths for maintainability. - Refactoring
Refactor
Plan and run structural refactors that preserve behavior and public contracts. - Review
Security Review
Review code, skills, and prompts for vulnerabilities and insecure defaults.
- Memory
Memory
Use AI DevKit memory as a durable knowledge layer for reusable project context. - Memory
Session Compact
Turn a long or finished coding session into a structured handoff and resume prompt. - Documentation
Document Code
Document code entry points with structured analysis and dependency mapping. - Documentation
Technical Writer
Review and improve documentation for clarity, structure, and novice comprehension.
- Multi-agent
Agent Communication
Exchange information with active Codex, Claude Code, and other AI agents. - Multi-agent
Agent Management
List, start, inspect, and assign work to running AI coding agents. - Multi-agent
Agent Orchestration
Scan running agents, assess progress, and coordinate multi-agent workflows. - Remote
Remote From Slack
Connect the current agent session to an available Slack channel bridge. - Remote
Remote From Telegram
Connect the current agent session to an available Telegram channel bridge.
Search the Registry
Find skills by name, workflow, registry, or capability. Works with Claude Code, Codex, Cursor, opencode, Gemini CLI, GitHub Copilot, Cline, Devin, Kilo Code, and Roo Code.
Loading the registry…