ai-devkit
Control plane for managing multiple AI coding agents
All Skills in This Repository (25)
Pure Emerald Level Indicatorsmemory
Store and retrieve titled knowledge with tags and scope via CLI search.
dev-pr
Rebase, push, and open a code review request for a ready feature branch.
agent-management
Manages running AI coding agents through ai-devkit agent CLI commands.
brainstorm
Generates and evaluates ideas through a structured diverge-to-converge workflow.
changelog
Generate CHANGELOG.md Unreleased entries from git commits since the latest release.
verify
Enforces evidence-based completion claims by requiring fresh command output before reporting success.
dev-lifecycle
Orchestrates structured SDLC phase skills across requirements, design, planning, implementation, testing, and review.
dev-commit
Creates verified conventional git commits containing only intended changes.
structured-debug
Diagnose bugs through evidence-based reproduction, hypothesis testing, and validated fix plans.
dev-design
Reviews feature design documents against requirements and resolves architecture trade-offs.
document-code
Generates structured markdown documentation for code entry points with dependency mapping and mermaid diagrams.
dev-planning
Creates and reconciles feature implementation task plans within the AI DevKit dev-lifecycle workflow.
Frequently Asked Questions
FAQPage SchemaHow to install AI DevKit?โผ
Run `npx skills add codeaholicguy/ai-devkit --all -g -y` in your terminal to install all skills in this suite globally.
What problem does AI DevKit solve?โผ
It gives you one config, one console, and shared memory to manage multiple AI coding agents instead of juggling isolated terminal sessions.
Which AI coding agents does AI DevKit support?โผ
It works with Claude Code, Codex CLI, Gemini CLI, Cursor, opencode, GitHub Copilot, Devin, and other popular coding agents.
How does AI DevKit stop agents from claiming false completion?โผ
The verify skill blocks any completion claim until the agent runs fresh test or build commands and reports real output as evidence.
Can AI DevKit remember project conventions between sessions?โผ
Yes. It stores decisions, conventions, and fixes in a local SQLite memory that agents search only when relevant, avoiding context bloat.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core