AI Development Toolkit — Testing skill for Claude Code
Portable agent skills, QA workflows, specialist roles and tools for reliable AI-assisted development.
How to install AI Development Toolkit
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open MikeMoore1337/ai-development-toolkit and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AI Development Toolkit does
Portable agent skills, QA workflows, specialist roles and tools for reliable AI-assisted development.
Alternatives in Testing
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
- OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
- Cc Sdd — Spec-driven development (SDD) for your team's workflow 3.1k ★
README
[](docs/BEGINNER_START.md)
**English** · [Русский](README.ru.md)
[](https://github.com/MikeMoore1337/ai-development-toolkit/actions/workflows/validate.yml) · [Latest release](https://github.com/MikeMoore1337/ai-development-toolkit/releases/latest) · [Skills catalog](docs/SKILLS_CATALOG.md)
**[Start without a terminal](docs/BEGINNER_START.md)** · **[I have an existing project](docs/EXISTING_PROJECT.md)** · **[Local installation](#quick-start)** · **[Documentation](#documentation)**
**Already have a project?** Start with the [human-first guide](docs/EXISTING_PROJECT.md). The [coding agent contract](AGENT_START.md) is separate and is not required reading for a first request.
**Optional original [Graphify for local code navigation](docs/GRAPHIFY.md)** - opt-in, offline code-only, no runtime dependency.
**Toolkit integrations:** [ChatGPT plugin](integrations/chatgpt-plugin/README.md) · [Codex MCP](integrations/personal-mcp/README.md) · [Windows, Linux and macOS setup](docs/INTEGRATIONS.md) · [DeepSeek Chat](integrations/deepseek-chat/README.md) · [DeepSeek Harness](integrations/deepseek-harness/README.md)
**[Client choices, cost and permission boundaries](docs/CLIENT_ROUTE_SECURITY_MATRIX.md)** - what is actually tested, what requires consent, and how to keep personal settings private.
Start with the task
AI Development Toolkit is a **portable library of reusable instructions, specialized roles and QA workflows** for AI-assisted development. It is not a standalone coding agent, hosting service or permission to access your project.
| You want to… | Start here | What to expect |
|---|---|---|
| Describe an idea without using a terminal | Beginner guide | Five copy-ready requests and honest l |
Related Skills
Agent Roles Spec
Agent Roles is a host-neutral specification for packaging specialist AI agents as portable, mountable Roles.
Claude Webdev Skills
Stack-agnostic web development workflow skills for Claude Code — a portable branch → plan → test → commit → PR
Liminal Spec
Liminal Spec: spec-driven development methodology for AI-assisted coding. Claude Code skill.
Town Charter
A spec for AI-assisted multi-repo development workspaces
Vibe Setup
A small Bash CLI that bootstraps a project for AI-assisted development: seeds AGENTS.md/CLAUDE.md, a secrets-d
Salvage
Recover the real requirements from a project that went down a bad path and emit a portable spec to rebuild sim
Related Agents
A2a Advisor
Portable A2A v0.3.0 conformance checker for BOTH roles — server/provider (agent card, transports/methods, Task
OSpec CLI
Document-driven OSpec workflow for AI-assisted development with change-ready initialization, execution, valida
AI Optimization Architect
Use this agent when you need to optimize code libraries, frameworks, or systems for AI-assisted development wo