claude-toolbox
Structured design, implementation, review, and testing workflows
All Skills in This Repository (14)
Pure Emerald Level Indicatorstest-skill
Register and validate skill discovery and activation in the plugin system.
design
Convert raw ideas into design briefs and implementation plans.
merge-docs
Consolidate design and implementation docs into a unified specification with a prioritized task list.
test
Automate code change testing with profile-aware validators and validated contexts.
review-spec
Validate code against design and implementation docs to surface spec deviations.
review-code
Review current git changes for SOLID violations, security risks, and maintainability concerns.
diff-skill
Diff reachable Markdown files from SKILL.md between git refs and report degradations.
review-design
Review design and implementation documents for quality and technical soundness.
document
Generate rubric-driven documentation for software features, bug fixes, and design changes.
chain-of-verification
Generate initial answers and verify claims through structured verification questions.
dependency-handling
Enforce a lookup-before-use workflow for adding or upgrading dependencies.
implement
Automate end-to-end task implementation workflows with verification and review checkpoints.
Frequently Asked Questions
FAQPage SchemaHow to install claude-toolbox?โผ
Run `npx skills add serpro69/claude-toolbox --all -g -y` in your terminal to install all skills in this collection globally.
What does claude-toolbox do?โผ
It provides a structured development pipeline of 11 workflow skills covering design, implementation, code review, spec verification, testing, and documentation, plus pre-configured settings and MCP servers.
Does claude-toolbox work with Codex and Claude Code?โผ
Yes. It ships dedicated configurations for both providers, and a built-in generator automatically converts the skills and sub-agents for Codex.
Which programming languages are supported?โผ
It includes dedicated profiles with tailored design, implementation, testing, and review guidance for Go, Java, JavaScript/TypeScript, Kotlin, Kubernetes, and Python.
How does it keep code reviews unbiased?โผ
Isolated review modes spawn independent sub-agents and external models that never saw the code being written, removing authorship bias from the review.
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