han
Quality gates, validation hooks, and plugins for coding agents
All Skills in This Repository (150)
Pure Emerald Level Indicatorsdebugging
Diagnose software bugs through evidence collection and hypothesis testing.
explainer
Explain code and technical concepts with audience-adaptive structured formats.
refactoring
Refactor code incrementally with tests and isolated commits.
documentation
Generate structured documentation with code examples and parameter specifications.
proof-of-work
Require command outputs and file changes as evidence for code quality claims.
code-reviewer
Evaluate code diffs across correctness, safety, maintainability, testability, performance, and standards.
boy-scout-rule
Improve code quality while editing files without changing behavior.
project-memory
Organize Claude Code project memory into a CLAUDE.md with modular rules and path-specific globs.
legacy-code-safety
Add characterization tests before refactoring untested legacy code.
solid-principles
Apply SOLID design principles to Elixir and TypeScript modules.
simplicity-principles
Enforce KISS, YAGNI, and Least Astonishment principles during software design and refactoring.
architecture-design
Map business goals to high-level system structure and technology choices.
Frequently Asked Questions
FAQPage SchemaHow to install Han?โผ
Run `npx skills add TheBushidoCollective/han --all -g -y` in your terminal to install all plugins in this suite globally.
What does Han do for AI-generated code?โผ
Han runs validation hooks automatically when your coding session ends, checking linters, formatters, type checkers, and tests so the code is ready to merge.
Does Han work with my programming language?โผ
Yes. Han offers plugins for TypeScript, Python, Rust, Go, Ruby, Elixir, and more, and the auto-detect flag picks the right plugins for your stack.
Which AI coding tools does Han support?โผ
Han works with Claude Code and includes bridge plugins for OpenCode, Gemini CLI, Kiro, and Codex, with hooks and MCP servers shared across them.
Does Han send my code or metrics to the cloud?โผ
No. All metrics tracking and confidence calibration happen locally on your machine, and nothing leaves your environment.
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