Han: Skill Suite para Engenheiros Solitários
testdouble/han
Skills de IA para planejamento, codificação e review sem necessidade de time
Ver no GitHubHan é um conjunto de skills e agents de IA especializados para engenheiros de produto solo ou em pequenos times. Automatiza planejamento baseado em evidências, implementação test-driven, manutenção de documentação, revisão de código profunda e análise arquitetural através de agents especializados que você dispõe do Claude Code.
Instalação
npx convez-ai testdouble/han1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Planejar features com análise profunda antes da implementação
- Executar code review adversarial e análise arquitetural automática
- Manter documentação sincronizada durante desenvolvimento
- Gerar relatórios e summaries para stakeholders
- Integrar findings direto em PRs no GitHub
Veredito

Han é uma abordagem inovadora para multiplicar a capacidade de um engenheiro solo, delegando tarefas de julgamento pesado a agents especializados. Bem estruturado em skills compostas e documentação clara, ideal para times pequenos que precisam de rigor sem overhead de processo.
README
A tradução para o português deste README ainda está na fila.
Han: For the Solo Product Engineer
Han is a suite of AI skills and agents for solo (or small-team) product engineers. It combines evidence-based planning, test-driven implementation, full documentation maintenance, deep code review, and architectural analysis into a team of specialists you can dispatch from Claude Code.
What this plugin does
Han turns planning, implementation, review, and documentation work that would normally take a team into a set of deterministic skills you run from Claude Code. Each skill dispatches specialist agents (project managers, adversarial reviewers, investigators, architectural analysts, testing and security specialists) to do the judgment-heavy work, then folds their findings into an artifact you can trust.
The skills are designed to compose. You can plan a feature, then plan its implementation, then iterate on the plan, then build it test-first, then review the resulting code, then write the PR description. All through named skills that hand off to each other cleanly.
Read Concepts for the skill-and-agent model that runs through the whole plugin.
For Solo Product Engineers and Small Teams
Han is purpose-built for solo product engineers and small teams, instead of large teams or enterprise. This does not mean it can't work in larger teams, though. Read about why Han's focus is solo product engineers and small teams to understand Han's positioning and what it does not bring to the table.
Installation
Add the Test Double skills marketplace to Claude Code, then install the plugin:
/plugin marketplace add testdouble/han
/plugin install han@han
Han ships as multiple plugins:
| Plugin | Type | What it brings |
|---|---|---|
han | parent | the parent plugin that brings in han.core, han.planning, han.coding, han.github, and han.reporting |
han.core | bundled | research, analysis, and documentation skills plus every agent |
han.planning | bundled | planning skills you reach for before implementation |
han.coding | bundled | coding skills you reach for while working in code |
han.github | bundled | GitHub-facing skills like posting a code review on a PR |
han.reporting | bundled | reporting skills like the stakeholder summary |
han.feedback | opt-in | skill for capturing post-session feedback on Han skill runs |
han.atlassian | opt-in | skills for publishing docs and work items to Atlassian products |
han.plugin-builder | opt-in | carries the guidance for building your own skills, agents, and plugins |
Installing han@han pulls in the bundled suite (the meta-plugin plus han.core, han.planning,
han.coding, han.github, and han.reporting), and is the right choice for most people. If you do
not want the planning, coding, GitHub, or reporting skills, install han.core@han instead, and add other
specific plugins as desired.
For the full picture and a quick "which one do you need?" guide, see Choosing a Han plugin.
Documentation
- Concepts. Skill vs. agent, and how they compose. Read once before using the plugin.
- Choosing a Han plugin. The full suite vs. core only, the
han.planning,han.coding,han.github, andhan.reportingdependencies onhan.core, and a quick guide to which one to install. - Quickstart. Five paths for five common situations. Each path is a short sequence of skills.
- How-to guides. End-to-end recipes for planning a feature, triaging and investigating a bug, and researching a decision. Pick one when you want the full walkthrough, not only the path.
- Skills Index. All skills, grouped by purpose.
- Agents Index. All agents, grouped by role.
- Sizing. The small / medium / large model that decides how many agents the swarming skills dispatch.
- YAGNI. The evidence-based "You Aren't Gonna Need It" rule every planning, review, and architecture skill applies.
- Evidence. What counts as evidence in Han, how to characterize how strong it is, and what to do when no evidence exists at all.
- How to provide feedback on Han. Send the maintainers structured feedback on a skill or agent run.
- Extend Han via dependencies. Add your own custom skills on top of Han.
- Build a plugin that depends on Han. Ship a plugin that builds on Han's skills and agents.
- Contributing. Adding or editing skills, agents, and documentation.
- Changelog. What's new in each version of the plugin.
Maintenance and Support
- Maintenance horizon: Indefinitely maintained, best-effort. No SLA.
- Project type: Personal project, with some Test Double support
- How to report issues: GitHub Issues, with expected best effort for response within 2 weeks.
Han is an open source product of Test Double, and maintained by the following people:
- River Lynn Bailey: Creator, and primary maintainer
LEGAL NOTICES
Copyright 2026 Test Double, Inc. Distributed under the MIT license.