bmad-tea-automate — скилл для Claude Code: что делает и как установить
Скилл bmad-tea-automate для Claude Code генерирует тесты в режимах red или expand и чинит обнаруженные дефекты. Агент подключает его при запросах на автоматизацию тестов и ATDD.
MIT 887 установок ★ 118 обновлён 2026-11-13
npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmad-tea-automate -a claude-codeЧто делает bmad-tea-automate
Скилл работает под управлением мастера-архитектора тестирования и опирается на соседний скилл bmod-tea. Перед стартом скрипты проверяют конфигурацию проекта и мигрируют старые настройки из файлов bmad-testarch-automate.toml. Архитектура разбита на режимы создания, валидации и правки тестов через специализированные шаги.
Для работы скриптов требуется установленный uv и python-окружение в проекте. Без каталога bmod-tea и файла конфигурации скилл прерывает запуск и выводит требование настроить окружение командой bmad setup tea.
Какие задачи решает
- создать заготовки тестов до написания кода
- расширить покрытие тестов для реализованных функций
- запустить сгенерированные тесты и исправить ошибки
- проверить конфигурацию окружения для тестирования
Примеры запросов агенту
- автоматизируй тесты для нового модуля
- расширь тестовое покрытие текущего кода
- напиши приемочные тесты для фичи
Как установить bmad-tea-automate
1Через Skills CLI (Vercel)
npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmad-tea-automate -a claude-code2Вручную: положить файлы
~/.claude/skills/bmad-tea-automate/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/bmad-tea-automate/
1Через Skills CLI (Vercel)
npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmad-tea-automate -a codex2Вручную: положить файлы
.agents/skills/bmad-tea-automate/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmad-tea-automate -a cursor2Вручную: положить файлы
.cursor/skills/bmad-tea-automate/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install bmad-code-org/bmad-method-test-architecture-enterprise skills/bmad-tea-automate2Вручную: положить файлы
.github/skills/bmad-tea-automate/SKILL.md1Через Skills CLI (Vercel)
npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmad-tea-automate -a gemini-cli2Командой платформы
gemini skills install https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise --path skills/bmad-tea-automateВручную: положить файлы
.devin/skills/bmad-tea-automate/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmad-tea-automate -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о bmad-tea-automate
Как установить bmad-tea-automate в Claude Code?
Выполните команду npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmad-tea-automate -a claude-code, затем обратитесь к файлу ~/.claude/skills/bmad-tea-automate/SKILL.md.
Что делает bmad-tea-automate?
Скилл генерирует приемочные и модульные тесты в режимах создания или расширения покрытия, запускает их и автоматически устраняет выявленные дефекты.
Что нужно для работы bmad-tea-automate?
Для работы необходим соседний скилл bmod-tea, наличие инструмента uv в системе и предварительно настроенный файл конфигурации _bmad/config.toml.
Исходный текст
SKILL.md · MIT
---
name: bmad-tea-automate
description: 'Generate tests in red or expand mode and run-and-heal new tests. Use when the user says "lets expand test coverage", "I want to automate tests", "lets write acceptance tests", or "I want to do ATDD"'
---
# Test Generation: Red and Expand
**Goal:** Generate acceptance scaffolds before implementation in red mode, or expand passing coverage for implemented code in expand mode. Execute generated tests and repair confirmed test defects by default.
**Role:** You are the Master Test Architect.
You will continue to operate with your given name, identity, and communication_style, merged with the details of this role description.
## Conventions
- Bare paths (e.g. `instructions.md`) resolve from the skill root.
- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
- `{project-root}` is the nearest folder containing `_bmad/`, starting at the project working directory and moving up through its parents.
- `{tea-knowledge}` is the `knowledge/` folder of the `bmod-tea` skill, installed beside this one: `{skill-root}/../bmod-tea/knowledge`. `tea-index.csv` there lists every fragment by a path relative to that folder.
- `{tea-contracts}` is the `contracts/` folder of the `bmod-tea` skill, installed beside this one: `{skill-root}/../bmod-tea/contracts`. `story-identity.md` there says how a story is resolved, read and named.
- `{skill-name}` resolves to the skill directory's basename.
- Resolve sibling workflow files such as `instructions.md`, `checklist.md`, `steps-c/...`, `steps-e/...`, `steps-v/...`, and templates from `{skill-root}`.
## Route Before Activation
Read `{skill-root}/resources/test-generation-routing.md` completely and resolve `test_mode`, `test_operation`, and `workflow-key` before executing activation.
Keep `{skill-root}` bound to this canonical directory throughout both modes.
The router selects exactly one customization key (`workflow` for expand, `workflow.red` for red); activation below uses that key only.
## On Activation
Before resolving customizations or running hooks, inspect `{project-root}/_bmad/custom/` for `bmad-testarch-automate.toml`, `bmad-testarch-automate.user.toml`, `bmad-testarch-atdd.toml`, `bmad-testarch-atdd.user.toml`, `bmad-tea-atdd.toml`, and `bmad-tea-atdd.user.toml`. Red settings live under `[workflow.red]` in `bmad-tea-automate.toml` and `.user.toml`; the atdd files are read nowhere. If any exists, stop and tell the user to run `npx --package=bmad-method-test-architecture-enterprise@4 tea-migrate-customizations --project-root {project-root}`. Resolve any reported manual merge, then start a fresh chat. Do not continue with default settings while legacy overrides remain.
### Step 1: Resolve the Workflow Block
Run: `uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key {workflow-key}`
The returned object is the `workflow` block for the rest of the run: `{workflow.activation_steps_prepend}`, `{workflow.persistent_facts}` and the other keys below read from it, whichever mode was selected.
**If the script fails**, resolve the block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
1. `{skill-root}/customize.toml` — defaults
2. `{project-root}/_bmad/custom/bmad-tea-automate.toml` — team overrides
3. `{project-root}/_bmad/custom/bmad-tea-automate.user.toml` — personal overrides
Then take the `workflow` table, or its `red` sub-table when `workflow-key` is `workflow.red`. Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
### Step 2: Execute Prepend Steps
Execute each entry in `{workflow.activation_steps_prepend}` in order before proceeding.
### Step 3: Load Persistent Facts
Treat every entry in `{workflow.persistent_facts}` as foundational context you carry for the rest of the workflow run. Entries prefixed `file:` are paths or globs resolved from `{project-root}` — expand them and load every matching file in lexical path order as facts. All other entries are facts verbatim.
### Step 4: Load Config
Run `uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key core --key modules.tea`. If the script fails, merge `{project-root}/_bmad/config.toml`, `{project-root}/_bmad/custom/config.toml` and `{project-root}/_bmad/custom/config.user.toml` yourself, in that order, with the merge rules above. If `_bmad/config.toml` is missing or has no `modules.tea` table, tell the user TEA is not set up, ask them to run `bmad setup tea` first, and stop.
Each `core` and `modules.tea` key is available as `{<key>}`, and as `config.<key>` in later steps. Replace `{project-root}` inside a value with the project root. Setup answers are strings: read `"true"` and `"false"` as booleans.
If `{tea-knowledge}/tea-index.csv` does not exist, the `bmod-tea` skill is not installed beside this one (`{skill-root}/../bmod-tea`). Tell the user to install `bmod-tea` in the same scope as this skill, and stop until it is there. For a skill in the project's skills folder run `npx skills add bmad-code-org/bmad-method-test-architecture-enterprise --skill bmod-tea`; for a skill in the global skills folder add `-g`. Run the command on a yes. A headless run has no approval input: report the missing dependency and stop without running the installer. A `bmod-tea` installed in the other scope does not satisfy this skill.
### Step 5: Greet the User
Greet `{user_name}`, speaking in `{communication_language}`.
### Step 6: Execute Append Steps
Execute each entry in `{workflow.activation_steps_append}` in order.
Activation is complete. Begin the workflow below.
## Workflow Architecture
This workflow uses **tri-modal step-file architecture**:
- **Create mode (steps-c/)**: primary execution flow for new runs and resume continuation
- **Validate mode (steps-v/)**: validation against checklist
- **Edit mode (steps-e/)**: revise existing outputs
## Initialization Sequence
The router has already resolved the operation from the request.
For an interactive invocation that supplied no operation or generation intent, show Create, Resume, Validate and Edit once.
A generation intent starts Create; an autonomous invocation without an operation also starts Create.
Do not ask a second mode question.
Use `mode-prefix = red/` for red, or an empty prefix for expand:
- Create: load `{skill-root}/{mode-prefix}steps-c/step-01-preflight-and-context.md`.
- Resume: load `{skill-root}/{mode-prefix}steps-c/step-01b-resume.md`; continue its original `lastStep` mapping, scope and output path.
- Validate: load `{skill-root}/{mode-prefix}steps-v/step-01-validate.md`.
- Edit: load `{skill-root}/{mode-prefix}steps-e/step-01-assess.md`.
Resume restores Create progress; it does not start a new generation run.
Only Create terminals load `{skill-root}/resources/run-and-heal.md`.
Validate evaluates execution evidence as PASS/WARN/FAIL without repair or requiring a green suite.
Edit checks the requested changes only and never invokes automatic repair.
© bmad-code-org · MIT · bmad-code-org/bmad-method-test-architecture-enterprise