Bmad odoo setup
One-command setup of a BMAD + Odoo development environment in the current project — pulls BMAD METHOD and the Odoo agent-skills fresh, then lays down the odoo-ba-smartcore BA skill, subagents, BMAD agent/workflow overrides, and the Visual-QC engine. Use when the user says "thiết lập BMAD", "setup BMAD Odoo", "cài BMAD + Odoo", "khởi tạo môi trường BMAD cho dự án Odoo", or wants to bootstrap a new Odoo project for BMAD-driven analysis → design → dev.From its SKILL.md
npx -y skills add baolinhtb/BMAD-Odoo-Skills --skill bmad-odoo-setupAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.8 KB, 996 tokens by cl100k_base, as published. Nobody here has run it
BMAD + Odoo Setup
Bootstraps a complete BMAD-METHOD + Odoo workflow into an existing Odoo project with a single command. Fresh upstream pieces (BMAD core, Odoo knowledge skills) are pulled at install time so they are always the latest/optimal; the integration glue (BA skill, subagents, agent overrides, Visual-QC) is bundled in this repo.
What it installs
- BMAD METHOD (
bmmmodule,claude-codetools, Vietnamese) — pulled fresh vianpx bmad-method@latest. - Odoo agent-skills —
odoo-17/odoo-18/odoo-19,payment-integration,dtg-base,mcp-builder,ai-vibe-slides— pulled fresh vianpx skills add unclecatvn/agent-skills. - odoo-ba-smartcore BA skill (
/srs,/use-case,/gap-analysis,/user-story,/bpmn,/mockup,/to-bmad) — bundled. - Subagents
planner,odoo-code-review,odoo-code-tracer→.claude/agents/— bundled. - BMAD overrides (
_bmad/custom/*.toml) wiring the Odoo knowledge base + BA artifacts into analyst (Mary), architect (Winston), dev (Amelia), pm (John), ux (Sally), pluscreate-story/dev-story/quick-devworkflows — bundled. - Visual-QC engine (
_bmad/scripts/visualqc/) +bmad-qa-visual-reviewskill — bundled. docs/project-context.md+.odoo-versionpin +docs/analysis&docs/mockupsscaffolding.
How to run
From the root of the target Odoo project, run one of:
# A) curl one-liner (self-clones bundled assets)
curl -fsSL https://raw.githubusercontent.com/baolinhtb/BMAD-Odoo-Skills/main/install.sh | bash
# B) clone then run (offline-friendly, lets you inspect first)
git clone --depth 1 https://github.com/baolinhtb/BMAD-Odoo-Skills.git /tmp/bmad-odoo-kit
bash /tmp/bmad-odoo-kit/install.sh /path/to/odoo-project
When invoked as a skill, default to A with $PWD as the project dir, unless the user
names a different directory. Confirm the target directory with the user first if it is not
obviously an Odoo project (no addons/ or __manifest__.py nearby).
Options (env vars, prepend to the command)
| Var | Default | Purpose |
|---|---|---|
ODOO_VERSION | 19 | Odoo major to pin (17/18/19); rewrites overrides accordingly |
BMAD_LANG | Vietnamese | BMAD communication language |
SKIP_BMAD=1 | — | skip BMAD installer (re-run safe; auto-skips if _bmad/ exists) |
SKIP_SKILLS=1 | — | skip the agent-skills pull |
SKIP_VISUALQC=1 | — | skip Visual-QC engine + npm install |
Example: ODOO_VERSION=18 BMAD_LANG=English curl -fsSL .../install.sh | bash
After install
Tell the user the environment is ready and suggest the flow:
- Analysis — "talk to Mary" (analyst) →
/srs,/gap-analysis,/mockup→/to-bmad(emitsdocs/epics.md,docs/architecture.md,docs/ux.md, updatesdocs/project-context.md). - Planning — BMAD
sprint-planning→create-story. - Build —
dev-story(Amelia) implements with theodoo-19guides as source of truth;ORmenu item runs theodoo-code-reviewagent. - Visual QC — "visual qc <feature>" screenshots the running app vs the HTML mockup.
The setup is idempotent: re-running refreshes the bundled glue and re-pulls upstream
skills without clobbering _bmad/ or an existing docs/project-context.md.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most project setup skills give in 996 tokens
Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07
- Ask one question at a timein 29 of 999, across 28 files
- Detect the package manager from lockfilesin 28 of 999, across 9 files
- Present findings to the userin 26 of 999, across 5 files
- Explore current repo statein 24 of 999, across 3 files
- Update the agent skills block in place if it existsin 24 of 999, across 3 files
- Install husky lint-staged and prettierin 23 of 999, across 4 files
- Create the lintstagedrc filein 22 of 999, across 3 files
- Commit all changed filesin 22 of 999, across 3 files
- Run lint-staged to verify it worksin 22 of 999, across 3 files
- Create the husky pre-commit filein 21 of 999, across 2 files
- Create a prettierrc file if missingin 21 of 999, across 2 files
- Initialize huskyin 21 of 999, across 2 files
Said here and by no other author read
- run curl installer in target project
- confirm target directory with user if ambiguous
- skip bmad installer if directory exists
- suggest analysis planning build flow to user
- tell the user the environment is ready
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.