Run end-to-end Odoo acceptance on a change AND its blast-radius: map the affected cluster, plan an INDEPENDENT oracle, then EXECUTE it on a real running instance/UI and adjudicate PASS/FAIL with evidence. Fire on: acceptance test, QA the affected cluster, verify on the real UI, "write scenarios then run them", verify blast-radius, "works end-to-end before release". Also Vietnamese: "nghiệm thu cụm module", "chạy thật trên UI", "kịch bản test rồi chạy", "kiểm thử chấp nhận". Sole dispatcher of odoo-qa-planner (oracle) + odoo-qa-tester (live run); chains tours/HttpCase via odoo-instance. Routing: a STATIC release test-plan doc / deploy checklist -> route to odoo-qa-suite; rating ONE rendered screen -> route to odoo-ui-review; static code or PR review with no run -> route to odoo-code-review; writing the fix -> route to odoo-coding. EXECUTION needs a live instance + browser MCP (Odoo Semantic is static, no live data); with none up it still scopes + plans the oracle, then emits NEEDS_NEXT to provision one
Produce a CE vs EE vs custom-distribution comparison for a business domain - feature table, EE-only business-value notes, and an upgrade recommendation ready for a proposal. Version-aware: uses MCP check_module_exists/model_inspect; confirm version when unspecified. Trigger when edition differences come up, even in passing. Trigger on: "CE vs EE feature table", "edition comparison", "which modules are EE-only?", "is X a CE or EE feature?", "upsell argument for EE", "PLM / Studio / Maintenance - which edition?", "which edition is module X in?". Also fires on Vietnamese: "so sánh CE và EE", "tính năng nào chỉ có ở Enterprise", "module X thuộc bản nào", "cần bản Community hay Enterprise". Trigger even when the user names a specific feature/module and asks "what edition do I need?". When the user asks about ONE feature's availability (not a comparison), route to odoo-feature-check. When they want marketing copy for the Enterprise features themselves, route to odoo-feature-highlights
Process a business requirement list (BRL) of any size - tens to thousands of items - into a classified, costed, dependency-ordered implementation plan. For each requirement: 4-way classification (Available-in-Odoo-CE / Available-in-Odoo-EE / Available-in-Viindoo / Custom) via double-profile odoo-semantic-mcp tool calls, a deterministic cost estimate (lookup table, no fabrication), and a requirements traceability matrix (RTM) for consultant export. Runs as a chunked sequential-outer / parallel-inner pipeline with checkpoint/resume after interruption. Fire ANY time someone pastes or points to a multi-item requirement list to scope end-to-end: "classify these 400 requirements", "turn this RFP spreadsheet into an effort + cost plan". Also fires on Vietnamese: "phân loại danh sách yêu cầu này", "biến RFP thành kế hoạch chi phí + công". For a SINGLE feature use odoo-feature-check; for a short ad-hoc gap matrix with no cost, no chunked pipeline, and no scale requirement use odoo-gap-analysis
Plan a multi-week, multi-channel marketing campaign for an Odoo vertical or geography push - blueprint with timeline, channel mix matrix, asset inventory, KPIs, and owner map (AI-doable vs human-required). ORCHESTRATES campaigns; does NOT draft individual content. Trigger on: "plan a campaign for", "campaign brief", "multi-channel plan for vertical X", "build a campaign blueprint", "marketing push plan for", "campaign roadmap for", "go-to-market blueprint". Also fires on Vietnamese: "lập kế hoạch chiến dịch", "kế hoạch marketing đa kênh", "chiến dịch go-to-market cho ngành X", "lộ trình truyền thông". DO NOT trigger for: individual content draft (→ odoo-content-draft), competitive positioning analysis (→ odoo-competitive-brief), feature-highlight slides for a sales deck (→ odoo-feature-highlights), capability proof for a prospect (→ odoo-capability-proof). STANDALONE-FIRST: works without MCP; OSM optional for feature-claim verification only
Review Odoo code (Python, JavaScript, XML, OWL) for bugs, convention violations, security, and performance - severity-graded findings, suggested fixes, corrected version. Dispatches to the odoo-code-reviewer agent. Fire whenever code is shared with feedback intent, even without the word "review". Trigger on: "does this look correct?", "audit this PR", "should I worry about N+1?", "before I merge", "review PR #123". Also fires on Vietnamese: "review giúp đoạn này", "kiểm tra code Odoo", "code này có bug không", "soát trước khi merge", "đánh giá PR". Trigger on model overrides, write/create overrides, computed fields, OWL components, or XML view overrides - Odoo-specific failure modes a generic reviewer misses. Static analysis only - a live render/console error -> odoo-debug, rating a rendered screen's look/UX -> odoo-ui-review. Write new code -> odoo-coding. Pre-upgrade audit -> odoo-deprecation-audit. A dedicated performance-only deep scan -> odoo-perf-audit; a security-only scan -> odoo-security-audit
Use when someone wants to build or change Odoo behavior and needs the code written - the single front door for ALL Odoo coding and the ONLY dispatcher of the per-module odoo-coder coordinator, scoping modules and ordering by dependency. Fire on ANY request to add or change something in an Odoo module, even with no technical words (e.g. "discount can never exceed 20% of unit price", "ticking urgent sets the deadline to tomorrow"): new model/field, computed/related field, constraint, onchange/auto-fill, create/write/unlink override, access rights, migration script, OWL/JS/QWeb/SCSS widget or form/list/kanban UI. Also Vietnamese: "thêm trường / model", "override create/write", "ràng buộc", "onchange tự điền", "phân quyền đọc ghi", "widget OWL / sửa form". DO NOT trigger for non-Odoo code. Review existing code → odoo-code-review. Hook point → odoo-override-finding. Design first → odoo-solution-design. Runtime/render bug → odoo-debug. Rate a screen → odoo-ui-review. Planning/estimate → odoo-planning
Produce a competitive intelligence brief for a Strategist / CEO - board-ready capability matrix vs Odoo, GTM moves (user-provided only), threat assessment, and recommended response. Standalone-first - works WITHOUT OSM. Fire when user mentions a competitor alongside strategic intent: "competitor brief on", "analyze competitor X", "competitive landscape analysis", "competitive update for board", "threat assessment for", "competitive intelligence update". Also fires on Vietnamese: "phân tích đối thủ X", "brief cạnh tranh cho ban lãnh đạo", "đánh giá mối đe doạ cạnh tranh". DO NOT trigger for: (a) sales talking-point objections ("they say Odoo can't do X") → odoo-objection-handling; (b) feature comparison drill-down between Odoo versions → odoo-version-diff; (c) detailed add-on diff → odoo-addon-diff; (d) marketing copy or campaign messaging about competitive positioning → odoo-content-draft or odoo-campaign-plan; (e) simple feature availability check → odoo-feature-check
Draft ready-to-publish marketing content for Odoo or your distribution - LinkedIn post, blog article, YouTube script, email sequence, landing page copy, or social caption. Language: English default; Vietnamese and other locales on request. Trigger on: "draft a blog post", "write a LinkedIn post", "YouTube script for", "draft email sequence", "landing page copy", "social caption for". Trigger when user asks to CREATE any of these formats - even without the word "marketing". Also fires on Vietnamese: "viết bài blog", "soạn bài LinkedIn", "kịch bản YouTube", "chuỗi email", "nội dung landing page", "caption mạng xã hội". DO NOT trigger for: proposal/gap-analysis text (-> odoo-gap-analysis), objection-handling rebuttals (-> odoo-objection-handling), feature-highlight decks (-> odoo-feature-highlights), competitive positioning briefs (-> odoo-competitive-brief), multi-channel campaign orchestration (-> odoo-campaign-plan). STANDALONE-FIRST: works without MCP; OSM optional for grounding claims