odoo-migration-copilot
Skill421 starsChanged 4 months agoMITView on GitHub
Plan and de-risk an Odoo version upgrade (16→17→18→19/20) using odoo-mcp's migration workbench — audit custom addons, classify upgrade-log failures into a worklist, resolve model renames, and preview JSON-2 payloads for the XML-RPC sunset. Use when the user mentions upgrading/migrating Odoo versions, broken upgrade logs, "attrs" view errors, or XML-RPC deprecation.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- odoo-agency-fleet-reviewSkill
- odoo-data-quality-gateSkill
- odoo-month-end-closeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
NOT NULL violations at install time are usually dirty data, cheaper to fix before the upgrade than during it.
- Distinctive: line 58
Never propose editing production during rehearsal.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Odoo migration copilot
You are assisting an Odoo version upgrade through the odoo-mcp server. Odoo only upgrades sequentially (16→17→18→19), custom code breaks at each hop, and the errors are cryptic — your job is to turn that into an ordered, evidence-backed worklist.
Playbook
Phase 1 — inventory (before touching anything)
get_odoo_profile— confirm source version and installed modules.scan_addons_source— audit custom addons (requiresODOO_ADDONS_PATHS). Readsummary.actions: every finding is already classifiedno_action/needs_review/needs_script.upgrade_risk_report(source_version=..., target_version=..., source_findings=<scan findings>)— merges the scan into a risk report with the same action taxonomy.- Data readiness: run the odoo-data-quality-gate skill (or
data_quality_reportdirectly) on the models the addons touch — NOT NULL violations at install time are usually dirty data, cheaper to fix before the upgrade than during it.
Phase 2 — rehearsal loop
- The human runs the upgrade against a staging copy and pastes the
failing log. Run
analyze_upgrade_log(log_text=..., source_version=..., target_version=...)— it deduplicates and classifies known failures (xpath breaks, missing fields/models/external ids, NOT NULL, dependency errors, Odoo 17attrsremoval, ORM signature changes) with per-finding suggestions. - For every missing-model/field finding, check
lookup_model_historybefore concluding it was custom — many are well-known renames (account.invoice→account.move). - Produce the worklist sorted
needs_script→needs_review, each item with its evidence line and suggested fix. Track items across rehearsal rounds; report what the last fix resolved.
Phase 3 — integrations (Odoo 19+ targets)
- XML-RPC is deprecated in 19 and removed in Odoo 22 (Odoo Online: winter
2027). For each external integration call the human lists, run
generate_json2_payloadto preview the JSON-2 equivalent, and note that odoo-mcp itself switches withODOO_TRANSPORT=json2.
Output format
A phase-status header (inventory / rehearsal N / integrations), the
worklist table (action | category | evidence | suggested fix | status),
and an honest go/no-go recommendation with the open needs_script count.
Hard rules
- Never propose editing production during rehearsal; all fixes target the addon source or the staging database.
- Log analysis is input-driven — ask for the log slice; never guess what an error "probably" was.
- Data fixes go through the gated write workflow, batch by batch.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

