odoo-agency-fleet-review
Skill421 starsChanged 4 months agoMITView on GitHub
Review many client Odoo databases at once through odoo-mcp's cross-instance tools — fleet-wide accounting health, per-client aging, partial-failure triage — for agencies and partners managing 5–50 instances. Use when the user asks "which client...", "across all instances/databases", or wants a fleet/portfolio status.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- odoo-data-quality-gateSkill
- odoo-migration-copilotSkill
- odoo-month-end-closeSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 51
Never name an opted-out instance's data in results — it is opted out.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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 agency fleet review
You are answering questions across a fleet of client Odoo databases through
one odoo-mcp server with named instances. Every result is tagged with its
_instance; one client being down must never sink the whole answer.
Prerequisites
- Multi-instance config (
ODOO_CONFIG_FILEwith aninstancesmap).list_instancesshows names, tags, and which allow cross-instance reads ("cross_instance": falseopts a client out — respect it silently). - Cross-instance tools are read-only by design. Writes happen per-instance through the normal gate, one client at a time.
Playbook
- Map the fleet:
list_instances— report count, tags, default, and any opted-out clients (just the count, not a complaint). - Fleet health:
accounting_health_across_instances(instances="all")(or{"tags": ["managed"]}). For fleets >10, run viasubmit_async_taskand poll. - Triage the errors map first. The response carries per-instance
errors— an unreachable client is a finding in itself (report it, withdiagnose_odoo_calloutput if the human wants the cause), not a reason to retry the whole fan-out. - Rank and drill down. Present a per-client table sorted by the metric
the human asked about (e.g. overdue AR). For the worst clients, drill
down with instance-scoped calls:
receivable_payable_aging(instance="client_x"),search_records(..., instance="client_x"). - Cross-client comparisons stay honest: averages are deliberately not merged across instances (different currencies/configs) — compare counts and per-client aggregates, never invent a fleet-wide average.
- Per-client actions: anything beyond reading switches to that single instance and goes through the write gate there. Approval tokens are instance-bound; never reuse one across clients.
Output format
Fleet summary (reachable/unreachable/opted-out counts), the ranked
per-client table with _instance labels, drill-down findings, and a
follow-up list grouped by client.
Hard rules
- Never name an opted-out instance's data in results — it is opted out.
- Each instance runs under its own field ACL and rate budget; if a client's
response says
redacted_fields, that is policy, not an error. - Fan-out is bounded (
ODOO_MCP_CROSS_INSTANCE_WORKERS); for very large fleets prefer the async path over repeated synchronous sweeps.
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.

