agentleFS
Sign inStart free
actinon-comactinon-com/brass-monkey/skills/odoo-helpdesk/SKILL.md

odoo-helpdesk

Skill2 starsChanged 3 months agoMITView on GitHub

MANDATORY for Tickets (helpdesk.ticket) and SLAs (helpdesk.sla). Expertise in Odoo's support engine and customer service.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Routing: Every ticket belongs to a Helpdesk Team (helpdesk.team), which dictates the available stages and assignment method (Manual, …

    line 13
  2. Very specific:

    Mandate: Always prioritize tickets with the earliest sla_deadline to avoid breach.

    line 18
  3. Very specific:

    Returns: If a product is faulty, link/create a Return (stock.picking) from the ticket.

    line 22
  4. Very specific:

    Field Service: If on-site work is required, generate a Task (project.task).

    line 23
  5. Very specific:

    Public Reply: Use message_post with message_type: 'comment' and body_is_html: true (if sending HTML) for messages sent directly to the …

    line 27
  6. Very specific:

    Internal Note: Use message_post with subtype_xmlid: 'mail.mt_note' and body_is_html: true (if sending HTML) for internal technical updates.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: Odoo Helpdesk & Customer Support

This skill provides the agent with high-level functional expertise in Odoo's Customer Support engine, covering Ticket management, SLA compliance, and multi-channel integration.

Core Mandates

1. Ticket Lifecycle & Routing

  • Creation: Tickets are generated via Email Aliases, Website Forms, Live Chat, or manual entry.
  • Routing: Every ticket belongs to a Helpdesk Team (helpdesk.team), which dictates the available stages and assignment method (Manual, Random, Balanced).
  • Stages: Progression is tracked via Stages (helpdesk.stage). Tickets in "folded" stages are considered closed.

2. SLA Compliance

  • Deadlines: Service Level Agreements (helpdesk.sla) calculate the sla_deadline based on the ticket's priority and team configuration.
  • Mandate: Always prioritize tickets with the earliest sla_deadline to avoid breach. Use the sla_reached flag to verify compliance.

3. Integrated Resolution (Backend/Frontend)

Helpdesk is the bridge between a customer problem and a technical solution:

  • Returns: If a product is faulty, link/create a Return (stock.picking) from the ticket.
  • Field Service: If on-site work is required, generate a Task (project.task).
  • Sales/Invoicing: Reference the original sale.order_id to verify warranty status or bill for support time via sale_line_id.

4. Communication Protocol

  • Public Reply: Use message_post with message_type: 'comment' and body_is_html: true (if sending HTML) for messages sent directly to the customer.
  • Internal Note: Use message_post with subtype_xmlid: 'mail.mt_note' and body_is_html: true (if sending HTML) for internal technical updates.
  • Mandate: Clearly distinguish between the two. Never leak internal technical jargon to the customer.

Available Resources

  • helpdesk-logic.md: Deep-dive into SLA calculations, Website/Portal configuration, and action triggers for Returns/Repairs.
  • helpdesk-fields.json: Dense technical map of fields for Ticket, Team, Stage, and SLA models.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free