agentleFS
pobstetapobsteta/aigora/.claude/skills/odoo/SKILL.md

odoo

Skill0 starsChanged 45 days agoMITView on GitHub

Odoo CRM for leads and opportunities - show the pipeline, find a prospect, create an opportunity from a validated research-lead file, move it to another stage, add an internal note. Use when the user mentions Odoo, CRM, pipeline, opportunité, prospect à suivre, relance, or after a research-lead the user approved.

  • Reads credentials

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Every write (create-lead, move, note) runs first WITHOUT --confirm: show the preview, get an explicit yes, then rerun with --confirm.

    line 39
  2. Very specific:

    create-lead refuses probable duplicates (same email, or same contact + company).

    line 41
  3. Very specific:

    Never delete records and never change partners, quotes or invoices from AIGORA.

    line 45
  4. Very specific:

    After a research-lead the user approved: offer create-lead --from-json, which fills contact, company, job title, LinkedIn URL, summary, …

    line 47

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

Odoo CRM

Odoo Community (LGPL-3, open source) or Odoo Online, reached through the official external API by .claude/skills/odoo/scripts/odoo.py:

  • JSON-2 (Odoo 19+): POST /json/2/<model>/<method>, bearer API key.
  • XML-RPC fallback for Odoo 18 and older (deprecated since 19, removal planned in Odoo 22): needs ODOO_DB and ODOO_LOGIN too. ODOO_API=auto (default) picks the right one. All output is JSON with success.

Setup (if ODOO_URL / ODOO_API_KEY are missing)

The user runs aigora_odoo_configurer() in the R console (asks URL, database, login and API key, key masked, then tests). Never ask for the Odoo password; only an API key. Guide: docs/ODOO.md. On Odoo Online, external API access may require a specific plan: if the API answers 401/403 with a valid key, say so.

Commands

O=".claude/skills/odoo/scripts/odoo.py"
python3 $O status                                   # protocol + CRM stages
python3 $O stages
python3 $O pipeline [--stage "Qualifié"] [--limit 50] [--all-types]
python3 $O find --email x@y.ch | --name "Jeanne Martin" --company "Géo-Conseil"
python3 $O create-lead --from-json .tmp/leads/<slug>/combined.json [--stage "Nouveau"] [--tags "AIGORA"]   # preview
python3 $O create-lead ... --confirm                # really creates
python3 $O move --id 42 --stage "Proposition" --confirm
python3 $O note --id 42 --text "Relancé par mail" --confirm

Rules

  • Every write (create-lead, move, note) runs first WITHOUT --confirm: show the preview, get an explicit yes, then rerun with --confirm.
  • create-lead refuses probable duplicates (same email, or same contact + company). Show the existing records; use --allow-duplicate only if the user says it is a different deal.
  • Opportunities are created with type=opportunity (they appear in the pipeline even when the "Leads" step is disabled in Odoo). Use --type lead only if the user works with leads.
  • Never delete records and never change partners, quotes or invoices from AIGORA.
  • Personal data stays in Odoo: do not copy prospect details into memory files, logs or kChat.
  • After a research-lead the user approved: offer create-lead --from-json, which fills contact, company, job title, LinkedIn URL, summary, chosen hook, proposed first message and score.

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.