agentsclimarketplace

Odoo grill

Skill omas-odoo/odoo-superpowers/skills/odoo-grill

Odoo development skills for AI coding agents — a Claude Code plugin (also Codex & Gemini CLI) packaging PSDU principles for models, views, security, migrations, tests & code review. Principles, not rules.

Install
npx -y skills add omas-odoo/odoo-superpowers --skill odoo-grill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use before implementing a non-trivial Odoo feature or design, to pressure-test the approach before any code is written. Symptoms — "I'm about to build X", an underspecified plan, or a design with multi-company / upgrade implications. Interrogates the plan one question at a time, each with a recommended answer, walking the design tree. Not for quick fixes the user already scoped.

SKILL.md

2.7 KB, 521 tokens by cl100k_base, as published. Nobody here has run it

Grill the plan

Before writing Odoo code, interrogate the plan — one question at a time, each carrying your recommended answer — and walk the design tree to its leaves. The grill produces decisions, not code; it pre-empts the rework that surfaces when a wrong assumption is only discovered mid-implementation. Implementation starts after the plan survives, not before.

If the codebase can answer a question, read the code instead of asking. Wait for the answer before the next question.

Question lenses (walk the tree through these)

  1. Functional before technical. What does the customer actually need to happen? Could a setting, an automated action, Studio, or an existing module deliver it with zero custom code? Why does this need a new module — or any code — at all?
  2. The Odoo dimensions. Multi-company, multi-currency, multi-language, multi-warehouse, multi-website: which apply, and what happens at each boundary? Invent a concrete scenario per applicable dimension and make the plan resolve it.
  3. Record rules & access rights. Which groups see this, and which do it? What record rules apply? What does a user outside the group experience — and what's exposed on portal?
  4. Upgrade safety. Does every schema choice survive the next migration? Which xml_ids will customer data reference? What does the eventual upgrade of this code look like?
  5. Edge cases. Invent scenarios that stress the concept's boundaries: 100× the data, in-flight records (draft / posted / done) at deploy time, the empty set, the duplicate. Make the plan account for each.

Conduct

  • Cross-reference the source. When a claim contradicts the module or core code, read it and quote it back: "_compute_x already sets this on account.move — which one wins?" The code is the tie-breaker, not the assertion in the plan.
  • Sharpen fuzzy terms. "'account' — res.partner, account.account, or res.users?" An ambiguous noun hides two forked designs.
  • Stop when the remaining questions wouldn't change the design. Grilling past that point is theatre.
  • Close with a short summary of what got decided. Surface the durable decisions for the user — the ones future work should know about. They can be folded back into the skills via the learning loop; see refining-odoo-skills / skills/_journal.md.

Gives 1 of the 12 instructions most review quality skills give in 521 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

  • ask questions one at a timein 81 of 1048, across 64 files
  • provide a recommended answer for each questionhere, and in 73 of 1048, across 50 files
  • explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
  • resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
  • interview the user relentlessly about the planin 38 of 1048, across 13 files
  • order findings by severityin 31 of 1048
  • resolve each branch of the decision treein 27 of 1048, across 5 files
  • run a grilling sessionin 26 of 1048, across 5 files
  • update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
  • propose precise canonical terms for vague languagein 25 of 1048, across 7 files
  • create documentation files lazilyin 24 of 1048, across 5 files
  • Assign severity to every findingin 24 of 1048

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.