What is odoo-ui-review?

A review guide for a running Odoo interface, covering appearance, user interactions, stability, accessibility, performance, and consistency with the design system. It bases findings on browser evidence such as screenshots, console messages, Lighthouse results, and page structure.

Use it to review individual Odoo screens for layout issues, broken controls, browser errors, accessibility problems, slow performance, and mismatched theming.

It helps teams evaluate what users actually see and can do, rather than reviewing source code alone. It brings visual, functional, accessibility, and performance problems into one review.

odoo-ui-review — Skill for Claude Code by Viindoo

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Viindoo/odoo-mcp-client

Claude Code

/plugin install odoo-ai-agents

Made for: Claude Code.

Or install odoo-ai-agents, the plugin that ships this one along with the rest of its 51 skills, 8 commands, 26 agents, 8 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-ui-review/github.svg)](https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-ui-review)

Your own site

<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-ui-review"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-ui-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/viindoo/odoo-mcp-client/odoo-ui-review"><img src="https://agentmods.dev/badge/skills/viindoo/odoo-mcp-client/odoo-ui-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 234 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,516 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00234	$0.02516
Opus 5	$0.00117	$0.01258
Sonnet 5	$0.00047	$0.00503
Haiku 4.5	$0.00023	$0.00252

Measured 7d ago against content hash f869a3e76dea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

odoo-ui-review scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`find <ISOLATE_DIR>/visual/screenshots/ -mindepth 1 -maxdepth 1 -type d -mmin +43200 -exec rm -rf {} +`

plugins/odoo-ai-agents/skills/odoo-ui-review/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

UI/UX reviewer for rendered Odoo screens. Judges the running interface - what a user sees and clicks - across six lenses: aesthetics, functional correctness, stability, accessibility, performance, and design-system fidelity (does the screen match the Odoo design system and the project mockup, or is it off-theme?). Evidence-based: every finding cites a screenshot, a console message, a Lighthouse score, a computed-style readout, or a snapshot node - never an unverified impression.

Out of Scope

Investigating WHY a screen is broken / errors / blank render → odoo-debug
Comparing two states or builds for visual drift / regression → odoo-visual-regression
Executing a full workflow / QA-ing the affected cluster across roles with a PASS/FAIL verdict → odoo-acceptance (this skill rates how ONE rendered screen looks/behaves; it does not drive CRUD/role flows or adjudicate an acceptance oracle)
Recording a demo or marketing walkthrough video → odoo-demo-recording
Writing or changing Odoo frontend JS/OWL source → odoo-coding
Source-level code review (Python/JS/XML) → odoo-code-review

When to invoke

Main agent launches the odoo-ui-reviewer agent as a subagent when the user has a running Odoo instance and wants a verdict on how a rendered screen looks and behaves. The agent drives a live browser (chrome-devtools MCP) to capture the screen, exercise controls, run a Lighthouse audit, sweep responsive breakpoints, then ground every styling defect in the codebase via OSM. It runs as an autonomous agent (not inline) because the review needs many sequential+parallel browser/MCP round-trips.

Brief context - Odoo UI review pitfalls

Key things the agent watches for:

Selector era by version - v17+ backend uses /odoo with .o_form_view / .o_list_view / .o_kanban_view; older versions use /web. Pin the version before navigating.
Login first - Odoo screens are session-gated; the agent logs in before capturing.
Six-lens coverage - a finding in one lens (e.g. a console error) often explains a defect in another (a control that silently fails); cross-reference them.
Source-grounded fixes - a styling defect is only actionable once the owning module/stylesheet is named, so the fix lands in the right place rather than as an inline override.
Design-system / theme lens - run a token-reality check per ${CLAUDE_PLUGIN_ROOT}/skills/_shared/odoo-frontend-fidelity.md: read getComputedStyle on :root + representative elements and flag empty/transparent surfaces, self-referential CSS custom properties, --bs-* references (Odoo sets $variable-prefix:'', so Bootstrap --bs-* runtime vars are absent across v16+ confirmed through v19 - reference --primary / --o-color-* instead), hardcoded palette, and divergence from the mockup. Emit remediation as a token+file pointer, not an inline patch.

Read the full file on GitHub · 147 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

evals/evals.json 10.0 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 147 lines · 234 tokens per session scan C f869a3e76dea

Subscribe to this mod's changes

odoo-ui-review is a skill published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed 4d ago), licensed MIT. It adds 234 tokens to every session and 2,516 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Design and UX

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

odoo-ui-review