Home Assistant Dashboard Designer
Codex skill for structured Lovelace dashboards, YAML refactoring, and careful validation.
- Skill Road
- Home Assistant Dashboard Designer
Categories
Home Assistant Dashboard Designer is a public skill by CCOSTAN from the standalone Home-Assistant-Codex-Skills repository. The original Smithery registration pointed to codex_skills/homeassistant-dashboard-designer inside the larger Home-AssistantConfig repository. According to the commit history, that path was moved into a dedicated repository. The currently reachable primary source is homeassistant-dashboard-designer/SKILL.md, accompanied by reference material, a Lovelace validator, and focused tests. The skill is working guidance for Codex, not a Home Assistant server, a finished dashboard application, or a replacement for official Home Assistant documentation.
Purpose and inputs
According to the provider, the skill supports planning, updating, and refactoring Lovelace views written in YAML. Users should state the goal, the exact view or partial path under config/dashboards, screen-size requirements, and areas that must not change. When those details are missing, the instructions call for focused questions rather than an uncontrolled broad edit. The source names infrastructure, home, energy, and environment as possible intents. A view should retain one clear intent so that its layout, metrics, and entities remain understandable.
Layout and components
The primary structure uses grid and vertical-stack with limited nesting. Horizontal stacks inside grid cells, freeform positioning, and layout logic inside card-mod are avoided. The source recommends custom:button-card first, with styling kept in centralized templates. card-mod is reserved for shared visual rules. Flex Horseshoe cards and Mini Graph cards are intended for one clearly defined metric at a time. Core cards such as entities or history-graph remain fallbacks that should be justified. Templates should be reused, and new templates should not be created without explicit instruction. These rules reduce visual drift, diff size, and hard-to-review special logic.
Validation and limits
Before editing, the target repository, includes, templates, and local instructions should be read. According to the provider, an available Home Assistant MCP must be used to check entities, services, and payload fields. If the MCP is unavailable, entity or service identifiers must not be invented; repository configuration and official integration documentation should be used instead. Existing dashboard validators, a Home Assistant configuration check, and the included validator should then run. Passing a YAML check proves neither that measurements are correct nor that the resulting presentation is meaningful.
Security and responsibility
A dashboard can expose private device, presence, energy, and environmental data. File and network access should remain limited to the intended project. The skill does not request credentials, tokens, or private keys, and such values must not appear in YAML, examples, logs, or skill files. An MCP or connected model provider may process inputs and results outside the local machine; local YAML storage does not prove local model processing. Prefer read access first. Changes to dashboards, services, scenes, or automations require human confirmation, explicit target review, and a recoverable rollback before application. Automated decisions cannot reliably eliminate wrong entities, stale states, or ambiguous intent. Therefore test changes in a non-production copy first, review the diff, and keep a recovery path. Actions such as switching, restarting, locking, unlocking, or triggering an automation must not follow solely from a plausible model response. A model cannot reliably know local safety rules, resident preferences, or physical consequences. The standalone repository is MIT licensed under its published terms, but that does not replace checking the Home Assistant version, custom cards, integrations, or local operating rules. A successful browser rendering also does not prove that a device is reachable or that an automation is correct.
Installation instructions
What the Home Assistant Dashboard Designer is and why it matters
The Home Assistant Dashboard Designer is a skill from the repository Home-Assistant-Codex-Skills maintained by GitHub user CCOSTAN, which, despite the repository's name, is explicitly documented for Claude-compatible assistants and was built specifically for designing dashboards in the open-source smart home platform Home Assistant. Home Assistant renders its interfaces through a system called Lovelace, in which dashboards are described as YAML files, with individual sections organized into what are called views, and each view built from nested cards. According to its own description, the skill helps design, update, and refactor such dashboards as a consistent system, with predictable structure, reusable templates, and as little stylistic drift between individual cards as possible. For users managing their own smart home with many sensors, infrastructure components, or energy monitoring, the skill addresses a well-known pain point: without clear conventions, Lovelace configurations tend to grow into an unwieldy patchwork of individually styled cards that are hard to maintain and that introduce fresh inconsistencies with every extension.
Step 1: Prerequisites
Anyone wanting to use the skill first needs a running Home Assistant installation with YAML-based dashboard configuration in the config/dashboards directory, plus the custom Lovelace cards the skill assumes, in particular custom:button-card as the primary structural element, card-mod for shared styling adjustments, and optionally custom:flex-horseshoe-card and custom:mini-graph-card for rendering individual metrics. These additional cards are not part of the Home Assistant core and are typically installed through the community store HACS. For reliable operation, the skill also recommends using a Home Assistant MCP server, through which entity and service IDs can be validated live against the actual installation to avoid typos such as sensor.foo_bar instead of sensor.foobar. Optionally, a Stitch MCP server can also be connected, which according to the skill's description serves purely for visual ideation and must never be adopted directly as implementation code.
Step 2: Step-by-step setup
The workflow described in the skill begins by reading the existing repository conventions and version control state, for instance whether changes are applied directly, through a branch, or through a multi-stage staged-promotion process. Next comes determining the intent behind the request, where the skill distinguishes between four dashboard types, infra, home, energy, and environment, and allows only one such intent per view. Before making any substantive change, the skill requires validating every referenced entity and service, preferably through the mentioned Home Assistant MCP server, and recording that validation step in work notes before any YAML is written at all. A layout draft is then created using the allowed container types grid and vertical-stack, with the skill imposing a maximum nesting depth of two levels and explicitly excluding horizontal-stack inside grid cells. Implementation follows a clear priority order: the four tier-1 cards, button-card, card-mod, flex-horseshoe-card, and mini-graph-card, should be used first, while tier-2 cards such as entities, markdown, or iframe are only permitted as a justified fallback, accompanied by an explanatory YAML comment right next to the card. Finally, the skill requires a multi-stage validation, starting with project-specific validation scripts, moving through native Home Assistant configuration checking, and ending with its own bundled validation script for individual view files.
Security and best practices
Since faulty Lovelace configurations can, in the worst case, cause a dashboard to fail to load or to display the wrong entities, the skill places heavy emphasis on validation before any change is applied. The rule that stands out most is that entity and service IDs must never be invented: if the Home Assistant MCP server is unavailable, the skill's description requires falling back on the repository configuration or the official integration documentation instead, and explicitly asking the user about anything that remains unresolved. Equally important is how the optional Stitch tool is handled, which is explicitly meant only for inspiring visual hierarchy and spacing; the skill explicitly forbids adopting Stitch's output directly as implementation, because that could introduce unsafe or invalid YAML structures. The skill also mandates that, on validation failure, work must stop and the error output be surfaced to the user rather than simply applying an invalid configuration, which considerably reduces the risk of a broken live dashboard.
Practical example and limits
A typical example given in the skill's own documentation is a request to refactor an existing view for a MariaDB database server to match the button-card-based system already used in other infrastructure views, without creating new templates, using four columns on desktop and two on mobile. In this case the skill would first check the existing templates in the repository, reuse matching ones, validate every referenced sensor, and only then implement the layout according to the grid rules. One clear limit of the skill is that it explicitly does not create new card templates unless specifically instructed to, instead either using the closest existing template when no suitable one exists or actively asking for permission to add one. Its scope is likewise limited to Home Assistant's own Lovelace YAML structures; it does not substitute for general web development or for deeper customization of Home Assistant's underlying frontend architecture. For users with growing, increasingly cluttered dashboards, though, it remains an effective tool for systematically restoring consistency and maintainability instead of patching things up card by card.
- Provider
- CCOSTAN
- License
- MIT
- Last reviewed
- 10.09.2026
Repository and documentation
Categories
Compatible with
Related guides
Guides and background related to this entry.