← ClaudeAtlas

ha-dev-workflow-applylisted

Applies and validates the HA code-style / strict-typing / validation workflow (spec/ha/dev-workflow) against an existing HA Custom Integration — Ruff format, ordered imports, f-strings (logging excepted), file-header docstrings, full type annotations, a local mypy-strict profile as the platinum strict-typing bridge, hassfest validation, and voluptuous config validation for YAML-configurable platforms — then reports CONFORMANT / NEEDS-WORK against the spec's MUST rules keyed to a target tier (bronze floor to platinum). Activate on "apply the HA dev workflow", "make this integration strict-typing / platinum-ready", "run ruff + mypy strict + hassfest", or equivalent German requests. Do not activate for a read-only quality-scale tier check (ha-quality-scale-audit), a security audit (ha-security-audit), the pytest harness (ha-test-harness-augment), devcontainer / Kind setup (ha/dev-environment), or deploying to a live HA instance.
nolte/claude-home-assistant · ★ 1 · AI & Automation · score 68
Install: claude install-skill nolte/claude-home-assistant
# HA Dev-Workflow Apply Spec: `spec/claude/ha-dev-workflow-apply/en.md` (EN canonical) / `spec/claude/ha-dev-workflow-apply/de.md` (DE translation). Grounding spec: `spec/ha/dev-workflow/en.md` — this skill operationalises that spec's MUST rules; read it for the pinned HA-original rules. This skill is the owning skill of `spec/ha/dev-workflow`: it **applies** the HA coding workflow (style, strict typing, validation) to an existing Custom Integration and **validates** the result, closing the spec-vs-skill gap where the Platinum tier of `ha-integration-solution` previously resolved to a bare checklist item. ## Why this is a skill, not an agent - **Human-visible apply surface** — like the sibling `ha-translation-sync`, the user invokes it directly, watches the format/typing/validation edits land, and reads the CONFORMANT / NEEDS-WORK report; a skill keeps that on the visible command surface. - **Bounded, tool-driven work** — it runs `ruff`, `mypy`, and `hassfest` over one integration and applies mechanical fixes; the read/edit volume fits inline, so the pressure that biases toward an isolated agent does not apply. - **Dispatched by an orchestrator** — `ha-integration-solution` dispatches it for `target_tier: platinum`; the skill-orchestrates-skill default keeps it in skill form. - Counter-dimension considered: the strict-typing pass could run as a fire-and-forget agent, but the annotation edits and the mypy-strict decisions should stay visible and reviewable in the user cont