[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AB48WMPGDK2REBC3WS8T32":3,"skill-same:01M7AB48WMPGDK2REBC3WS8T32":53},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M7AB48WMPGDK2REBC3WS8T32","ha-quality-review",null,"Perform a structured quality review of this Home Assistant custom integration, either as a full audit or scoped to a diff. Use when asked to \"review the integration\", \"audit the code\", \"check quality scale\", \"are we bronze\u002Fsilver\u002Fgold\", \"is this ready to release\", \"review my changes\", \"what's missing before publishing\", or before opening a pull request that touches integration code. Covers running the automated gates first, then auditing architecture, the Integration Quality Scale rules, error handling, security, performance, user experience, and documentation — and reporting findings ranked by severity with concrete fixes. SYMPTOMS — load this if you are about to: report a review that only restates linter output; claim real-device testing that did not happen; give a finding without a file path and a fix; or judge quality without running `script\u002Fhassfest` and the test suite first.","amg0\u002Fha_ksenia","amg0","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F16444411?v=4","01M7AAZDRNF8BXHM6GAN9QWJ41","01M7AAZDSEHKPEWK6PKK22S2NN",0,"MIT","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-quality-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ha-quality-review\ndescription: >-\n  Perform a structured quality review of this Home Assistant custom integration, either as a full audit or scoped\n  to a diff. Use when asked to \"review the integration\", \"audit the code\", \"check quality scale\", \"are we\n  bronze\u002Fsilver\u002Fgold\", \"is this ready to release\", \"review my changes\", \"what's missing before publishing\", or\n  before opening a pull request that touches integration code. Covers running the automated gates first, then\n  auditing architecture, the Integration Quality Scale rules, error handling, security, performance, user\n  experience, and documentation — and reporting findings ranked by severity with concrete fixes. SYMPTOMS — load\n  this if you are about to: report a review that only restates linter output; claim real-device testing that did\n  not happen; give a finding without a file path and a fix; or judge quality without running `script\u002Fhassfest` and\n  the test suite first.\n---\n\n# Review the integration\n\nA review that only restates the linter is worthless. Run the machines first, then spend your attention on what they\ncannot see: layering, failure behaviour, and whether a user would understand what this integration does.\n\n## 0. Scope the review\n\nAsk, or infer from the request:\n\n- **Full audit** of the integration, or **diff review** of the current branch?\n- Is there a target tier (this project aims for Silver, ideally Gold)?\n\nFor a diff review: `git diff main...HEAD --stat`, then read the changed files in full — not just the hunks.\n\nWhen the diff is an open pull request, read what others already said before adding to it:\n`gh pr view \u003Cnumber> --comments` and `gh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cnumber>\u002Fcomments` for the inline ones. Every\nearlier finding — a human's, a bot's, another agent's — is either fixed in the current head, answered in the thread,\nor still open; report the open ones instead of rediscovering them, and do not repeat what was already settled.\n\n## 1. Automated gates (always first)\n\n```bash\nscript\u002Flint          # ruff format+fix, shfmt, prettier\u002Fmarkdownlint, yamllint, zizmor, shellcheck\nscript\u002Ftype-check    # pyright — never auto-fixed\nscript\u002Fhassfest      # manifest, services.yaml, translations, integration structure\nscript\u002Ftest --cov-html\n```\n\nAnything these report is a finding, not something to fix silently mid-review — but do note that `script\u002Flint` already\nauto-heals formatting, so only its **remaining** output counts.\n\n## 2. Architecture\n\n- Layering is Entity → Coordinator → source. Any entity importing `api\u002F` directly, or any coordinator holding HTTP\n  details, is a finding.\n- Package structure matches the fixed set (`api\u002F`, `coordinator\u002F`, `config_flow_handler\u002F`, `entity\u002F`, `entity_utils\u002F`,\n  `\u003Cplatform>\u002F`, `service_actions\u002F`, `utils\u002F`). A `helpers\u002F`, `common\u002F`, `shared\u002F`, or `lib\u002F` package is a finding.\n- Files are 200–400 lines, one entity class per file.\n- Runtime state lives in `entry.runtime_data`, never `hass.data[DOMAIN]`.\n- No circular imports; `TYPE_CHECKING` guards for type-only imports.\n\n**Two upstream requirements this project deliberately does not meet.** Neither is a finding here, and both should be\nstated as decisions rather than silently passed over:\n\n- Core requires all device or service communication to be wrapped in a PyPI library. As a custom integration this\n  project allows an in-repo client (`AGENTS.md` § Custom Integration Flexibility) — with the consequence that the\n  client would have to be extracted before this could ever be submitted to Core.\n- Core wants the coordinator in `coordinator.py`, the base entity in `entity.py` and actions in `services.py`. This\n  project's `coordinator\u002F`, `entity\u002F` and `service_actions\u002F` packages are the accepted equivalents.\n\n## 3. Quality scale audit\n\n| File                                                                     | When to read                                                                      |\n| ------------------------------------------------------------------------ | --------------------------------------------------------------------------------- |\n| [`references\u002Fquality-scale-rules.md`](references\u002Fquality-scale-rules.md) | Auditing a tier. All 54 rule identifiers with one-line criteria, grouped by tier. |\n\nWalk the rules for the target tier and report each as **pass \u002F fail \u002F not applicable**. For every fail, name the file\nand the fix.\n\nHome Assistant reports every custom integration's tier as `custom`, whatever `quality_scale` in the manifest says, so\nthe tier is a self-assessment, not something Home Assistant checks. A claimed Silver or above still needs at least one\nentry in `codeowners` (`integration-owner`).\n\nThe rules most often missed in this codebase's shape:\n\n- `action-setup` — actions registered in `async_setup()`, not per entry.\n- `parallel-updates` — every platform package's `__init__.py` defines `PARALLEL_UPDATES` at module level: `0` on a\n  read-only coordinator platform, a value the device can take on platforms that send commands.\n- `entity-translations` \u002F `icon-translations` — no hardcoded `name=` or `icon=` in `EntityDescription`.\n- `exception-translations` — no English strings inside raised exceptions.\n- `log-when-unavailable` — the coordinator must not log on every failed poll.\n- `entity-category` \u002F `entity-disabled-by-default` — diagnostics entities are marked and often disabled by default.\n- `stale-devices` \u002F `dynamic-devices` — devices appear and disappear with upstream reality.\n\n## 4. Code quality\n\n| File                                                               | When to read                                                                                                                            |\n| ------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------- |\n| [`references\u002Fcore-lint-checks.md`](references\u002Fcore-lint-checks.md) | Any review of integration code. The integration-specific checks Home Assistant Core lints in its own CI and this repository cannot run. |\n\nLook for the failure modes linters miss:\n\n- **Typing** — full annotations, `-> None` on procedures, no bare `Any` where a `TypedDict` or dataclass is meant,\n  no `from __future__ import annotations` (banned on Python 3.14).\n- **Async** — no blocking I\u002FO in the event loop (`requests`, `open()`, `time.sleep`, sync SDK calls); every network call\n  has a timeout; `asyncio.timeout` rather than a deprecated helper.\n- **Exceptions** — specific types, never bare `except:`; `raise ... from err` to preserve the chain; the coordinator\n  translates client exceptions into `UpdateFailed` \u002F `ConfigEntryAuthFailed` correctly.\n- **Properties** — no I\u002FO, no raising, no side effects.\n- **Constants** — no magic numbers or duplicated strings; reuse `homeassistant.const` names.\n- **Logging** — lazy `%s` formatting, `debug` for the normal path, no secrets in any log line at any level.\n\nPatterns Core reviewers catch that no tool does:\n\n- **Signs of unreviewed AI output** — fixes for problems that do not exist, defensive code for conditions that cannot\n  happen, test fixtures changed without a change in behaviour, or a polished description on top of code that shows a\n  basic misunderstanding. Agent-written code in this repository is held to the same test.\n- **Truthiness on device values** — `bool(value)` or `int(value)` on something that can be `None` or a string:\n  `bool(None)` turns a missing value into \"off\", and `bool(\"0\")` is `True`. Convert explicitly (`value == \"1\"`).\n- **`entry.runtime_data` read where setup may have failed** — error paths, unload, and anything iterating\n  `async_entries()`. It is set only for a loaded entry; use `async_loaded_entries()` and handle none.\n- **Lifecycle boundaries** — every listener, timer and connection opened in setup or `async_added_to_hass` is released\n  through `entry.async_on_unload` \u002F `self.async_on_remove`, and connections also close on Home Assistant stop. A\n  `try` that wraps everything is not a fix; small `try` blocks around the call that can raise are.\n\n## 5. Security\n\nCheck each; the rule and how to comply live in the linked file.\n\n- **Credentials** only in `entry.data`, and the data\u002Foptions split right for `config-flow` —\n  [`blueprint.config_flow`](..\u002F..\u002Finstructions\u002Fblueprint.config_flow.instructions.md#data-vs-options).\n- **Diagnostics** redact the whole payload, and `TO_REDACT` still matches the API response —\n  [`blueprint.diagnostics`](..\u002F..\u002Finstructions\u002Fblueprint.diagnostics.instructions.md).\n- **TLS verification** on by default; a `CONF_VERIFY_SSL` option defaults to `True`, and no secret has a schema\n  default.\n- **Log lines** mask keys and IDs with `partial_redact()` — [`blueprint.python`](..\u002F..\u002Finstructions\u002Fblueprint.python.instructions.md).\n- **Admin-only actions**, and **caller-supplied paths** checked with `is_allowed_path()` —\n  [`blueprint.service_actions`](..\u002F..\u002Finstructions\u002Fblueprint.service_actions.instructions.md).\n- **Webhooks** called from the LAN are `local_only` —\n  [`blueprint.coordinator`](..\u002F..\u002Finstructions\u002Fblueprint.coordinator.instructions.md).\n- Data from a device or service never reaches `eval()`, `exec()` or a shell.\n- **Dependencies** pinned identically in `manifest.json` and `requirements.txt`, and reviewed for supply-chain risk —\n  [`blueprint-tooling`](..\u002Fblueprint-tooling\u002FSKILL.md).\n\n## 6. Performance\n\n- One coordinator poll serves all entities; no per-entity API calls.\n- Interval appropriate for the source ([`ha-coordinator-debug`](..\u002Fha-coordinator-debug\u002FSKILL.md)), a constant —\n  a polling-interval field is a finding ([`blueprint.config_flow`](..\u002F..\u002Finstructions\u002Fblueprint.config_flow.instructions.md)),\n  and removing one users already set goes through [`ha-breaking-changes`](..\u002Fha-breaking-changes\u002FSKILL.md).\n- No unnecessary `async_write_ha_state()`; no work in `__init__`.\n- Data structures let entities read by key rather than scanning lists.\n\n## 7. User experience\n\n- Config flow validates before creating the entry and shows recoverable, translated errors.\n- Entity names read well in the UI with `has_entity_name` (no repeated device name).\n- Units, device classes, and state classes are set so history and statistics work.\n- Failures surface as repair issues or reauth flows rather than silent unavailability.\n- For an integration that depends on a remote endpoint, consider `system_health.py`: a `@callback async_register`\n  that calls `register.async_register_info(...)`, whose info callback returns a dict whose values may be coroutines\n  (the frontend shows a spinner and resolves them). `system_health.async_check_can_reach_url(hass, ENDPOINT)` covers\n  the common case, and every key needs a `system_health.info.\u003Ckey>` translation. It turns \"it is broken\" into\n  \"the API is unreachable\" on the user's own system page.\n\n## 8. Documentation and release hygiene\n\n- `README.md`, `docs\u002Fuser\u002F` describe what actually exists — not the blueprint's placeholder text.\n- The `docs-*` rules are met by the integration's own documentation — which file covers which rule:\n  [`quality-scale-rules.md`](references\u002Fquality-scale-rules.md#where-the-docs--rules-are-met).\n- `manifest.json`: correct `integration_type`, `iot_class`, `documentation`, `issue_tracker`, `codeowners`, `version`.\n- Publishing readiness, when it is meant to be listed — repository preconditions, brand images, the CI gates the\n  catalog requires: [`ha-marketplace`](..\u002Fha-marketplace\u002FSKILL.md) has the checklist.\n- Architectural choices worth remembering are in `docs\u002Fdevelopment\u002FDECISIONS.md`\n  ([`ha-planning`](..\u002Fha-planning\u002FSKILL.md)).\n- Breaking changes carry a migration path ([`ha-breaking-changes`](..\u002Fha-breaking-changes\u002FSKILL.md)).\n\n## Report format\n\nRank by severity and be specific. A finding without a file path and a fix is noise.\n\n```markdown\n## Summary\n\n\u003C2–3 sentences: overall state, current effective tier, biggest risk.>\n\n## Critical — must fix before release\n\n### 1. \u003CTitle>\n\n- **Where:** `custom_components\u002F\u003Cdomain>\u002Fcoordinator\u002Fbase.py:82`\n- **Problem:** \u003Cwhat is wrong and what it breaks for a user>\n- **Fix:** \u003Cconcrete change>\n\n## Warnings — should fix\n\n## Suggestions — nice to have\n\n## Quality scale\n\n| Tier | Status | Failing rules |\n| ---- | ------ | ------------- |\n\n## Verified\n\n\u003CWhat you actually ran, and what you could not verify — e.g. no real device available.>\n```\n\nBe honest in the last section. Do not describe checks you did not run, and do not imply real-device testing happened\nwhen it did not — that is an explicit rule of this project's [`AI_POLICY.md`](..\u002F..\u002F..\u002FAI_POLICY.md).\n\nVerify each finding by running something — a gate, a test, a grep of the installed Home Assistant source — rather than\nfrom memory or from how the code reads. A finding you could not verify that way stays in the report, marked\n**unverified**, with what would confirm it.\n\n## After the review\n\nReport findings; do not silently fix them unless the developer asked for fixes. If they did, fix in severity order, run\n`script\u002Flint && script\u002Ftype-check && script\u002Ftest` after each group, and state what you changed.\n","# Review the integration\n\nA review that only restates the linter is worthless. Run the machines first, then spend your attention on what they\ncannot see: layering, failure behaviour, and whether a user would understand what this integration does.\n\n## 0. Scope the review\n\nAsk, or infer from the request:\n\n- **Full audit** of the integration, or **diff review** of the current branch?\n- Is there a target tier (this project aims for Silver, ideally Gold)?\n\nFor a diff review: `git diff main...HEAD --stat`, then read the changed files in full — not just the hunks.\n\nWhen the diff is an open pull request, read what others already said before adding to it:\n`gh pr view \u003Cnumber> --comments` and `gh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003Cnumber>\u002Fcomments` for the inline ones. Every\nearlier finding — a human's, a bot's, another agent's — is either fixed in the current head, answered in the thread,\nor still open; report the open ones instead of rediscovering them, and do not repeat what was already settled.\n\n## 1. Automated gates (always first)\n\n```bash\nscript\u002Flint          # ruff format+fix, shfmt, prettier\u002Fmarkdownlint, yamllint, zizmor, shellcheck\nscript\u002Ftype-check    # pyright — never auto-fixed\nscript\u002Fhassfest      # manifest, services.yaml, translations, integration structure\nscript\u002Ftest --cov-html\n```\n\nAnything these report is a finding, not something to fix silently mid-review — but do note that `script\u002Flint` already\nauto-heals formatting, so only its **remaining** output counts.\n\n## 2. Architecture\n\n- Layering is Entity → Coordinator → source. Any entity importing `api\u002F` directly, or any coordinator holding HTTP\n  details, is a finding.\n- Package structure matches the fixed set (`api\u002F`, `coordinator\u002F`, `config_flow_handler\u002F`, `entity\u002F`, `entity_utils\u002F`,\n  `\u003Cplatform>\u002F`, `service_actions\u002F`, `utils\u002F`). A `helpers\u002F`, `common\u002F`, `shared\u002F`, or `lib\u002F` package is a finding.\n- Files are 200–400 lines, one entity class per file.\n- Runtime state lives in `entry.runtime_data`, never `hass.data[DOMAIN]`.\n- No circular imports; `TYPE_CHECKING` guards for type-only imports.\n\n**Two upstream requirements this project deliberately does not meet.** Neither is a finding here, and both should be\nstated as decisions rather than silently passed over:\n\n- Core requires all device or service communication to be wrapped in a PyPI library. As a custom integration this\n  project allows an in-repo client (`AGENTS.md` § Custom Integration Flexibility) — with the consequence that the\n  client would have to be extracted before this could ever be submitted to Core.\n- Core wants the coordinator in `coordinator.py`, the base entity in `entity.py` and actions in `services.py`. This\n  project's `coordinator\u002F`, `entity\u002F` and `service_actions\u002F` packages are the accepted equivalents.\n\n## 3. Quality scale audit\n\n| File                                                                     | When to read                                                                      |\n| ------------------------------------------------------------------------ | --------------------------------------------------------------------------------- |\n| [`references\u002Fquality-scale-rules.md`](references\u002Fquality-scale-rules.md) | Auditing a tier. All 54 rule identifiers with one-line criteria, grouped by tier. |\n\nWalk the rules for the target tier and report each as **pass \u002F fail \u002F not applicable**. For every fail, name the file\nand the fix.\n\nHome Assistant reports every custom integration's tier as `custom`, whatever `quality_scale` in the manifest says, so\nthe tier is a self-assessment, not something Home Assistant checks. A claimed Silver or above still needs at least one\nentry in `codeowners` (`integration-owner`).\n\nThe rules most often missed in this codebase's shape:\n\n- `action-setup` — actions registered in `async_setup()`, not per entry.\n- `parallel-updates` — every platform package's `__init__.py` defines `PARALLEL_UPDATES` at module level: `0` on a\n  read-only coordinator platform, a value the device can take on platforms that send commands.\n- `entity-translations` \u002F `icon-translations` — no hardcoded `name=` or `icon=` in `EntityDescription`.\n- `exception-translations` — no English strings inside raised exceptions.\n- `log-when-unavailable` — the coordinator must not log on every failed poll.\n- `entity-category` \u002F `entity-disabled-by-default` — diagnostics entities are marked and often disabled by default.\n- `stale-devices` \u002F `dynamic-devices` — devices appear and disappear with upstream reality.\n\n## 4. Code quality\n\n| File                                                               | When to read                                                                                                                            |\n| ------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------- |\n| [`references\u002Fcore-lint-checks.md`](references\u002Fcore-lint-checks.md) | Any review of integration code. The integration-specific checks Home Assistant Core lints in its own CI and this repository cannot run. |\n\nLook for the failure modes linters miss:\n\n- **Typing** — full annotations, `-> None` on procedures, no bare `Any` where a `TypedDict` or dataclass is meant,\n  no `from __future__ import annotations` (banned on Python 3.14).\n- **Async** — no blocking I\u002FO in the event loop (`requests`, `open()`, `time.sleep`, sync SDK calls); every network call\n  has a timeout; `asyncio.timeout` rather than a deprecated helper.\n- **Exceptions** — specific types, never bare `except:`; `raise ... from err` to preserve the chain; the coordinator\n  translates client exceptions into `UpdateFailed` \u002F `ConfigEntryAuthFailed` correctly.\n- **Properties** — no I\u002FO, no raising, no side effects.\n- **Constants** — no magic numbers or duplicated strings; reuse `homeassistant.const` names.\n- **Logging** — lazy `%s` formatting, `debug` for the normal path, no secrets in any log line at any level.\n\nPatterns Core reviewers catch that no tool does:\n\n- **Signs of unreviewed AI output** — fixes for problems that do not exist, defensive code for conditions that cannot\n  happen, test fixtures changed without a change in behaviour, or a polished description on top of code that shows a\n  basic misunderstanding. Agent-written code in this repository is held to the same test.\n- **Truthiness on device values** — `bool(value)` or `int(value)` on something that can be `None` or a string:\n  `bool(None)` turns a missing value into \"off\", and `bool(\"0\")` is `True`. Convert explicitly (`value == \"1\"`).\n- **`entry.runtime_data` read where setup may have failed** — error paths, unload, and anything iterating\n  `async_entries()`. It is set only for a loaded entry; use `async_loaded_entries()` and handle none.\n- **Lifecycle boundaries** — every listener, timer and connection opened in setup or `async_added_to_hass` is released\n  through `entry.async_on_unload` \u002F `self.async_on_remove`, and connections also close on Home Assistant stop. A\n  `try` that wraps everything is not a fix; small `try` blocks around the call that can raise are.\n\n## 5. Security\n\nCheck each; the rule and how to comply live in the linked file.\n\n- **Credentials** only in `entry.data`, and the data\u002Foptions split right for `config-flow` —\n  [`blueprint.config_flow`](..\u002F..\u002Finstructions\u002Fblueprint.config_flow.instructions.md#data-vs-options).\n- **Diagnostics** redact the whole payload, and `TO_REDACT` still matches the API response —\n  [`blueprint.diagnostics`](..\u002F..\u002Finstructions\u002Fblueprint.diagnostics.instructions.md).\n- **TLS verification** on by default; a `CONF_VERIFY_SSL` option defaults to `True`, and no secret has a schema\n  default.\n- **Log lines** mask keys and IDs with `partial_redact()` — [`blueprint.python`](..\u002F..\u002Finstructions\u002Fblueprint.python.instructions.md).\n- **Admin-only actions**, and **caller-supplied paths** checked with `is_allowed_path()` —\n  [`blueprint.service_actions`](..\u002F..\u002Finstructions\u002Fblueprint.service_actions.instructions.md).\n- **Webhooks** called from the LAN are `local_only` —\n  [`blueprint.coordinator`](..\u002F..\u002Finstructions\u002Fblueprint.coordinator.instructions.md).\n- Data from a device or service never reaches `eval()`, `exec()` or a shell.\n- **Dependencies** pinned identically in `manifest.json` and `requirements.txt`, and reviewed for supply-chain risk —\n  [`blueprint-tooling`](..\u002Fblueprint-tooling\u002FSKILL.md).\n\n## 6. Performance\n\n- One coordinator poll serves all entities; no per-entity API calls.\n- Interval appropriate for the source ([`ha-coordinator-debug`](..\u002Fha-coordinator-debug\u002FSKILL.md)), a constant —\n  a polling-interval field is a finding ([`blueprint.config_flow`](..\u002F..\u002Finstructions\u002Fblueprint.config_flow.instructions.md)),\n  and removing one users already set goes through [`ha-breaking-changes`](..\u002Fha-breaking-changes\u002FSKILL.md).\n- No unnecessary `async_write_ha_state()`; no work in `__init__`.\n- Data structures let entities read by key rather than scanning lists.\n\n## 7. User experience\n\n- Config flow validates before creating the entry and shows recoverable, translated errors.\n- Entity names read well in the UI with `has_entity_name` (no repeated device name).\n- Units, device classes, and state classes are set so history and statistics work.\n- Failures surface as repair issues or reauth flows rather than silent unavailability.\n- For an integration that depends on a remote endpoint, consider `system_health.py`: a `@callback async_register`\n  that calls `register.async_register_info(...)`, whose info callback returns a dict whose values may be coroutines\n  (the frontend shows a spinner and resolves them). `system_health.async_check_can_reach_url(hass, ENDPOINT)` covers\n  the common case, and every key needs a `system_health.info.\u003Ckey>` translation. It turns \"it is broken\" into\n  \"the API is unreachable\" on the user's own system page.\n\n## 8. Documentation and release hygiene\n\n- `README.md`, `docs\u002Fuser\u002F` describe what actually exists — not the blueprint's placeholder text.\n- The `docs-*` rules are met by the integration's own documentation — which file covers which rule:\n  [`quality-scale-rules.md`](references\u002Fquality-scale-rules.md#where-the-docs--rules-are-met).\n- `manifest.json`: correct `integration_type`, `iot_class`, `documentation`, `issue_tracker`, `codeowners`, `version`.\n- Publishing readiness, when it is meant to be listed — repository preconditions, brand images, the CI gates the\n  catalog requires: [`ha-marketplace`](..\u002Fha-marketplace\u002FSKILL.md) has the checklist.\n- Architectural choices worth remembering are in `docs\u002Fdevelopment\u002FDECISIONS.md`\n  ([`ha-planning`](..\u002Fha-planning\u002FSKILL.md)).\n- Breaking changes carry a migration path ([`ha-breaking-changes`](..\u002Fha-breaking-changes\u002FSKILL.md)).\n\n## Report format\n\nRank by severity and be specific. A finding without a file path and a fix is noise.\n\n```markdown\n## Summary\n\n\u003C2–3 sentences: overall state, current effective tier, biggest risk.>\n\n## Critical — must fix before release\n\n### 1. \u003CTitle>\n\n- **Where:** `custom_components\u002F\u003Cdomain>\u002Fcoordinator\u002Fbase.py:82`\n- **Problem:** \u003Cwhat is wrong and what it breaks for a user>\n- **Fix:** \u003Cconcrete change>\n\n## Warnings — should fix\n\n## Suggestions — nice to have\n\n## Quality scale\n\n| Tier | Status | Failing rules |\n| ---- | ------ | ------------- |\n\n## Verified\n\n\u003CWhat you actually ran, and what you could not verify — e.g. no real device available.>\n```\n\nBe honest in the last section. Do not describe checks you did not run, and do not imply real-device testing happened\nwhen it did not — that is an explicit rule of this project's [`AI_POLICY.md`](..\u002F..\u002F..\u002FAI_POLICY.md).\n\nVerify each finding by running something — a gate, a test, a grep of the installed Home Assistant source — rather than\nfrom memory or from how the code reads. A finding you could not verify that way stays in the report, marked\n**unverified**, with what would confirm it.\n\n## After the review\n\nReport findings; do not silently fix them unless the developer asked for fixes. If they did, fix in severity order, run\n`script\u002Flint && script\u002Ftype-check && script\u002Ftest` after each group, and state what you changed.\n",{"name":5,"description":7},"main","3a408474735fec0ac5d62b86fc842420a899e090",".agents\u002Fskills\u002Fha-quality-review","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia","https:\u002F\u002Fgithub.com\u002Famg0","2026-11-15 01:01:02",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add amg0\u002Fha_ksenia --skill ha-quality-review",{"tool":35,"command":36},"bunx","bunx skills add amg0\u002Fha_ksenia --skill ha-quality-review",{"tool":38,"command":39},"pnpm","pnpm dlx skills add amg0\u002Fha_ksenia --skill ha-quality-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-quality-review\u002FSKILL.md",true,[43,49],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"references\u002Fcore-lint-checks.md","REFERENCE","参考文档",16131,"https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-quality-review\u002Freferences\u002Fcore-lint-checks.md",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fquality-scale-rules.md",21779,"https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-quality-review\u002Freferences\u002Fquality-scale-rules.md",[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M7AB5RYA92GRR64CP6VMWV6Z","issues","Triage\u002Ffix the GitHub issue backlog via branch + PR, with auto-merge on green CI for this session.","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fissues\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M7AB5G6DR1KGAPRT7JHDCD2Y","ha-translations","Add or fix user-facing strings for this Home Assistant custom integration — translations\u002Fen.json and other languages, icons.json, entity names and states, config flow labels and errors, service action descriptions, exception messages, and repair issue text. Use when asked to \"update translations\", \"add a translation key\", \"translate\", \"fix the entity name\", \"add strings for the new sensor\u002Faction\u002Foption\", \"add icons\", or when hassfest reports a missing or unused translation key. Covers the key structure, which keys each feature needs, placeholders, the icons.json contract, and the project's strict rule about only touching en.json. SYMPTOMS — load this if you are about to: write user-facing English into Python; edit a language file other than `en.json`; add an entity without its `entity.\u003Cplatform>.\u003Ckey>.name` key; skip `data_description` on a config flow field; or set `icon=` instead of using `icons.json`.","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-translations\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M7AB56JBRMF19W4N2NG9Y5GW","ha-testing","Write, fix, or extend automated tests for this Home Assistant custom integration using pytest and pytest-homeassistant-custom-component. Use when asked to \"add tests\", \"write a test\", \"the tests fail\", \"improve coverage\", \"add a regression test\", \"test the config flow\", \"update snapshots\", or when a behavioural change needs verification before it can be called done. Covers the tests\u002F layout, the conftest.py fixtures this project needs, mocking the API client, config flow and entity test patterns, registry assertions, syrupy snapshots, freezing time, and the script\u002Ftest commands. SYMPTOMS — load this if you are about to: instantiate an entity class directly instead of asserting on `hass.states`; write a test without `enable_custom_integrations`; use `time.sleep` instead of `async_fire_time_changed`; silence a DeprecationWarning to make the suite pass; or commit a snapshot you have not read.","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-testing\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M7AB4V9XKDYRDCRHEA68GRZ5","ha-service-action","Add, change, or remove a Home Assistant service action (also called a \"service\" or \"action\") in this custom integration. Use when asked to \"add a service\", \"add an action\", \"expose X as a service call\", \"add a service that returns data\", \"make this callable from an automation\", or when editing services.yaml, the service_actions\u002F package, service schemas, service response data, or the async_setup() registration. Covers the services.yaml contract, probatio schemas, selectors, entity\u002Fdevice targeting, response data, translated error messages, and the Bronze quality-scale rule that actions must be registered in async_setup(). SYMPTOMS — load this if you are about to: register an action in `async_setup_entry()`; add a `services.yaml` field without a selector; add an `entity_id` field where `target:` belongs; raise a plain English `HomeAssistantError`; or swallow an action failure into a log line.","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-service-action\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M7AB4J65REZ9T9VS9MQH73CC","ha-release","Cut a release of this Home Assistant custom integration, or prepare the commits that feed it. Use when asked to \"release\", \"cut a version\", \"bump the version\", \"prepare release notes\", \"what will the next version be\", \"write a commit message\", \"why didn't release-please pick this up\", or when reviewing whether a change is user-facing. Covers the Conventional Commits rules commitlint enforces here, how release-please derives the version and changelog, the pre-1.0 bump rules, script\u002Fversion and script\u002Frelease-notes, skipping a commit from the notes, and the commit rules this project enforces for agents. SYMPTOMS — load this if you are about to: commit without an explicit request; offer to `git push`; label a user-facing fix as `chore` (chore, like every hidden type, never reaches the changelog and never triggers a release); write a commit subject over 100 characters or in sentence case; or edit the version in `manifest.json` by hand.","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-release\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M7AB3Z99XZ5PN9Z59PJG52BW","ha-planning","Plan a large change to this Home Assistant custom integration before writing code, or record an architectural decision. Use when asked to \"create a plan\", \"plan this feature\", \"how should we approach\", \"propose an architecture\", \"write an ADR\", \"document this decision\", \"should we use library X or write our own client\", or whenever a change would touch more than about ten files or alter the integration's structure. Covers when a plan is mandatory, the phased plan format, where plans live, when a decision is worth recording, and the DECISIONS.md entry format used by this project. SYMPTOMS — load this if you are about to: start a refactor spanning more than ten files without confirmation; write a plan whose phases name no files; write one in prose nobody will finish reading; create a planning markdown file outside `.agents\u002Fscratch\u002F`; or make a hard-to-reverse architectural choice without recording why.","https:\u002F\u002Fgithub.com\u002Famg0\u002Fha_ksenia\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fha-planning\u002FSKILL.md",[],[]]