본문으로 건너뛰기
cccskills
무료GitHub에 공개

home-assistant-integration

Use this skill when creating, scaffolding, reviewing, or maintaining Python Home Assistant custom integrations, including work on custom_components, manifests, config flows, options flows, config entries, platforms/entities, DataUpdateCoordinator, integration automation triggers, diagnostics, repairs, discovery/networking, authentication, HACS-ready repositories, or Home Assistant integration quality scale compliance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(9)

  • SKILL.md5.6 KB
  • agents/openai.yaml347 B
  • assets/home-assistant.png11.2 KB
  • README.md253 B
  • references/architecture.md2.5 KB
  • references/automation-triggers.md2.0 KB
  • references/core-integration-files.md2.6 KB
  • references/entities-and-domains.md2.3 KB
  • references/quality-rules.md5.0 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Home Assistant Integration Skill

Use this skill for Home Assistant custom integration development. This is separate from Home Assistant automation, helper, script, and Lovelace work.

Start With Current Docs

Fetch the latest markdown from the Home Assistant developers docs repository before coding. All doc paths in this skill and its references are relative to this base URL — prepend it when fetching:

https://raw.githubusercontent.com/home-assistant/developers.home-assistant/master/docs/

Use rendered pages on developers.home-assistant.io only as secondary reading. Do not copy Home Assistant docs into generated skill or repo files. Fetch only the files relevant to the task.

The reference files in this skill are the routing indexes to the doc paths; do not rely on remembered Home Assistant APIs. Always consult the relevant reference, then fetch the current markdown files it points to, before editing matching files:

ReferenceUse when
references/architecture.mdEditing generic integration architecture, lifecycle, setup, manifest, config entries, data fetching, events, diagnostics, auth, networking, docs, tests, or translations
references/core-integration-files.mdEditing core integration files such as __init__.py, manifest.json, config_flow.py, coordinator.py, diagnostics.py, repairs.py, services, translations, tests, or docs
references/entities-and-domains.mdEditing platform/entity files such as sensor.py, binary_sensor.py, calendar.py, weather.py, or deciding which platform domain fits a feature
references/automation-triggers.mdAdding or maintaining new integration-provided automation triggers in trigger.py and triggers.yaml
references/quality-rules.mdChecking Bronze/Silver/Gold/Platinum quality scale rules or reviewing an integration against Home Assistant quality requirements

Local Workflow

  1. Inspect local instructions first: AGENTS.md, scripts, pyproject.toml, workflows, README files, and existing custom_components/<domain> files.
  2. Preserve repo conventions. Prefer existing user Home Assistant repo patterns: uv tooling, scripts/lint, scripts/test, typed runtime data, DataUpdateCoordinator, config flows, diagnostics, translations, and minimal diffs.
  3. Keep API/client code Home Assistant agnostic where the repo already separates it from integration code.
  4. Use config entries and UI setup by default for real integrations. Use YAML only when the user explicitly asks or the existing repo still requires it.
  5. Keep entities cheap: no I/O in entity properties; update cached values through setup, coordinator refreshes, or event callbacks.
  6. Use ConfigEntry.runtime_data for runtime objects when adding or reshaping integration state.
  7. Handle setup failures with the Home Assistant exceptions that match the failure: retryable setup failures, auth failures, and permanent invalid configuration should not be conflated.
  8. Add tests for changed behavior. Run the repo scripts requested by local instructions, usually scripts/lint after Python changes and scripts/test before finishing.
  9. When behavior is unclear, add narrow debug logging or ask for logs instead of guessing.

Scaffolding Guidance

When scaffolding a new integration from an existing user repo, copy structure and tooling style, then remove business logic that does not belong to the new integration. Keep only the integration basics needed for setup, manifest validity, importability, testability, and future feature work.

Minimum shape for a custom integration is usually:

custom_components/<domain>/
  __init__.py
  manifest.json

Add files such as config_flow.py, platform modules, coordinator.py, entity.py, diagnostics.py, repairs.py, translations, tests, and brand assets only when required by the requested scope or the selected quality target. Use references/core-integration-files.md before adding or editing these files.

Quality Scale

Default to Bronze. Higher levels are cumulative and should only be added when the user asks or explicitly accepts the extra scope. Bronze means all Bronze rules apply; Silver includes Bronze; Gold includes Silver and Bronze; Platinum includes all lower levels.

Before finishing ordinary integration work, read references/quality-rules.md, confirm the current rule list from core/integration-quality-scale/_includes/tiers.json, fetch the latest markdown for each relevant rule, and verify every Bronze rule against the current code. If the user asks for Silver, Gold, or Platinum, make the additional rule set part of the implementation scope before coding.

Review Checklist

Before finishing:

  1. Re-fetch relevant docs and quality rule files.
  2. Verify the requested quality level, defaulting to Bronze.
  3. Run component and platform review checklists relevant to changed files.
  4. Confirm config entry setup, unload, runtime data, entity IDs, translations, diagnostics, and tests match the selected scope.
  5. Run local validation scripts from the repo instructions.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

agent-log

무료

Use this skill to maintain an agent log in .agents/log, a decision journal shared by the developer and agents. Trigger when the user explicitly asks to use agent-log or record/update an agent log entry; when planning, implementing, or finalizing a significant feature in a repo with an existing .agents/log; or before non-trivial changes or questions in areas covered by existing entries. Never initialize .agents/log unless the user explicitly asks for an agent log.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

denysdovhan/agents182026년 7월 29일 업데이트

commit

무료

Use this skill when an agent needs to prepare a focused commit, follow repository commit-message conventions, write a clear commit message, and create the git commit cleanly.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

denysdovhan/agents182026년 7월 29일 업데이트

Use when creating, reviewing, debugging, or maintaining Home Assistant custom Lovelace cards or card editors, including custom elements, Web Components, hass data, setConfig, getCardSize/getGridOptions, getConfigElement/getConfigForm, window.customCards, resource registration, HACS card packages, entity display, service calls, translations, or frontend build validation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

denysdovhan/agents182026년 7월 29일 업데이트

Use this skill when debugging runtime behavior requires live data from the running app, temporary instrumentation, or hypothesis verification through logs. Trigger for async timeouts, stale or incorrect state updates, race conditions, event ordering bugs, intermittent failures, browser/client behavior that static inspection cannot explain, or any issue where the agent should create a local debug HTTP server, insert temporary probes, ask the user to reproduce, inspect .debug/debug.log, then remove all debug instrumentation and assets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

denysdovhan/agents182026년 7월 29일 업데이트

denysdovhan의 스킬 모두 보기

이 스킬의 문제 신고