Skip to content
Automation
Skill

/ha-integration-health

Detect dropped HA integrations by computing per-domain unavailable-entity ratios from the latest context snapshot. Flags domains where most entities are unavailable, suggesting the integration lost its connection. Runs daily as a routine via reflect --check-id

From plugin
hermitd
8489 skills14 agents

Claude Code

$ npx -y skills add gtapps/hermitd --skill ha-integration-health --agent claude-code

SKILL.md

ha-integration-health.SKILL.md
name: ha-integration-health
description: Detect dropped HA integrations by computing per-domain unavailable-entity ratios from the latest context snapshot. Flags domains where most entities are unavailable, suggesting the integration lost its connection. Runs daily as a routine via reflect --check-id ha-integration-health --check hermitd-homeassistant:ha-integration-health.
allowed-tools:
  - Bash

HA Integration Health

Purpose

When an HA integration loses its connection (lost WiFi, API change, expired token), its entities go `unavailable`. This skill reads the latest normalized snapshot, groups entities by domain, and flags domains with a high unavailable ratio.

Steps

Run the integration-health check via the CLI:

${CLAUDE_PLUGIN_ROOT}/bin/ha-agent-lab ha integration-health

The CLI:

  • Checks that `snapshot-ha-normalized-latest.json` exists and is fresh (< 24h). If stale or missing, runs `ha refresh-context` first to bring it up to date, then proceeds with analysis.
  • Groups entities by domain prefix, computes unavailable ratios, and flags domains where `total >= 3` AND `ratio >= 0.5`.
  • Writes `.hermit/state/integration-health-degraded-domains.json` — a machine-readable state artifact consumed by `ha-analyze-patterns` (via `silence.ts`) to suppress overlapping `long_unavailable` findings.
  • Prints one JSON object: `date`, `scanned_domains` and `degraded` (each entry `domain`, `unavailable`, `total`, `percent`), or `{"date","status":"skipped","reason","detail"}` with `reason` `refresh_failed` (snapshot stale or missing and HA unreachable) or `snapshot_unreadable`.

Output contract

reflect --check-id ha-integration-health --check hermitd-homeassistant:ha-integration-health routes the findings block through the proposal pipeline. Render it from the JSON in this fixed shape, one line per `degraded` entry with `percent` to one decimal:

ha-integration-health findings — <date>
Degraded domains: N
- <domain>: <unavailable>/<total> entities unavailable (<percent>%)

If `degraded` is empty: `No actionable findings. (<scanned_domains> domains scanned)`. If `reason` is `refresh_failed`: `No actionable findings. (skipped: snapshot stale, refresh failed — <detail>)`. If `reason` is `snapshot_unreadable`: `No actionable findings. (skipped: snapshot unreadable — <detail>)`.

Keep the output to this shape: no prose, no extra sections.

Read more
@gtapps
Ships withhermitd

Run an always-on Claude Code agent on your own machine, for you or your team. Start and orchestrate sessions from chat in any project it can reach. Take over the same session in the Claude app or the CLI.

8489 skills14 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
84
Star history of gtapps/claude-code-hermit on GitHub, a chart by star-history.com

Other skills on hermitd.

bump-core-req

bump-core-req

Updates the minimum core version requirement for a fleet plugin in all three canonical places: `required_core_version` and…

@gtapps@gtappsInstall Skill
commit

commit

Changelog and commit — lightweight motion for day-to-day plugin dev work in the monorepo. One commit per plugin scope; CHANGELOG…

@gtapps@gtappsInstall Skill
docs-drift

docs-drift

Documentation-drift audit for the plugin monorepo. Audits either each scoped plugin's unreleased changelog claims or its latest…

@gtapps@gtappsInstall Skill
downstream-impact

downstream-impact

Explain in plain language what a fix, feature, PR, or plan will actually change for downstream hermits and the operators chatting…

@gtapps@gtappsInstall Skill
fleet-release

fleet-release

Use this skill whenever the user wants to release, ship, prep, or cut versions for two or more plugins together on the current…

@gtapps@gtappsInstall Skill
pipeline-digest

pipeline-digest

Daily release-pipeline digest with a change gate — reports which plugins are pending release, whether main's CI is green, which…

@gtapps@gtappsInstall Skill

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n12d209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
agent-browser

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…

@vercel-labs-2@vercel-labs-2Install Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about ha-integration-health.

Which coding agents can use ha-integration-health?
ha-integration-health installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.