Claude Skills by gtapps

Browse and explain the hermit's Home Assistant automations — list by topic, filter by keyword with plain-language YAML explanations, or sort by last-fired. Read-only. Use when the operator asks "what automations do I have / what does this one do / which haven't fired."

Check Home Assistant connectivity, context freshness, and locale. Auto-refresh context if stale. Use at session start or when HA status is unclear.

Draft a Home Assistant automation or script YAML from a description. Validates against the entity inventory and safety policy. Use when the user wants to create or modify HA automations.

Evening house brief — end-of-day security check, device status, and energy snapshot. Runs as a daily routine at 22:30 or on demand.

Get a quick live status of the house via MCP. Shows lights, covers, climate, presence, and notable states. Use when the operator asks about house state.

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.

Morning house brief — live status, overnight anomalies, energy snapshot, pending proposals, and today's priorities. Runs as a daily routine or on demand.

Presence history & tracker-health report — current home/away state, reliability, recent arrival/departure transitions, and activity patterns for person/device_tracker entities. Use when the operator asks about presence history or when a presence-dependent automation (locks, alarm, vacuum, climate) misbehaves.

Fetch and normalize the full Home Assistant state into durable artifacts. Use before drafting automations or when context is stale.

Audit all live Home Assistant automations and scripts against the safety policy. Catches policy drift from entities added via the HA UI that bypassed this plugin's safety gate. Runs weekly as a routine via reflect --check-id ha-safety-audit --check hermitd-homeassistant:ha-safety-audit.

Guided build-out of a Home Assistant house — create areas, assign entities and devices, provision helpers, and scaffold starter automations. Thin orchestration of existing CLI commands; all structural writes are gated by ha_safety_mode.

Capture the state of a set of Home Assistant entities (lights, covers, climate, switches) to a named artifact and restore it later via scene.apply. Use to make automation testing reversible — snapshot before a risky change, restore if it misbehaves. Restore of sensitive entities is gated by ha_safety_mode.

Detect pending Home Assistant updates (Core, OS, Supervisor, add-ons, HACS) from the update.* domain and surface them as actionable proposals. Runs daily as a routine via reflect --check-id ha-update-check --check hermitd-homeassistant:ha-update-check.

One-time Home Assistant setup for this hermit. Configures HA access, connects to the official Home Assistant MCP Server integration, and verifies both the CLI and HA MCP. Run once per project after /hermitd:hatch.

Deploy a site on Laravel Forge. Always surface-then-approve (preview-deploy first, then deploy with native approval). Watches via the hermit /watch registry and writes a deploy-incident on failure. Triggers on "deploy", "trigger deployment", "deploy site", "run deployment", "check deployment status".

Routine check: scans the Forge estate for sites whose latest deployment is in a failure state. Runs daily via its own routine; findings are routed through the proposal pipeline as Evidence Source: scheduled-check/forge-failed-deploys.

List, inspect, and reboot Laravel Forge servers. Reboot always goes through surface-then-approve (preview-reboot → native approval → server-reboot). Triggers on "list servers", "show server", "reboot server", "server status".

List and inspect sites on Laravel Forge servers. Triggers on "list sites", "show site", "site detail", "what sites are on server X".

One-time Laravel Forge hermit setup. Installs the Forge PHP SDK, verifies credentials, and wires the estate scan into config.json. Run once per project after /hermitd:hatch.

One-time setup for hermit-scribe — appends the Issue Filing block to CLAUDE.md/CLAUDE.local.md. Run once per project; re-run to refresh after an upgrade.

File a GitHub issue or post a comment on an existing issue via a GitHub App bot identity. Use when the operator says "file as a GH issue", "open an issue for PROP-NNN", "report this to the tracker", "add a comment to issue #NNN", "comment on #NNN", "reply to issue #NNN", or similar. Requires HERMIT_GH_APP_ID, HERMIT_GH_APP_INSTALL_ID, HERMIT_GH_APP_KEY_FILE in env.

Returns a 5-line executive summary of recent work. Checks open resident records first, then recent task outcomes. Activates on messages like "brief", "what happened", "morning update", "overnight summary", "progress", "what are you working on", "how's it going".

Monthly routine plus on-demand hermit-voice brainstorm — synthesizes memory, capabilities, recent artifacts, and codebase shape into at most 2 capability ideas, each gated by proposal-triage before becoming a PROP. Runs on the capability-brainstorm routine and when the operator asks to brainstorm capabilities or ideate, e.g. "brainstorm capabilities", "what could you be doing for me?", "any capability ideas?".

Handles inbound messages tagged <channel source=...> from Claude Code Channels, routing replies, task work, approvals, and operator controls with session context.

Guided channel activation for local/tmux users — adds a channel entry when none is configured, installs the plugin, configures the bot token in the project-local state dir, and walks through pairing. Run after hatch, or any time to add or re-enable a channel.

The 'why is my bill high' skill: audits where spend goes across token categories (cache_read, cache_write, output, input) and per-session attribution. Invoke for questions like 'cost breakdown', 'which sessions are expensive', 'what's driving spend', or 'cold start costs'. Not for week-over-week trend lines (use hermit-evolution) or simple total-spend summaries.

Route a request to install a tool, binary, package, env var, persistent directory, side service, or personal/third-party skill in the hermit Docker container to the first channel that can carry it. Apt packages go in the Dockerfile operator block; boot-time shell work goes in docker-entrypoint.hermit-local.sh; compose and Dockerfile only when nothing else fits. Activates on messages like "install skills in the container", "install gog in the container", "add an apt package", "download a binar...

Opt-in advanced Docker security hardening beyond the docker-setup baseline — LAN containment with DNS policy, resource bounds with kernel-hygiene sysctls, and a boot-time plugin install audit log. Applied as a reversible docker-compose overlay (does not touch the base compose file) and verified against the live container. Run after /docker-setup; requires bridge networking.

Host-only, operator-invoked. Generates Docker scaffolding and walks the operator through token setup, build, start, MCP plugin configuration, workspace trust, and verification. Offers to back up and overwrite existing Docker files. Run after /hatch.

Initializes the autonomous agent in the current project. Creates the state directory, templates, OPERATOR.md, and config.json. Appends session discipline to CLAUDE.md. Detects installed hermits. Run once per project, like git init.

Executes the heartbeat checklist from HEARTBEAT.md. Reads the checklist, evaluates each item, and reports findings, acknowledges with HEARTBEAT_OK, or acknowledges a rejected evaluation with HEARTBEAT_INDETERMINATE. Supports run/start/stop/status/edit subcommands.

Designs this hermit's dashboard around what it tracks, writing a renderer that rebuilds it every refresh at no model cost. Use for "design/customize/change my dashboard", "put X on my dashboard", "remove my custom dashboard".

Runs the hermit's read-only health checks (runtime, config, hooks, state integrity, cost and spend, scheduling and watchdog, channels, credentials, permissions, docker, backup) and reports the summary. Use when diagnosing an install, before a release, or after suspicious behavior. Activates on messages like "/hermit-doctor", "health check", "diagnose the hermit", "what's wrong", "run diagnostic".

Show how this hermit has evolved: cost trend and source split, routines and watches, top things produced, and what grew since hatch. Activates on messages like 'how am I trending', 'cost trend', 'evolution report', 'am I improving', 'proposal velocity', 'monthly report', 'what did I produce last month'.

Evolves hermit configuration and templates after a plugin update. Detects version gaps and runs the upgrade (migrations, templates, new settings) in an isolated subagent. Run after updating the plugin.

Show alert state, proposal queue depth, routine engagement, knowledge state, channel availability, plus fragile zones, stale accepted proposals, and recent learnings. Activates on messages like 'health check', 'how's the hermit', 'is anything broken', 'hermit health', 'system health', 'anything wrong', 'hermitd status', 'hermit brain', 'are routines running', 'what's stuck', 'any fragile zones', 'show me what's blocked', 'recent learnings', 'what have you learned lately', 'where are the weak ...

Schedules routines via one native plugin monitor (zero-token skips); CronCreate fallback where Monitor is unavailable. heartbeat-restart stays a CronCreate re-arm anchor.

View or change hermit configuration for this project. Manages model, channels, morning brief, heartbeat, routines, compaction thresholds, Docker packages, and unattended mode.

Record a claim to check later. Use for "check in N days whether", "remind me to verify", or "did the fix hold".

Accept, defer, dismiss, or resolve a proposal. For accepted proposals, asks how to proceed: start implementing now, queue a task, or note for manual implementation. Activates on messages like "accept PROP-", "dismiss PROP-", "defer PROP-", "resolve PROP-".

Creates a proposal for a high-leverage improvement discovered during work. Only for ideas with real impact — not trivial fixes. Use when you discover something worth operationalizing.

Lists all proposals with their status, source, and age. Shows auto-detected proposals prominently. Activates on messages like "what have you noticed", "any improvements", "any proposals", "show proposals".

Open, close, or check the Remote Control spawn gate — the hermit-managed `claude remote-control` server that lets a phone spawn new sessions into this project.

Full-text search over the recorded past: session reports, compiled notes, proposals, and the channel log. Use it whenever the operator asks what already happened — 'recall X', 'what did I learn/decide/figure out about X', 'when did we last touch X', 'did we ever discuss X', 'have we seen this error before', 'find that proposal about X', 'yesterday I asked you to X' — even when you could grep or Read .hermit/ yourself: this search also covers the channel-message database that file greps miss, ...

Reflect on recent work and propose improvements if patterns are noticed.

Renew the hermit's Claude credential (token or claude.ai sign-in, per `auth_mode`) over the channel, before it expires. Relays a one-time sign-in link to the operator, takes the code back, installs the new token, and restarts. Activates on messages like 'relogin', 'renew my login', 'reauth', 'the login is expiring', or when doctor's credential-expiry check flags the Claude credential.

Orient a resident after boot, resume or context refresh, reconcile recovery and report readiness without choosing work.

Spawns a background Claude Code helper in the project or another folder with the configured Remote Control and the boot-written helper system prompt that a hand-built `claude --bg` omits, watches it until idle, and relays its report to the operator. Use when the operator says "spawn a helper", "spawn a new session", "run this in a background session", asks for a new session with `--model` or `--effort`, or names `/spawn-session`.

Tracks chat assignments, steering in a task thread, WORKER completions, and confirmations alongside task progress and results.

Handle a voice note or audio attachment the hermit cannot read, and set up transcription when the operator wants it. Activates when a channel message carries an audio attachment (Telegram voice message, Discord voice-message.ogg), or on "can you understand voice notes", "transcribe my voice message", "set up voice notes".