skills/pulse/SKILL.md
Returns a compact summary of the current session state. Channel-optimized (under 10 lines). Pass --full to append infrastructure health (proposals, routines, last activity, knowledge). Activates on messages like "status", "progress", "what are you working on", "how's it going".
npx skillsauth add gtapps/claude-code-hermit pulseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Provide a compact summary of the current session state. Designed for channel responses (Telegram, Discord) where brevity matters.
.claude-code-hermit/sessions/SHELL.md/claude-code-hermit:session to start one."
2b. If Status is idle (session between tasks), format as:
Session (idle) | started YYYY-MM-DD | N tasks completed
Last: [latest Session Summary entry]
Ready for work. Tell me what's next, or run /claude-code-hermit:session-start
Cost: $X.XX (cumulative)
Return this output and stop — do not proceed to step 3.**ID:** line**Status:** line**Tags:** line (if present and non-empty)**Budget:** line (if present and non-empty)## TaskTaskList and count by status. Total = all tasks, completed = completed tasks.in_progress## Blockers (if any non-comment content)## Cost (if any non-comment content)Session S-NNN | in_progress | [tags if present]
Working on: one-line summary
Progress: X/Y tasks | Current: Step N - description
Budget: $spent / $total (percentage%)
Blockers: none (or brief description)
Cost: $X.XX (NNK tokens)
/debug to diagnose, or /claude-code-hermit:session to start a new session."When the operator passes --full, append infrastructure health sections after the session block above.
This answers "is my hermit healthy?" — not a config dump (that's hermit-settings), not a work summary (that's brief).
.claude-code-hermit/config.json.claude-code-hermit/proposals/PROP-*.md. For each file, parse the status field from YAML frontmatter (or bullet-point metadata for legacy files). Count per status (proposed, accepted, in_progress, resolved, dismissed, deferred)..claude-code-hermit/state/micro-proposals.json. Count entries where status is pending.routines array: list each routine as id (schedule, on/off)..claude-code-hermit/state/reflection-state.json for last_reflection timestamp and counters. Read .claude-code-hermit/state/alert-state.json for the most recent alert timestamp. Compute relative age ("2h ago", "45m ago")..claude-code-hermit/raw/** (excluding .archive/), .claude-code-hermit/compiled/**, .claude-code-hermit/raw/.archive/**.Format the additional sections:
Proposals: N proposed, N accepted, N in_progress
Micro: N pending decision
Routines: morning-brief (08:00 daily), weekly-deps (09:00 mon, off)
Last: reflect 2h ago, heartbeat 45m ago
Reflect: N runs, N empty | judge: N accepted / N downgraded / N suppressed | output: N proposals, N micro | since YYYY-MM-DD
Knowledge: N raw, N compiled, N archived
— (not an error)counters is absent: Reflect: —total_runs is 0: Reflect: no runs yet (since YYYY-MM-DD)| output: ... clause if both proposals_created and micro_proposals_queued are 0tools
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.
development
Evening house brief — end-of-day security check, device status, and energy snapshot. Runs as a daily routine at 22:30 or on demand.
tools
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."
tools
On-demand HA-voice brainstorm — reads entity inventory, automation/script listings, and operator intent to surface at most 2 capability-gap ideas, each gated by proposal-triage before becoming a PROP. Invoke when the operator asks "what automations am I missing?", "any coverage gaps?", or "brainstorm improvements". Never runs autonomously.