Menu
SkillsMP has collected 19 skills from Apocrathia/home-assistant-config. Open a skill to review its source and details.
Showing 19 of 19 collected skills.
Mine Home Assistant history for automation trigger candidates from a narrative or structured event brief. Use when finding a reliable trigger, correlating a morning/evening sequence, ranking sensor signals for a new automation, or running the pattern-analyst…
Interview the operator about a topic until shared understanding, walking each branch of the decision tree one at a time. Use when stress-testing an idea, design, or requirement; resolving open questions before acting; or when the user says alignment,…
Explore packages/, layout, and .agents/ for architectural friction (coupling, shallow packages, missing boundaries) and file or recommend agent issues under docs/issues/. Use when improving config shape, before large refactors, or when find-work should…
Create or update an agent-reported issue under docs/issues/. Use when an agent finds a bug, feature gap, or spec-level ask that is out of scope for the current lap, or when asked to file an issue. Does not create GitHub issues. Never writes Local Todo ICS or…
Orient on Home Assistant Homelab, scout read-only work sources (docs/issues + docs/plans, local_todo Issues/Tasks/Ideas ICS, shopping list, docs, TODO markers), rank a backlog with evidence, and emit launch briefs. Use when the user says find work,…
One change lap for Home Assistant Homelab: scope, edit, validate, hand off with a suggested Conventional Commit. Use when implementing a config fix, package change, plan checkbox, or agent-context update.
Fix drift in Home Assistant Homelab agent context (AGENTS.md, CLAUDE.md, .agents/context/, rules, skills, agents) against the repo. Run check_links and check_discovery. Use when asked to sync, reconcile, or update agent context.
Sync docs/ with Home Assistant packages and project reality, and delete satisfied docs/issues and docs/plans in the shipping change. Use after package/layout changes or when asked to update docs.
Create a new agent persona under .agents/agents/. Use when the user says create agent, new agent, add a persona, or when a recurring delegation pattern needs its own subagent charter.
Create a new skill under .agents/skills/. Use when the user says create skill, new skill, add a skill, or when a repeated multi-step procedure should become a reusable, invocable workflow instead of being re-explained each session.
Pull changes from the prime-context core into Home Assistant Homelab's .agents/ tree — diff shared rules, skills, and scripts, reconcile layer 1 and 2 changes, and preserve project-specific content. Use when the user says sync upstream, integrate upstream…
Query historical Home Assistant entity state via Grafana's Home Assistant InfluxDB datasource (InfluxQL). Use when the user asks about past states, "was X on/off", "when did…", history for an entity, overnight activity, or numeric sensor series over a time…
Optional, operator-gated metric experiments under .scratch/ for Home Assistant Homelab. Prefer prototype for design questions. Use only when a measurable eval exists and the operator wants a short experiment log — not a swarm research loop or docs/research PR.
Session wrap-up for Home Assistant Homelab: summarize what changed, what is still open, and suggested next steps. Does not sync main or clean up merges.
Build a throwaway prototype under .scratch/ to answer a design question. Use when the user wants to sanity-check automation/state logic, explore a dashboard or notification shape, or says prototype or /prototype.
Structured post-work retrospective for Home Assistant Homelab: review outcomes, mine git history for context drift, classify lessons, and route improvements — HA-local vs contribute back to prime-context. Use when the user says retro, /retrospective, what did…
Pre-handoff quality gate for Home Assistant YAML, docs, and agent context. Lint, validate, and smoke-check the working-tree diff. Use before handing changes to the operator.
Light Home Assistant Homelab work loop: find-work, pick with the operator, implement-change, review-loop, ship-work handoff, then STOP. Use when the operator says self-improve or wants one guided contribution lap.
Hand off completed Home Assistant Homelab work to the operator: summarize diffs, suggest a Conventional Commit, list validation done, and remind them to apply/reload HA and commit. Does not commit or push.