homerail

Design and maintain truthful HomeRail generative UI for voice or text. Use for dashboards, cards, charts, visual reports, screenshot-ready output, or supervised multi-Actor live panels that update in parallel and across follow-ups.

Exact HomeRail local-source TypeScript CLI command and configuration reference. Use when: (1) configuring or invoking the homerail CLI from a local checkout, (2) listing orchestration templates, starting runs, checking status, (3) supervising DAG runs, inspecting chats/handoffs/scorecards, (4) injecting instructions or replaying runs, or (5) translating a known HomeRail operation into an exact hr command. For workflow topology selection use homerail-dag-patterns; for multi-Actor Surface lifecycle and operational procedure use homerail-dag-ops. For deployment, service startup, or skill installation, use homerail-install-ops first.

Run, monitor, inspect, debug, and author HomeRail DAG workflows through the CLI or Manager Tools, including supervised multi-Actor runs with stable live Surfaces and later per-Actor follow-ups. Use when: (1) listing templates, (2) starting a DAG run, (3) supervising or watching a run, (4) inspecting chats, handoffs, scorecard, eval-run, or replay output, (5) creating multiple parallel UI panels that update while Actors work, (6) sending commands to waiting Actors, (7) injecting instructions into running nodes, or (8) creating custom DAG templates. For installing or starting Manager/Node/Worker services, use homerail-install-ops first.

Select, inspect, instantiate, adapt, and validate HomeRail's built-in DAG design patterns. Use when an agent needs to design a reusable workflow for periodic triage, read-only issue diagnosis, planner/worker fan-out, on-demand executor/advisor consultation, budget admission, graduated trust, standing-goal verification, quorum decisions, adversarial builder/breaker review, monotonic improvement, or evidence-driven process evolution. Also use when deciding whether a workflow needs condition, loop, join, or while gateway semantics. Patterns describe control-flow invariants; for stable live Actor panels, Surface updates, or follow-up commands, use homerail-dag-ops and a concrete presentation-aware Workflow.

Present an evidence-grounded pull request closeout decision after review, CI, or real-machine validation.

Create and revise a structured topic outline from an evolving brief, audience, angle, thesis, sections, questions, and sources.

Create or replace a complete semantic release-notes snapshot.

Generate a video cover through the sandboxed GPU runtime and Manager Artifact Broker.

Determine whether a GitHub pull request can leave Draft or is ready for its owner to merge, using immutable validation, review, CI, dependency, and approval evidence. Never merge a pull request.

Run HomeRail's built-in read-only pull request review DAG. Use when the user asks to review a GitHub PR, requests an evidence-backed PR audit, or wants a reusable runtime/security/tests/frontend review with independent quorum.

Install, configure, start, verify, update, and troubleshoot a local-source HomeRail deployment for AI-agent use. Use when a user wants to deploy HomeRail from a local checkout or local Git address, install HomeRail skills, set up Manager/Node/Worker services, configure provider credentials, run doctor/smoke, or repair a broken local install before npm publication exists.

HomeRail DAG review and execution best practices. Use when designing, running, or reviewing HomeRail fan-out/fan-in DAGs, especially model-backed DAG audits, environment checks, and agent handoff evidence.

Shared HomeRail rules for AI agents operating the local-source release candidate: service roles, environment variables, secrets, provider boundaries, Docker callback networking, update expectations, and safe command behavior. Use whenever installing, configuring, upgrading, troubleshooting, or running HomeRail through other HomeRail skills.