health_agent_infra

Partition unstructured user narration into the typed `hai intake` commands the runtime expects. Use when the user volunteers information outside a form — readiness, gym sets, nutrition, subjective stress, or free-text context. Also drives the session-start gap-filling protocol: read `hai intake gaps`, compose ONE consolidated question, route the answer. You route; you do not interpret.

Authoritative mapping from user natural-language intent to `hai` CLI workflow sequences. Reads the `hai capabilities --json` manifest as the source of truth for which commands exist, what they mutate, and what exit codes they return. Never mutates state itself — it composes invocations of other `hai` subcommands that cross the determinism boundaries. Always surfaces the proposed pipeline before any mutation command runs. Teaches the agent `hai` the way Claude already knows `gh`.

Fail-closed boundaries for the health agent. Defines what the system must not claim, when to refuse, and how to handle ambiguous or unsafe signal.

Reconcile per-domain proposals into a coherent daily plan by composing rationale and uncertainty across domains. The runtime already applied every Phase A X-rule mutation mechanically; this skill adds the human-legible joint narration on top. It never computes bands, evaluates R-rules, or applies X-rule mutations — those are runtime-owned.

Answer bounded questions about what a term means in this system, or why a runtime rule would fire, using only the allowlisted local source registry under `hai/src/health_agent_infra/core/research/`. Read-only. Cite or abstain. Never mutates recommendations, never triages, never diagnoses.

Produce a bounded NutritionProposal for today by consuming the runtime-computed `classified_state` + `policy_result` and applying judgment-only steps — action matrix, rationale prose, honest handling of micronutrient unavailability. The runtime already did every band, every score, and every R-rule; this skill does not re-derive them. Macros-only v1 per the Phase 2.5 retrieval-gate outcome.

Produce a bounded RecoveryProposal for today's session by consuming the runtime-computed `classified_state` + `policy_result` and applying judgment-only steps — action matrix, rationale prose, and vendor cross-check. The runtime already did every band, every score, and every policy rule; this skill does not re-derive them.

Narrate committed recommendations and their audit trail to the end user in plain language. Use when the user asks what today's plan is, why it was made, or how past sessions have gone.

Schedule, record, and summarise review outcomes against previously-issued recommendations via `hai review`. Use when yesterday's plan needs a review question scheduled, when the user reports whether a recommendation helped, or when you need a history summary before reasoning about future confidence.

Produce a bounded RunningProposal for today's run by consuming the runtime-computed `classified_state` + `policy_result` and applying judgment-only steps — action matrix, rationale prose, vendor cross-check, follow-up composition. The runtime already did every band, every score, and every R-rule; this skill does not re-derive them.

Produce a bounded SleepProposal for today by consuming the runtime-computed `classified_state` + `policy_result` and applying judgment-only steps — action matrix, rationale prose, vendor cross-check. The runtime already did every band, every score, and every R-rule; this skill does not re-derive them.

Convert a user's narrated strength session into structured `hai intake gym` calls. Judgment-only — all name resolution and parsing lives in code.

Produce a bounded StrengthProposal for today by consuming the runtime-computed `classified_state` + `policy_result` and applying judgment-only steps — action matrix, rationale prose, cross-checks. The runtime already did every band, every score, every R-rule; this skill does not re-derive them.

Produce a bounded StressProposal for today by consuming the runtime-computed `classified_state` + `policy_result` and applying judgment-only steps — action matrix, rationale prose, vendor cross-check. The runtime already did every band, every score, and every R-rule; this skill does not re-derive them.