Menu
Lifecycle status skill for the HI evidence pipeline. Runs rh-skills status to show project-level state and per-topic recommendations derived from tracking.yaml. Read-only. Modes: show · check-changes.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Reviewer-gated extraction skill for deriving L2 structured artifacts from ingested normalized sources. Runs MCP terminology enrichment, presents batch proposals for human review, records decisions via concept review CLI, and writes finalized `topics/<topic>/structured/concepts/concepts.yaml` plus an extract plan that includes an explicit `concepts` terminology artifact row. Supported modes: plan · implement · verify. Use when the user asks to extract structured artifacts from sources for a topic.
Reviewer-gated formalization skill for converging approved L2 structured artifacts into L3 FHIR computable resources. Uses type-specific strategies to map each L2 artifact type to its correct FHIR R4 targets. Modes: plan, implement, verify
Source preparation skill for the HI evidence pipeline. Normalizes all files in sources/ to Markdown, infers and initializes topics, classifies each source (using discovery-plan.yaml as optional enrichment when present), and annotates with concept metadata in normalized front matter for downstream extraction. Modes: plan, implement, verify
First-class CQL (Clinical Quality Language) authoring, review, debugging, and test-plan skill for the rh-skills informatics workflow.
Interactive conflict resolution guide for RH lifecycle plans. Iterates through all open concerns across extract-plan.yaml and formalize-plan.yaml, presents each to the human reviewer, records the resolution, and confirms the plan is clear before proceeding to implementation.
Unified topic-level verification orchestrator for the RH lifecycle. Read-only. Launches stage-specific verify workflows via subagents and returns one consolidated report. Modes: verify.
| name | rh-inf-status |
| description | Lifecycle status skill for the HI evidence pipeline. Runs rh-skills status to show project-level state and per-topic recommendations derived from tracking.yaml. Read-only. Modes: show · check-changes. |
| compatibility | rh-skills >= 0.1.0 |
| context_files | ["reference.md","examples/output.md"] |
| metadata | {"author":"RH Skills","version":"1.0.0","source":"skills/.curated/rh-inf-status/SKILL.md","lifecycle_stage":"any","reads_from":["tracking.yaml"],"writes_via_cli":[]} |
rh-inf-status shows the current state of the research portfolio and recommends
next steps for each topic. It reads tracking.yaml and checks for
discovery-plan.yaml to surface context-aware recommendations. It never
modifies any file.
rh-inf-status never writes files, modifies tracking.yaml, or
creates artifacts.rh-skills CLI. All status queries and
recommendations are produced by rh-skills status CLI commands. The agent presents
output and may add one sentence of context per topic; it does not invent
recommendations beyond what the CLI produces.Next steps bullet list emitted by the
canonical CLI surface. Do not append A/B/C-style menus.$ARGUMENTS
$ARGUMENTS is optional. If a topic name is supplied, show status for that
topic only. If empty, show the full portfolio.
tracking.yaml exists. If absent, advise rh-skills init <topic>.tracking.yaml.
If not found, suggest rh-skills init <topic>.verifyAll operations are read-only. No files are written.
Step 1 — Run status
rh-skills status # full portfolio
rh-skills status show <topic> # single topic (when topic supplied)
Present the CLI output as-is. For each topic, you may add one sentence of
context if the recommended next step is non-obvious (e.g., explain what
rh-inf-extract does if the user may not know).
If the user explicitly asks for drift detection or changed-source checks, run:
rh-skills status check-changes <topic>
Present the canonical rh-skills status output as-is. If you add any context,
limit it to one brief sentence before the CLI output. Do not append a second
menu, alternate recommendations, or lettered choices after the CLI output.
<canonical rh-skills status output>
Next steps:
- <deterministic action>
- <deterministic action>
| Condition | Action |
|---|---|
tracking.yaml missing | Advise rh-skills init <topic>; exit |
| Topic not found | Advise rh-skills list and rh-skills init <topic>; exit |
rh-skills status exits non-zero | Surface the error verbatim; do not continue |