メニュー
Diagnose and repair common M4 environment, dataset, skill installation, backend, and vitrine setup problems. Use when M4 tools, datasets, skills, or visualization are missing or broken.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | m4-setup |
| description | Diagnose and repair common M4 environment, dataset, skill installation, backend, and vitrine setup problems. Use when M4 tools, datasets, skills, or visualization are missing or broken. |
| tier | community |
| category | system |
Use this skill when the M4 environment looks incomplete, a dataset is missing, skills are stale, or vitrine is unavailable.
from m4 import ... fails or the wrong Python environment is activelist_datasets() or m4 status --all does not show expected datasetsvitrine imports fail or the display server is not reachableRun commands from the M4 repo root unless the user is intentionally working elsewhere.
pwd
uv run python - <<'PY'
from m4 import list_datasets
print("datasets:", list_datasets())
PY
uv run m4 status --all
uv run m4 agent-env --dataset mimic-iv-demo --json
uv run m4 skills --list
uv run vitrine status
If plain python cannot import m4, use uv run python; M4 is usually installed in the project virtual environment.
Expected built-in datasets:
| Dataset | Notes |
|---|---|
mimic-iv-demo | Local demo tabular dataset |
mimic-iv | MIMIC-IV tabular data and derived tables |
mimic-iv-note | MIMIC-IV notes |
eicu | eICU tabular data |
Custom datasets live under the M4 data directory in datasets/*.json and should
appear in m4 status --all. By default the data directory is m4_data; if
M4_DATA_DIR is set, it must point directly at the data directory.
Common checks:
uv run m4 agent-env --json
M4_CONFIG_DIR="${M4_HOME:-${M4_DATA_DIR:-m4_data}}"
cat "$M4_CONFIG_DIR/config.json"
find "${M4_DATA_DIR:-m4_data}/databases" -maxdepth 1 -type f -name '*.duckdb' -print
find "${M4_DATA_DIR:-m4_data}/datasets" -maxdepth 1 -type f -name '*.json' -print
Pass dataset="name" when querying, then inspect schema with get_schema(dataset=...) and get_table_info(..., dataset=...).
The canonical bundled skills are under src/m4/skills. Installed tool directories are generated copies.
uv run m4 skills --tools claude,codex
uv run m4 skills --list
Filtered installs are additive; existing non-matching skills are left in place. If an installed skill is stale, reinstall from the bundled source.
Check ${M4_HOME:-${M4_DATA_DIR:-m4_data}}/config.json:
| Field | Meaning |
|---|---|
backend | duckdb or bigquery |
bigquery_project_id | Billing/project id for BigQuery |
For local work, backend: "duckdb" requires the matching file in the data
directory's databases/ folder. For BigQuery work, credentialed datasets
require valid Google credentials and a configured project.
uv run python - <<'PY'
import vitrine
print("vitrine import ok")
print(vitrine.server_status())
PY
uv run vitrine restart
Use the vitrine-api skill for display API details.
uv run ... commands to avoid using the wrong environment.get_schema(dataset=...) and get_table_info(..., dataset=...).m4 status --all but not in list_datasets(), check the data directory's datasets/*.json files and reload through the M4 API.src/m4/skills and reinstall from the canonical source.Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.
Start a structured clinical research session. Use when users describe research goals, want to analyze cohorts, investigate hypotheses, or need a rigorous research plan. Interviews the user, then produces a research protocol.
Use the M4 Python API to query clinical datasets programmatically. Use when writing code to access clinical databases, executing SQL via Python, or performing multi-step data analysis.
Calculate Charlson Comorbidity Index (CCI) and Elixhauser Comorbidity Index for hospital admissions. Use for risk adjustment, mortality prediction, case-mix analysis, or comparing comorbidity burden across patient populations.
Identify first ICU stays and first hospital admissions for cohort selection. Use to exclude readmissions, create independent observations, or build adult patient cohorts.
Guide users through creating M4 skills with proper structure, provenance tracking, and tier assignment. Use when users want to create a new M4 skill, document a clinical concept, or contribute a skill to the M4 skills library.