Menú
Audit experiment artifact folders for completeness, schema consistency, and promotion traceability across single and grid runs.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Build candidate features, run feature screening and diagnostics, and prepare accepted feature sets for downstream flywheel experiments.
Run OpenQuant notebook-to-experiment flywheel iterations (single run and grid run), capture artifacts, and summarize ranked outcomes for promotion decisions.
Execute OpenQuant notebook code cells non-interactively, persist outputs to artifact paths, and fail fast on runtime errors.
Verify parity between notebook-like pipeline execution and scripted experiment workflows so research findings are reproducible.
Evaluate promotion readiness from flywheel outputs using statistical and economic gates, then produce a concise go/no-go decision note.
Build and run an AFML-grounded, chapter-by-chapter documentation loop for OpenQuant docs. Use this when you need consistent module docs, hierarchical chapter coverage, and iterative progress tracking with MCP-backed prompts.
| name | artifact-auditor |
| description | Audit experiment artifact folders for completeness, schema consistency, and promotion traceability across single and grid runs. |
Use this skill when validating whether research runs are publishable/reviewable by another quant without hidden notebook state.
metrics.parquet and leaderboard.parquet.decision.md + run_manifest.json).run_manifest.jsonmetrics.parquetevents.parquetsignals.parquetweights.parquetbacktest.parquetdecision.mdleaderboard.parquetrun_manifest.json# quick schema check (example)
uv run --python .venv/bin/python - <<'PY'
import polars as pl
from pathlib import Path
p = Path("experiments/artifacts")
for lf in p.rglob("leaderboard.parquet"):
df = pl.read_parquet(lf)
required = {"run_name", "net_sharpe", "promote_candidate"}
missing = required - set(df.columns)
if missing:
print(f"{lf}: missing {sorted(missing)}")
PY