Menu
Review DataClaw analysis outputs against structured evidence, hypotheses, findings, gates, and artifact metadata.
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
Author and publish bespoke analytical reports from validated findings, bounded aggregate evidence, methodology, caveats, and an evidence ledger. Use for final reports, report-like dashboards, interactive analytical briefings, or redesigning existing report HTML; the creative author owns all unspecified story, prose, layout, and visual decisions.
Use Dataclaw tools for governed data science and analytics work. Includes tools for interacting with data, running jupyter notebooks, proposing, updating and reviewing analytical plans, experiment tracking, training machine learning models, and generating reports.
Publish, revise, inspect, export, and troubleshoot DataClaw artifacts. Use when a report, dashboard, chart, profile, model card, or living-report note should become a secure, versioned, shareable artifact through dataclaw-artifacts.
Estimate and defend causal effects inside the Dataclaw data-science workflow by choosing an identification strategy, stating the estimand, testing design-specific assumptions, quantifying uncertainty, and refusing unsupported causal claims. Use for impact analysis, policy or treatment effects, difference-in-differences, matching or weighting, instrumental variables, regression discontinuity, synthetic controls, interrupted time series, mediation questions, and observational “does X cause Y?” requests.
Design, analyze, or audit randomized experiments inside the Dataclaw data-science workflow with a defensible randomization unit, power and duration, pre-registered outcomes, assignment and exposure checks, sequential and multiplicity control, and uncertainty at the assignment level. Use for A/B and multivariate tests, cluster or geo experiments, switchbacks, holdouts, factorial designs, non-inferiority, uplift and heterogeneous-treatment analyses, experiment readouts, and sample-size planning.
Build reproducible, leakage-safe model inputs inside the Dataclaw data-science workflow by defining prediction-time availability, excluding identifiers, fitting transforms within folds, cross-fitting target-derived features, handling temporal and grouped data correctly, and versioning feature lineage. Use for tabular, temporal, categorical, text, geospatial, nested, interaction, aggregation, embedding, selection, and dimensionality-reduction features used by predictive, forecasting, causal, uplift, or segmentation models.
| name | analysis_review |
| description | Review DataClaw analysis outputs against structured evidence, hypotheses, findings, gates, and artifact metadata. |
| tags | ["analysis","review","validation","artifacts","eda"] |
Related skills: structured_eda (produces the hypothesis and finding ledger this skill audits).
Audit coherence between claims, ledger state, and evidence anchors. Do not mutate analysis state. Do not run data queries unless a future scoped read-only reviewer tool explicitly allows it.
Use request_analysis_review(scope="plan_step", target_id=plan_step_id) when a high-risk or EDA-like step is completed and before setting ready_for_validation: true. Inspect the gate with get_review_gate; resolve checklist findings with resolve_review_finding after the underlying issue is fixed, or use accepted_with_rationale only when the user explicitly accepts the risk. A checklist-only review may clear ordinary deterministic blockers, but it must remain unknown when the request marked the scope as sub-agent-required.
unverified findings carry the mandatory caveatfinding_id or a valid evidence anchorWhen used as a reviewer prompt, return fenced JSON with a findings array. Each finding should include:
{
"severity": "required",
"category": "hypothesis_hygiene",
"claim": "Completed EDA step has an open high-priority leakage hypothesis",
"evidence": ["hyp-1234"],
"recommendation": "Resolve or defer the hypothesis before marking the step ready",
"status": "open"
}
Prefer precise required findings over broad commentary. Optional suggestions are useful only after required blockers are clear.