K-Dense-AI/scientific-agent-skills / skills/peer-review
peer-review
VerifiedPrepares evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Supports authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and citation critique; or revision-response planning.
assets/statistical_reproducibility_template.json
View on GitHub{
"schema_version": "2.0",
"checklist_id": "STAT-REPRO-SYNTHETIC-001",
"study_design": "randomized_trial",
"specialist_review": {
"needed": "undetermined",
"areas": [],
"requested": false
},
"items": [
{
"id": "question.estimand_alignment",
"category": "question",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Check alignment among the question, target quantity, design, analysis, and interpretation"
},
{
"id": "design.unit_and_independence",
"category": "design",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Identify the experimental or observational unit and assess dependence"
},
{
"id": "design.sample_size_precision",
"category": "design",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess prospective sample-size or precision justification and assumptions"
},
{
"id": "design.allocation_randomization",
"category": "design",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess sequence generation, allocation concealment, or sampling procedures as applicable"
},
{
"id": "design.blinding",
"category": "design",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess who was blinded or masked and likely consequences when blinding was infeasible"
},
{
"id": "data.inclusion_exclusion",
"category": "data",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Trace prespecified inclusion, exclusion, attrition, and analysis populations"
},
{
"id": "data.missing_data",
"category": "data",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess missingness amounts, reasons, assumptions, methods, and sensitivity analyses"
},
{
"id": "data.outliers_transformations",
"category": "data",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Check rules for exclusions, transformations, detection limits, and influential observations"
},
{
"id": "analysis.prespecification",
"category": "analysis",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Compare analyses with the protocol, registration, and statistical analysis plan"
},
{
"id": "analysis.method_design_alignment",
"category": "analysis",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess whether methods match the design, outcome type, estimand, and sampling structure"
},
{
"id": "analysis.assumptions_diagnostics",
"category": "analysis",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess model assumptions, diagnostics, robustness, and fallback analyses"
},
{
"id": "analysis.multiplicity",
"category": "analysis",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess outcome hierarchy, repeated looks, multiple comparisons, and error control"
},
{
"id": "analysis.clustering_repeated_measures",
"category": "analysis",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess clustering, pairing, repeated measures, nesting, and time dependence"
},
{
"id": "results.effect_sizes_uncertainty",
"category": "results",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Check effect estimates and compatible uncertainty intervals, not thresholded p-values alone"
},
{
"id": "results.denominators_flow",
"category": "results",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Reconcile denominators, participant or sample flow, exclusions, and analysis populations"
},
{
"id": "results.complete_outcomes_harms",
"category": "results",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Check all prespecified outcomes, null findings, adverse events, and deviations"
},
{
"id": "reproducibility.data_materials_access",
"category": "reproducibility",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess data, materials, protocol, repository, and justified access restrictions"
},
{
"id": "reproducibility.code_environment_parameters",
"category": "reproducibility",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess code, software versions, environments, seeds, parameters, and run instructions"
},
{
"id": "reproducibility.provenance_versions",
"category": "reproducibility",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Trace data provenance, transformations, versioned artifacts, and accession identifiers"
},
{
"id": "ethics.approval_consent_governance",
"category": "ethics",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Assess approvals, consent, welfare, privacy, governance, and conflicts as applicable"
},
{
"id": "interpretation.claim_evidence_causality",
"category": "interpretation",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Check claim strength against design, evidence, uncertainty, alternatives, and generalizability"
},
{
"id": "integrity.deviations_selective_reporting",
"category": "integrity",
"applicability": "applicable",
"status": "not_assessed",
"evidence_locations": [],
"note": "",
"requested_action": "Check unexplained deviations, outcome switching, selective reporting, and internal inconsistencies"
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |