Results for “evidence-based-review”

Reviews closed trades, partial exits, and monthly trade aggregates for process adherence, risk discipline, execution quality, and evidence-based trading behavior patterns.

Evaluate scientific claims and evidence quality by assessing experimental design, identifying biases and confounders, and applying evidence grading frameworks like GRADE and Cochrane Risk of Bias.

Evaluate scientific manuscripts and grant proposals with structured, checklist-based peer review covering methodology, statistics, reproducibility, ethics, and reporting standards.

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

Turn interactive commit reviews back on for the current herdr workspace.

Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.

将一篇经管实证论文摄取为实证研究 wiki：论文卡片 + 变量 + 数据 + 模型 + 机制 + 识别 + 稳健性 + 异质性 + 表格线索

Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose

Classifies code review findings to choose the smallest correct response, preventing one-patch-per-comment churn.

Mines a codebase for evidence-backed improvement opportunities, forcing two escalation gates to surface breakthrough ideas, and outputs a ranked portfolio with a plan seed without implementing.

Conduct a thorough project-wide code review as an expert panel, cross-referencing specs, changelogs, and design documents

Transforms A/B test and product experiment data into actionable readouts with hypothesis, metrics, interpretation, and decision.

Routes quality reviews to specialized critic agents based on file type or flags, covering peer review, code review, and manuscript polish.

Clade coverage-driven project review — walks every VERIFY.md checkpoint, fixes failures in-session, converges when all checkpoints pass. NOT the Claude Code built-in /review (which reviews a single pull request diff) — if the user wants a PR review, route to /review-pr (Clade's PR reviewer) or the CC built-in.

Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.

Use when adapting academic findings for a public audience (op-ed, social post, podcast) and the simplification must stay evidence-faithful, avoid overclaiming, respect embargoes, and disclose AI assistance.

Use when reviewer comments arrive and each one needs a tracked decision, when a revise and resubmit letter must map every comment to a manuscript change, or when contradictory reviewer demands need evidence-based, editor-facing framing.