review

Evaluate hypotheses across six review modes and log structured critique scores.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/achousal/EngramR --skill review-achousal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/achousal/EngramR/tree/main/.claude/skills/review
Command: npx skills add https://github.com/achousal/EngramR --skill review-achousal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Critically evaluate and synthesize hypothesis reviews across multiple lenses to improve evidence quality and decision-making in research workflows.

Core Features & Use Cases

  • Supports 6 review modes (Quick Screen, Literature Review, Deep Verification, Observation Review, Simulation Review, Tournament-Informed Review) to systematically critique hypotheses.
  • Reads and writes to Vault paths _research/hypotheses/ and _research/meta-reviews/ to maintain provenance.
  • Automates update of frontmatter scores and a timestamped Review History, enabling traceable evaluation.
  • Use Case: Researchers batch-review hypotheses to surface issues and track improvements.

Quick Start

Review a selected hypothesis using the Quick Screen and proceed to deeper modes if needed.

Frequently Asked Questions about review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I critically evaluate and score research hypotheses in a vault?

Critically evaluate hypotheses by applying six review modes to generate structured critique scores and flags, reading and writing results to _research/hypotheses/ and _research/meta-reviews/ vault paths.

What is the best way to track hypothesis review history and update frontmatter?

Tracking review history involves automating frontmatter score updates and appending timestamped logs, ensuring non-destructive vault I/O while maintaining provenance across meta-reviews.

Can I batch review multiple hypotheses using different evaluation modes?

Batch reviewing hypotheses is supported through six modes including Quick Screen, Literature Review, and Deep Verification, systematically critiquing each to surface issues and track improvements.

Does the hypothesis review process require external dependencies?

No external dependencies are required for the hypothesis review process, which operates with non-destructive vault I/O to safely read and write evaluation scores and review logs.

When should I use a simulation review versus a tournament-informed review?

Simulation review critiques hypotheses against simulated data, while tournament-informed review evaluates them based on tournament outcomes, both generating structured critique scores and flags.