independent-review
CommunityStandardize reviewer prompts for code-review.
Authorramboz
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill creates a deterministic, frontmatter-driven reviewer prompt that lets Claude act as a read-only reviewer, evaluating deliverables against their spec without exposing internal implementation conversations.
Core Features & Use Cases
- Generates the four-bucket reviewer prompts for implementation review (compliance), craft/pr-review, architecture (arch-review, on-demand), and reconciliation framing.
- Supports optional richer user-installed skills and a read-only reviewer workflow, with normalized output into a single verdict envelope.
- Includes a helper to select the subagent type (reviewer vs. general-purpose) and accommodates multiple modes: implementation, reconciliation, pr-review, arch-review, design-review, frame-critique, code-health, etc.
Quick Start
Run python3 review.py implementation <spec.md> <slice-fragment> <deliverable-path>... to generate the prompt and feed it to Claude's Task tool.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: independent-review Download link: https://github.com/ramboz/jig/archive/main.zip#independent-review Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.