Multi Review — Testing skill for Claude Code
Multi-review — a star review (you as primary + N independent secondaries) over a spec/plan doc or a PR, converging to a human gate.
How to install Multi Review
Installs to ~/.claude/skills/agrology-multi-review-multi-review/SKILL.md
mkdir -p ~/.claude/skills/agrology-multi-review-multi-review && curl -fsSL https://raw.githubusercontent.com/agrology/multi-review/HEAD/commands/multi-review.md -o ~/.claude/skills/agrology-multi-review-multi-review/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Multi Review does
description: Multi-review — a star review (you as primary + N independent secondaries) over a spec/plan doc or a PR, converging to a human gate. argument-hint: "[doc-path | PR-URL] [--reviewers ]"
You are the **primary** in a multi-review star review: you dispatch N independent secondaries, adjudicate their findings, and drive convergence — always stopping at a **human gate**. `fable` is one of the secondaries by default (your guaranteed in-harness review voice) and any `--reviewer
Alternatives in Testing
- OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
- Spec Driven Development — Drive Kandev feature work through spec, plan, independent tasks, implementation, QA, and verification 697 ★
- Setup Metrics — Set up your metrics framework — North Star selection, funnel definition, dashboard structuring, and A/B test d 73 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Sdflow Skills
Spec-driven development workflow for Claude Code / Codex: clarify → grill → generate the four artifacts, multi
Plan Freeze
Commit the active feature's spec.md + plan.md on a plan/ branch and open a PR for human review. Wraps scripts/
Feature Team
Run a multi-task plan with the implementer→spec-review→quality-review loop using the model ladder. For COMPLEX
Deepreview Spec
Multi-agent parallel spec/plan review with cross-validation
Captain Claude Code
Captain Claude Code (CCC): a Claude skill that takes a non-technical founder from a product spec to a working
Codex Goal Handoff
Turn a ticket into a verified, deployed PR — wraps OpenAI Codex CLI's /goal Ralph loop with a 4-file durable s
Related Agents
Claim Extractor.Agent
Same-family claim-extraction agent for the primary-source-verification (psv) skill. Runs in a fresh, independe
Build Pattern Scanner
Scans GitHub, Show HN, Bluesky, cv.inc hackathon galleries, and Hugging Face Spaces for independent small-buil
Fleet Plan Alt
Second planning opinion from an independent model. Use when the user asks for another view, when a plan needs