# Review

Enter the Review phase of CocoBrew.

- Repository: https://github.com/Snowflake-Labs/cocoplus (727 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-04
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Snowflake-Labs/cocoplus --skill review -g -a claude-code -y`
Codex: `npx skills add Snowflake-Labs/cocoplus --skill review -g -a codex -y`
Cursor: `npx skills add Snowflake-Labs/cocoplus --skill review -g -a cursor -y`
Gemini CLI: `npx skills add Snowflake-Labs/cocoplus --skill review -g -a gemini-cli -y`

## Description

Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec compliance check, and decision coverage gate. Produces review.md with decision points. Requires developer approval before $ship can proceed.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

You are executing the Review phase (5/6) of CocoBrew.

Before proceeding, verify that `.cocoplus/` exists.
If not: output "CocoPlus not initialized in this directory. Run `$pod init` to begin." Then stop.

Read `.cocoplus/lifecycle/meta.json`. Verify `phases_completed` contains `"test"`.
If not: output "The Test phase must be completed before review. Run `$test` first." Then stop.

## Aggregate Findings

Collect from these sources:

**1. Code Quality Findings**
Look for files matching `.cocoplus/quality-findings-*.md`. Read all and extract critical and high severity findings.

**2. CocoCupper Findings**
Read `.cocoplus/grove/cupper-findings.md`. Extract the most recent 5 findings.

**3. Spec Compliance Check**
Read `.cocoplus/lifecycle/spec.md` (Success Criteria, Deliverables) and `.cocoplus/lifecycle/test.md`.
For each success criterion: was it tested? Did it pass?
For each deliverable: does the file/table/artifact exist?

**4. Test Summary**
Read `.cocoplus/lifecycle/test.md`. Extract pass/fail summary.

**5. Decision Coverage Check**

Extract key decisions from `plan.md` (and `discuss.md` if it exists): evaluation target, data source, accuracy threshold, model to use, warehouse assignment, production safety requirements.

For each extracted decision, scan implementation artifacts, SQL functions, evaluation configurations, `flow.json` stage definitions, prompt files, for evidence that the decision is honored in the implementation.

A decision is **honored** if the artifact reflects the stated value or approach. A decision is a **Coverage Gap** if it is present in plan/discuss but absent or contradicted in the implementation.

Coverage Gaps are severity-equivalent to must-fix. `$ship` is blocked until all Coverage Gaps are resolved or explicitly acknowledged with a documented rationale written into `review.md`.

## Write Review Document

Write `.cocoplus/lifecycle/review.md`:

```markdown
# Review Report

The rest: https://github.com/Snowflake-Labs/cocoplus/blob/HEAD/.cortex/skills/cocobrew/review/SKILL.md