skills.rest
yiwei79
yiwei79OFFICIAL
Explore all skills by this author →
GitHub

cursor-review-insights

Generate governed D32 JSONL code-review insights for inbox triage.

Updated Apr 8, 2026
Search Tags:#insights#inbox#governance#code-review#blindspots#cursor#jsonl
One-click install
npx skills add https://github.com/yiwei79/azoth --skill cursor-review-insights
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cursor-review-insights
Source: https://github.com/yiwei79/azoth/tree/main/.opencode/skills/cursor-review-insights
Command: npx skills add https://github.com/yiwei79/azoth --skill cursor-review-insights

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cursor-based code-review processes often miss blindspots during reviews. This Skill generates a repeatable, governance‑compliant review pass that outputs structured insights to the inbox for triage and action.

Core Features & Use Cases

  • Produces governed D32 JSONL insights for downstream inbox-based triage.
  • Targets common blindspots in code-review workflows and supports human gating via intake.
  • Use Case: when a team needs a repeatable review sweep to surface potential bugs, quality issues, or policy violations and have them delivered to the inbox for decision-making.

Quick Start

Execute a Cursor review pass to generate D32 insights and push them to the inbox.

Frequently Asked Questions about cursor-review-insights

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

FAQPage Schema
How do I automate code-review sweeps to find blindspots in Cursor?▼

Automated code-review sweeps in Cursor find blindspots by generating governed D32 JSONL insights, which are then pushed to your inbox for structured human triage and decision-making.

What is the D32 JSONL format for code review insights?▼

The D32 JSONL format for code review insights is a governance-compliant structure containing fields like id, source, severity, evidence, summary, recommended_action, and requires_human_gate to standardize triage.

How do I deliver code review findings to an inbox for triage?▼

Deliver code review findings to an inbox by executing a Cursor review sweep that formats identified bugs and issues into governed D32 JSONL insights for downstream intake workflows.

Can I use Cursor for governance-compliant bug hunts with human gating?▼

Yes, you can use Cursor for governance-compliant bug hunts by generating D32 JSONL insights that include a requires_human_gate field, ensuring identified issues route to an inbox for manual triage.

What fields are required for governance-compliant code review insights?▼

Governance-compliant code review insights require fields specified in kernel/GOVERNANCE.md, including id, source, source_type, timestamp, category, severity, target, evidence, summary, recommended_action, auto_applicable, and requires_human_gate.

When should I use automated code review sweeps instead of manual review?▼

Use automated code review sweeps when you need a repeatable process to surface potential bugs, quality issues, or policy violations across a Cursor environment, leaving final decisions to human triage via inbox intake.

Related Skills

Explore More Software Engineering Skills→
PayIt2PayIt2
1

campaign-context

Gather minimal campaign context before executing campaign-related commands.

Official
Advanced
PoleBarnesPoleBarnes

email

Triage and summarize email inbox contents via Gmail's MCP server.

Official
Intermediate
bitwardenbitwarden
129

classifying-review-findings

Classify code review findings into Bitwarden severity categories with emoji labels.

Official
Basic
gofhirgofhir
2

go-code-review

Analyze Go source code with golangci-lint and go vet for bugs and race conditions.

Official
Intermediate