skills.rest
NSObjects
NSObjectsCOMMUNITY
Explore all skills by this author →
Website𝕏@servenstayGitHub

requesting-code-review

Dispatch specpowers:code-reviewer subagent and synthesize specialist findings into one review.

4|1|Updated Apr 7, 2026
Search Tags:#spec-driven#subagent#code-review#security-review#review-orchestration#specialist-reviewer
One-click install
npx skills add https://github.com/NSObjects/specpowers --skill requesting-code-review-nsobjects
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/NSObjects/specpowers/tree/main/skills/requesting-code-review
Command: npx skills add https://github.com/NSObjects/specpowers --skill requesting-code-review-nsobjects

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill guarantees that standalone manual reviews happen with bounded scope and a single synthesized decision, preventing cascading issues before the work is merged.

Core Features & Use Cases

  • Unified review orchestration: The main agent dispatches the general specpowers:code-reviewer subagent, optionally escalates to specialist reviewers, and reconciles every finding into one conclusion.
  • Guided escalation rules: Only trigger specialists such as the security reviewer when a concrete risk area is identified, keeping review depth efficient.
  • Use case: After finishing a major feature or complex fix, request a review with clarified SHAs and spec scenarios to verify compliance before merging.

Quick Start

Dispatch specpowers:code-reviewer with the implemented scope, spec scenarios, and SHAs so the unified review can begin.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
How do I orchestrate a standalone code review before merging a major feature branch?▼

To orchestrate a standalone code review, dispatch the general code-reviewer subagent with your implemented scope, spec scenarios, and relevant SHAs, then synthesize all findings into a single unified decision before merging.

When should I request a dedicated code review instead of relying on per-task spec reviews?▼

Request a dedicated code review when reviewing entire branches, major features, or high-stakes fixes outside of per-task spec reviews, ensuring bounded scope and a single synthesized decision to prevent cascading issues.

How does guided escalation to specialist reviewers work during a security review?▼

Guided escalation triggers specialist reviewers, such as a security reviewer, only when a concrete risk area is identified by the initial code review, keeping the review depth efficient and focused on actual vulnerabilities.

What information do I need to provide to start a focused code review?▼

Start a focused code review by providing the implemented work scope, spec scenarios, and relevant commit SHAs, which allows the reviewing subagent to verify compliance and catch regressions effectively.

Can I use this to review high-stakes fixes outside my normal spec-driven workflow?▼

Yes, this workflow is designed specifically for standalone manual reviews of high-stakes fixes and complex features outside your normal spec-driven per-task reviews, guaranteeing bounded scope before merge.

What is the best way to reconcile multiple specialist findings into one merge decision?▼

Reconcile multiple specialist findings by having the main agent synthesize every escalated review result into a single unified conclusion, preventing scattered feedback and ensuring one clear merge decision.

Related Skills

Explore More Software Engineering Skills→
liamtran96liamtran96

requesting-code-review

Dispatch a code-reviewer subagent to assess code quality, architecture, testing, and production readiness.

Community
Basic
tatsushige-itatsushige-i

git-branch-cleanup

Delete non-main local Git branches and pull latest changes.

Community
Intermediate
LerianStudioLerianStudio
205

subagent-driven-development

Automate subagent-driven development with fresh subagents per task and automated reviews.

Official
Advanced
RedWoodOGRedWoodOG
174

subagent-driven-development

Automate multi-task implementation plans with isolated subagents and two-stage reviews.

Community
Advanced