Skip to content

Feature Human Style Review Output

Jump to bottom
amirbena edited this page Sep 17, 2026 · 2 revisions

Feature: Human-Style Review Output

A Feature-Pages entry. This page explains the capability; it never redefines it — see Feature-Pages for the canonical/Wiki boundary statement that applies to every page in this pattern.

What it does

Renders the final human-facing summary in a concise senior-engineer voice instead of the default structured shape: a short opening on merge safety and the top concern, then what's good / what's concerning / what to change in prose — each referenced finding keeping its P0/P1/P2 label. A companion option, human_inline_findings, extends the same voice to github-pr-review's inline comments.

Why it exists

A full structured report is the right default for auditability, but a short, readable verdict is often what's actually wanted when pasting a result into a chat or a PR description, or skimming many reviews at once.

When it applies

Explicitly requested, in natural language — no CLI flag. Recognized from a small, fixed phrase vocabulary (e.g. "review it like a senior engineer", "use concise review comments"); anything outside that vocabulary is ambiguous and does not set it. Applies to both Skills. local-code-review re-renders its report's summary; github-pr-review re-renders the final review summary comment (and the self-review informational COMMENT), and also re-voices any finding rendered in full in the review body (every finding in a passive review, or an active-review finding with no valid inline anchor).

How it works

human_inline_findings's default is derived — explicit_value ?? human_review_output — so turning on senior mode turns it on too; state it explicitly only to opt out (or to opt into the inline voice on its own, structured summary). It is presentation only in both directions: finding detection, severity, identity, deduplication, evidence, the mechanical decision, the GitHub review state, the canonical fix/action anchor, and the batched publication order are all unchanged.

Important options / modes

Invocation Summary Inline findings
default structured structured template
human_review_output on senior voice senior voice (derived)
human_review_output on + human_inline_findings=false senior voice structured template
human_review_output off + human_inline_findings=true structured senior voice

The option is normalized from the current invocation only — it never carries over to a later review or re-review in the same conversation. Publishing a previously-passive review that doesn't state a presentation asks once (Senior/human or Structured) before publishing.

Example

review PR #812 like a senior engineer

Related features

Canonical references

Wiki Page Map

Page What it covers
Home Wiki entry point: what the two Skills are and where to go next.
Getting-Started First steps to package and run either Skill.
Choosing-a-Review-Skill How to decide between local-code-review and github-pr-review.
How-the-Review-Model-Works Concept-level walkthrough of the review pipeline shared by both Skills.
Architecture-Overview Component-level map of how the repository's pieces fit together.
Specialist-Depth-Review When and how a review goes deeper than its base pass.
Local-Code-Review-Guide Usage guide for reviewing local, not-yet-PR'd Git changes.
GitHub-PR-Review-Guide Usage guide for reviewing an existing GitHub Pull Request.
Review-Context-and-Existing-Evidence How optional requirements/context and prior review evidence are supplied.
Feature-Pages Index of per-feature capability pages and their shared template.
Feature-Delta-Re-Review How a re-review scopes itself to only what changed since the last pass.
Feature-GitHub-Publication-and-Authorization What a PR review publishes to GitHub and under what authority.
Feature-Human-Style-Review-Output The senior-engineer-voice prose summary output option.
Feature-Requirement-Coverage How supplied requirements are checked and reported as covered or not.
Feature-Runtime-Validation-Evidence How a review can execute commands or reproductions as evidence.
Severity-and-Decision-Model The P0/P1/P2 severity levels and how the merge decision is derived.
Packaging-and-Portability How the Skills go from source repository to a standalone archive.
Development-Workflow Contributor guide for working on this repository itself.
Benchmark-Testing Orientation to this repository's own review-quality benchmark pipeline.
Repository-Documentation-Map Where each concern's canonical, authoritative source lives.
AI-Code-Review-Landscape Neutral snapshot comparing this project against other AI code-review products.
FAQ Short, practical answers to common questions.

Clone this wiki locally