review-hog-resolution-criteria

Decides per unresolved pull request review thread whether to fix, decline, or escalate.

713|118|Updated Aug 11, 2020
One-click install
npx skills add https://github.com/PostHog/posthog-foss --skill review-hog-resolution-criteria
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-hog-resolution-criteria
Source: https://github.com/PostHog/posthog-foss/tree/main/products/review_hog/skills/review-hog-resolution-criteria
Command: npx skills add https://github.com/PostHog/posthog-foss --skill review-hog-resolution-criteria

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automated code review agents need a consistent, conservative bar for settling unresolved pull request review threads without human supervision. This Skill defines the resolution criteria for deciding, per thread, whether an ask is worth implementing and safe to implement unattended, preventing sloppy or oversized autonomous fixes.

Core Features & Use Cases

  • Four Outcome Decisions: Classifies each unresolved review thread as fixed, wont_fix, already_fixed/obsolete, or escalate based on worth and safety checks.
  • Worth and Safety Gates: Verifies the problem still exists at the current head, requires fixes to be provable in-session via lint and existing tests, and escalates anything needing infrastructure changes or ambiguous interpretation.
  • Human Override Handling: Honors standing verdicts like SAFE TO FIX and E2E REQUIRED written by humans in the thread.
  • Use Case: An unattended review-resolution agent processes a PR with 12 unresolved threads, implements three contained typo and null-check fixes, declines four speculative overengineering asks with reasons, and escalates two threads requiring schema changes to a human.

Quick Start

Apply the review-hog resolution criteria to settle each unresolved review thread on this pull request, fixing what is provably safe and escalating the rest.

Frequently Asked Questions about review-hog-resolution-criteria

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

FAQPage Schema
How do I automatically resolve pull request review comments?

Process each unresolved thread one at a time, judging its latest state against the current code head. Implement only contained, provable fixes verified by lint and existing tests; decline noise with a reason and escalate risky or ambiguous asks to a human.

What review comments should an automated fixer decline?

Decline overengineering asks, speculative what-if scenarios already ruled out by types or validation, defensive-coding paranoia, unreachable edge cases, and pure style preferences. Each decline must name the deliberate reason in plain language.

When should an automated code review fix escalate to a human?

Escalate when correctness is only observable live (LLM prompts, external APIs, deploy semantics), when the fix needs schema changes, migrations, new abstractions, or dependencies, when the comment is ambiguous, or when a human reply says E2E REQUIRED.

Can an automated fixer modify tests to make a fix pass?

Tests may change only to reflect deliberately changed, correct behavior called out in the reply. Weakening or removing a test to make a run pass is never acceptable; if provability requires touching the test itself, escalate instead.

How are human overrides handled in automated review resolution?

A human reply saying SAFE TO FIX substitutes for the worth judgment, so the fix is implemented after verifying it still holds against current code. E2E REQUIRED forces escalation regardless of other conclusions.