resolve-pr-feedback

Cluster unresolved GitHub PR review threads and dispatch resolvers via the gh API.

1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/lucasmccomb/ccgm --skill resolve-pr-feedback-lucasmccomb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: resolve-pr-feedback
Source: https://github.com/lucasmccomb/ccgm/tree/main/modules/pr-feedback/skills/resolve-pr-feedback
Command: npx skills add https://github.com/lucasmccomb/ccgm --skill resolve-pr-feedback-lucasmccomb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Turn a pile of unresolved GitHub PR review threads into a small set of cluster-aware fix plans and automated actions, reducing noise and surfacing systemic issues before making code changes. It prevents ten one-off replies from obscuring two or three real concerns and avoids unnecessary churn by triaging handled vs new threads and grouping related feedback by category and spatial proximity.

Core Features & Use Cases

  • Fetch & Triage: Retrieve unresolved review threads via GraphQL and classify them as new, handled-not-replied, handled-and-replied, or outdated.
  • Cluster Analysis: Group new threads into one of eleven fixed categories and by spatial proximity to surface systemic issues and produce per-cluster fix hypotheses.
  • Dispatch & Safety Gates: Dispatch parallel pr-comment-resolver subagents for safe fixes, gate ambiguous changes for confirmation, batch manual/taste decisions for humans, and post advisory replies without code changes.
  • Modes & Artifacts: Support interactive, autofix, report-only, and headless modes and write run artifacts and manual-decision briefs for cross-invocation continuity and auditing.

Quick Start

Use the resolve-pr-feedback skill to fetch unresolved review threads for PR 123 in owner/repo and produce a clustered plan in interactive mode.

Frequently Asked Questions about resolve-pr-feedback

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

FAQPage Schema
How do I automatically resolve GitHub PR review comments?

To automatically resolve GitHub PR review comments, this skill fetches unresolved review threads via GraphQL, classifies them by status, groups related feedback into cluster-aware fix plans, and dispatches targeted resolvers to post inline replies and close threads through the gh API.

How does clustering pull request review threads work?

Clustering pull request review threads works by grouping new, unresolved comments into eleven fixed categories based on feedback type and spatial proximity, which surfaces systemic issues and produces per-cluster fix hypotheses before dispatching automated agents.

Do I need GraphQL access to triage unresolved PR review threads?

Yes, you need GraphQL access to triage unresolved PR review threads. The skill requires GraphQL access to read review thread state and local git history to compare branch commits for addressed threads and dispatch per-cluster automated agents.

What is the best way to group related code review feedback on GitHub?

The best way to group related code review feedback on GitHub is to triage handled versus new threads and cluster them by category and spatial proximity, preventing multiple one-off replies from obscuring a few real systemic concerns.

Can I run PR comment resolution in report-only or autofix mode?

Yes, you can run PR comment resolution in interactive, autofix, report-only, or headless modes. The skill dispatches parallel subagents for safe fixes, gates ambiguous changes for confirmation, and batches manual taste decisions for human review.

What are the limitations of automating GitHub PR thread resolution?

Limitations of automating GitHub PR thread resolution include the strict requirement for repository GraphQL access and local git history, while ambiguous changes are gated for confirmation and manual taste decisions are batched for humans rather than auto-applied.