Agent skill · Code Review & Quality

process-pr-reviews

Use when the user asks to process, triage, fetch, view, count, list, or resolve review feedback in a GitHub PR. Supports both CodeRabbit and Codex review workflows. In this workflow, “real review feedback” is strictly defined as actionable inline comments; for CodeRabbit, exclude review summaries and nitpicks, and for Codex, exclude review summary cards and use PR main-thread reactions only as status signals.

nexu95,528★ · +2,037/wk · 5 repos on radarProfile →
claude-codecodexMIT
Install
npx skills add nexu-io/nexu --skill process-pr-reviews --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 10 KB
Bundled scripts: none
Path: .agents/skills/process-pr-reviews/SKILL.md
Open the folder on GitHub →
Where it comes from
Source: nexu-io/nexu
Stars: 3,239
Language: TypeScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Process PR Reviews This workflow supports both CodeRabbit and Codex PR review signals. ## CodeRabbit Reviews “Real review feedback” is strictly defined as: - **inline review comments** - **not** a review summary - **not** a nitpick Nitpick comments from CodeRabbit must always be ignored to avoid unnecessary noise. There is no need to analyze the comment content itself. ### Data sources The CodeRabbit workflow only needs these two sources: 1. **PR review comments** ```bash gh api --paginate repos/<owner>/<repo>/pulls/<pr_number>/comments ``` This is the authoritative source for real inline comments. 2. **PR reviews** ```bash gh api --paginate repos/<owner>/<repo>/pulls/<pr_number>/reviews ``` This is only used to identify and exclude review summaries / nitpick summaries. It is not used to extract the final result. Do not treat these as primary sources: - `gh pr view ...` - `gh api repos/<owner>/<repo>/issues/<pr_number>/comments` Reason: they are not the authoritative source for actionable inline comments. ### Workflow #### 0. Optional: fetch review thread IDs early if resolve/dismiss may be needed If the user may ask you to resolve review conversations after triaging them, fetch

What's inside
Steps it walks through
  1. CodeRabbit Reviews
  2. Data sources
  3. Workflow
  4. Filtering rule
  5. Large output handling
  6. Resolving review conversations
  7. Resolution policy
  8. Codex Reviews
  9. Important behavior differences from CodeRabbit
Commands it runs
gh api --paginate repos/<owner>/<repo>/pulls/<pr_number>/comments
gh api --paginate repos/<owner>/<repo>/pulls/<pr_number>/reviews
gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "<thread_id>"}) { thread { isResolved } } }'
gh api repos/<owner>/<repo>/issues/<pr_number>/comments
gh api repos/<owner>/<repo>/issues/<pr_number>/reactions
More from nexu
All skills →
About this skill
What does the process-pr-reviews skill do?

Use when the user asks to process, triage, fetch, view, count, list, or resolve review feedback in a GitHub PR. Supports both CodeRabbit and Codex review workflows. In this workflow, “real review feedback” is strictly defined as actionable inline comments; for CodeRabbit, exclude review summaries and nitpicks, and for Codex, exclude review summary cards and use PR main-thread reactions only as status signals.

How do I install it?

Run `npx skills add nexu-io/nexu --skill process-pr-reviews --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From nexu-io/nexu, a repository with 3,239 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going