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.
SkillScore73Maintained
Automatic
◆Coding pack
Last verified 8/4/2026
What it changes
Passed 14 of 19 test cases with the skill, and 12 of 19 without it.
Without skill62%
With skill73%
Checks it passed that the model alone missed
Delegates processing of the large JSON output file to explorer.
Filters comment user login field for chatgpt-codex-connector[bot].
Uses reviews endpoint to identify review-level summaries and nitpick markers.
and 2 more in the full report
5 fixed14 passed either way5 still failing2 broke
Pass-rate lift
+12 pp
Tokens
+89%
Agent turns
0%
Response time
-57%
Model gemini-3.6-flashMeasured 8/4/2026v119 of 26 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
When sifting through inline comments in repos/nexu-io/core/pulls/115/comments, what exact user login identifier corresponds to Codex review comments?
What was checked, without and with the skill
Checked
Without skill
With skill
Filters comment user login field for chatgpt-codex-connector[bot].
Missed
Passed
case-17 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md276 linessingle file
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:
PR review comments
gh api --paginate repos/<owner>/<repo>/pulls/<pr_number>/comments
This is the authoritative source for real inline comments.
PR reviews
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