Skill
gh-address-comments: work through GitHub PR review comments
Official OpenAI Codex skill: fetch comments on the current branch's PR with the gh CLI, number them, then fix only the ones you pick; not tested.
This is a Codex skill in the curated folder of OpenAI's openai/skills repository. It lets Codex find the open PR for the current branch, read its comments and review threads, report them as a numbered list, and change code only after you choose. This page follows the official files, is not tested, and should be checked against the originals before use.
- Verified
- · Not tested by us
- How to invoke
- No official command
No fixed invocation command stated officially; agents/openai.yaml only carries a default prompt[1][6]
- Install
$skill-installer gh-address-commentsExample taken from the README, run inside Codex, restart Codex afterwards[4]
- License
- Apache-2.0 [3]
- Prerequisites
- Checked revision
49f948f- Tools
When to use
- The current branch has an open PR and its review comments need to be handled one by one.[2]
- You want a numbered summary first and then decide which comments to act on.[2]
When not to use
What it does and how it is invoked
SKILL.md describes the purpose: handle review or issue comments on the open GitHub PR for the current branch using the gh CLI, check gh login first, and prompt the user to authenticate if not logged in.[2]
- Step 1: run scripts/fetch_comments.py, which prints every comment and review thread on the PR.
- Step 2: number all threads and comments, summarize the fix each needs in a sentence, and ask which ones to address.
- Step 3: apply fixes only for the comments you select.
The official files give no fixed invocation command. agents/openai.yaml carries the default prompt "Address all actionable GitHub PR review comments in this branch and summarize the updates.", but the file does not say how it is triggered.[6]
Dependencies and prerequisites
| Category | What the official files say |
|---|---|
| Account | A logged-in GitHub identity; SKILL.md uses gh auth login as the example |
| CLI | The gh CLI; the script uses a python3 interpreter, version not stated officially |
| Permission | gh commands need elevated network access; gh auth status needs workflow and repo scopes; if the sandbox blocks it, rerun with sandbox_permissions=require_escalated |
| Cost | Not stated officially |
The script docstring says it relies on a completed gh login and requires the current branch to have an associated open PR.[5]
Install, license and repository status
The README installs curated skills by name with $skill-installer inside Codex, and says to restart Codex afterwards so the skill is picked up.[4]
LICENSE.txt in the skill folder is the Apache License 2.0 text.[3]
The README says each skill's license is the LICENSE.txt in its own folder.[4]
The folder listing at the pinned revision shows only LICENSE.txt, SKILL.md, agents, assets and scripts; no NOTICE file appears.[1]
The README opens with a notice that the repository is deprecated and points to the OpenAI Plugins repository. This page follows the pinned revision; whether the skill moves or changes later is to be confirmed.[4]
Sources
All links are official pages; verification dates are listed per source, and links point to the version checked.
- OpenAI · gh-address-comments
49f948f - OpenAI · SKILL.md
49f948f - OpenAI · LICENSE.txt
49f948f - OpenAI · README.md
49f948f - OpenAI · fetch_comments.py
49f948f - OpenAI · agents/openai.yaml
49f948f
Related tools
Codex
OpenAI’s software-development agent tools with local terminal workflows and cloud task entry points for inspecting, modifying, checking and reviewing projects.