Agent skill

Address Review

by edgafner in edgafner/GBrowser

A skill your agent uses when told to check PR review, address feedback, resolve threads, or after creating a PR that received review comments.

Apache-2.0Auto-check passedDevelopment

Install Address Review

skills CLI
$ npx skills add edgafner/GBrowser --skill address-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install edgafner/GBrowser address-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/edgafner/GBrowser.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/address-review .claude/skills/address-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
address-review
GitHub stars
100
Token cost
~1.4k tokens
SKILL.md length
509 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when told to check PR review, address feedback, resolve threads, or after creating a PR that received review comments.

  • Works in 8 steps: Determine PR Number and Repo → Fetch ALL Review Feedback → Classify Each Thread/Comment → …
  • Told to check PR review
  • SKILL.md covers Usage, Step 1: Determine PR Number…, Step 2: Fetch ALL Review… and Step 3: Classify Each…, plus 7 more sections
  • Calls gh and git

What it does

Address Review is an agent skill from edgafner/GBrowser. Use when told to check PR review, address feedback, resolve threads, or after creating a PR that received review comments. Also use when user says "check the review", "address issues", or "resolve threads". Checks BOTH file-level review threads AND PR-level comments (Copilot, Claude bot, reviewers).

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests. It works with JetBrains IDEs. The repository describes itself as: A Browser embedded in your IDE. The licence is Apache-2.0.

When your agent uses it

  • Told to check PR review
  • Address feedback
  • Resolve threads
  • After creating a PR that received review comments

Example prompts

  • “check the review”
  • “address issues”
  • “resolve threads”
  • “/address-review”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Determine PR Number and Repo
  2. Fetch ALL Review Feedback
  3. Classify Each Thread/Comment
  4. Apply Fixes
  5. Commit & Push
  6. Resolve Threads
  7. Report
  8. Check CI Status

What it can do on your machine

Read from SKILL.md and the folder at commit fe34382. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Address Review loads about 1.4k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 509 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from edgafner/GBrowser at commit fe34382, republished under its Apache-2.0 licence (© edgafner). 509 words, ~1,392 tokens.

Download SKILL.mdSave it as .claude/skills/address-review/SKILL.md (or your agent's skills folder).
name
address-review
description
Use when told to check PR review, address feedback, resolve threads, or after creating a PR that received review comments. Also use when user says "check the review", "address issues", or "resolve threads". Checks BOTH file-level review threads AND PR-level comments (Copilot, Claude bot, reviewers).

Address PR Review

Fetch all review threads on a PR, address actionable issues, resolve fixed/no-op threads, and push fixes.

Usage

  • /address-review — find PR from current branch automatically
  • /address-review 123 — address review on PR #123

Step 1: Determine PR Number and Repo

If $ARGUMENTS is provided and is a number, use it as the PR number.

Otherwise, detect from current branch:

bash
gh pr list --head "$(git branch --show-current)" --json number,url --jq '.[0]'

If no PR found, ask the user which PR to address.

Set variables for use in all subsequent steps:

bash
PR_NUMBER=<detected or provided number>
OWNER=$(gh repo view --json owner --jq '.owner.login')
REPO=$(gh repo view --json name --jq '.name')

Step 2: Fetch ALL Review Feedback

Step 2a: Fetch Unresolved Review Threads (file-level comments)
bash
gh api graphql -f query='
query($owner: String!, $repo: String!, $number: Int!) {
  repository(owner: $owner, name: $repo) {
    pullRequest(number: $number) {
      reviewThreads(first: 100) {
        nodes {
          id
          isResolved
          path
          line
          comments(first: 10) {
            nodes {
              body
              author { login }
              createdAt
            }
          }
        }
      }
    }
  }
}' -f owner="$OWNER" -f repo="$REPO" -F number=$PR_NUMBER

Filter to only unresolved threads. This is the primary source for file-level review comments.

Step 2b: Fetch PR-level comments and review bodies

These are comments NOT attached to specific file lines — posted on the PR body itself.

Issue comments (bot summaries, reviewer questions):

bash
gh api repos/{owner}/{repo}/issues/$PR_NUMBER/comments

Review submissions (reviewer summaries posted via GitHub's "Submit review" button):

bash
gh api repos/{owner}/{repo}/pulls/$PR_NUMBER/reviews

Note: {owner} and {repo} are auto-substituted by gh when inside a git repo.

Filter to comments/reviews that contain actionable feedback. Ignore:

  • Bot status messages (CI reports with "all right", deployment notifications)
  • Approval-only reviews with empty body
  • "LGTM" or "looks good" comments
Consolidating feedback

Combine findings from Steps 2a and 2b into a single triage list. Step 2a covers file-level threads; Step 2b covers PR-level comments and review bodies. There should be no duplicates between them since they cover different types of feedback.

Step 3: Classify Each Thread/Comment

For each unresolved thread or actionable PR-level comment, read the comment and the current code at the file path + line:

ClassificationAction
Already fixedCode already addresses the concern → resolve
ActionableValid issue, code needs change → fix it
Praise / No-opPositive comment, no action needed → resolve
QuestionReviewer asked a question → reply with answer, then resolve

Step 4: Apply Fixes

If any threads are actionable:

  1. Edit the code to address the issue
  2. Build/test to verify (use the Quick Compilation Check table from root CLAUDE.md)
Show full SKILL.md (190 more words)Show less

Step 5: Commit & Push

If fixes were made:

  1. Stage only the changed files (not git add -A)
  2. Commit: fix: address PR review feedback
  3. Push to the PR branch

Step 6: Resolve Threads

For each addressed thread (fixed, already-fixed, praise, or answered):

bash
gh api graphql -f query='
mutation($threadId: ID!) {
  resolveReviewThread(input: {threadId: $threadId}) {
    thread { id isResolved }
  }
}' -f threadId="THREAD_ID"

Step 7: Report

markdown
## Review Address Summary — PR #<number>

| Thread | File | Action | Status |
|--------|------|--------|--------|
| "concern about X" | path/file.kt:42 | Already fixed | Resolved |
| "missing null check" | path/other.kt:15 | Fixed | Resolved |
| "nice pattern!" | path/file.kt:30 | No-op (praise) | Resolved |

**Fixes pushed:** Yes/No
**Threads resolved:** X/Y
**Remaining unresolved:** Z (with reasons)

Step 8: Check CI Status

After resolving threads and pushing fixes, check CI:

bash
gh pr checks $PR_NUMBER

Report: passing/failing/pending. If any check failed, show gh run view <run-id> --log-failed | tail -30.

Troubleshooting

  • If GraphQL query fails: verify $OWNER and $REPO match the actual repo (gh repo view)
  • If gh pr checks shows no checks: the CI may not have started yet — wait a moment and retry
  • If gh api returns 403: rate limited — wait or check gh auth status
  • If PR number is wrong: verify with gh pr list --head "$(git branch --show-current)"

Rules

  • NEVER duplicate comments on existing threads — check before commenting
  • NEVER re-report issues in unchanged code
  • ALWAYS resolve threads where the current code already addresses the concern
  • ALWAYS build/test before pushing fixes
  • Only create NEW commits for fixes (never amend previous commits)
  • If unsure whether an issue is fixed, read the current code first

© edgafner, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/address-review of edgafner/GBrowser.

Open the folder on GitHubat commit fe34382

Compare with similar skills

Address Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Address Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Address Review this skilledgafner/GBrowser100—~1.4kAutomated safety check: PassApache-2.0
Git WorkflowJetBrains/ideavim10k—~424Automated safety check: PassMIT
PR ChecklistSwttch/swttch203—~1.8kAutomated safety check: PassAGPL-3.0
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • Git Workflow

    JetBrains/ideavim

    Official

    IdeaVim git workflow conventions covering commits, branches, PRs, and CI.

    10k GitHub stars~424 tokensUpdated today
    DevelopmentAuto-check passed
  • PR Checklist

    Swttch/swttch

    Pre-PR review checklist for the claude-code-gui-jetbrains project.

    203 GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed

Works with

Categories

Questions about Address Review

What does Address Review do?

A skill your agent uses when told to check PR review, address feedback, resolve threads, or after creating a PR that received review comments. Address Review is an agent skill from edgafner/GBrowser. Use when told to check PR review, address feedback, resolve threads, or after creating a PR that received review comments.

When should I use Address Review?

Address Review fits situations like: told to check PR review; address feedback; resolve threads; after creating a PR that received review comments.

How do I install Address Review in Claude Code?

Run `npx skills add edgafner/GBrowser --skill address-review -a claude-code`. Or copy the skill folder (.claude/skills/address-review in edgafner/GBrowser) into .claude/skills/address-review in your project. Claude Code loads it when a task matches its description.

How do I install Address Review in Codex?

Run `npx skills add edgafner/GBrowser --skill address-review -a codex`. Or copy the skill folder (.claude/skills/address-review in edgafner/GBrowser) into .agents/skills/address-review in your project. Codex loads it when a task matches its description.

Can I use Address Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add edgafner/GBrowser --skill address-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/address-review, .gemini/skills/address-review, .github/skills/address-review and .opencode/skills/address-review in your project.

What does Address Review need to run?

Going by SKILL.md and its folder, Address Review needs the command-line tools its instructions call (gh and git).

Does Address Review access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Address Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Address Review use?

Address Review is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Address Review use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Address Review?

Skills that share tags, products or a category with Address Review: Git Workflow (JetBrains/ideavim, 10k stars), PR Checklist (Swttch/swttch, 203 stars), Finishing a Development Branch (obra/superpowers, 297k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Address Review?

edgafner (a GitHub organization) maintains it in edgafner/GBrowser, which has 100 GitHub stars. The repository was last updated on October 8, 2026.

Source: edgafner/GBrowser on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.