Agent skill

Address Current Branch Review

by epam in epam/ai-dial-chat

Read unresolved GitHub code review threads for the pull request associated with the current branch, classify each comment, and implement and verify required code fixes.

Apache-2.0Auto-check passedDevelopment

Install Address Current Branch Review

skills CLI
$ npx skills add epam/ai-dial-chat --skill address-current-branch-review -a claude-code

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

GitHub CLI
$ gh skill install epam/ai-dial-chat address-current-branch-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/epam/ai-dial-chat.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/address-current-branch-review .claude/skills/address-current-branch-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-current-branch-review
GitHub stars
504
Token cost
~1.7k tokens
SKILL.md length
865 words
Files
2
Skills in repo
18
Repo updated
First seen
Licence
Apache-2.0

At a glance

Read unresolved GitHub code review threads for the pull request associated with the current branch, classify each comment, and implement and verify required code fixes.

  • Works in 11 steps: Read repository instructions before… → Resolve the current pull request. → Load thread-aware review data. → …
  • Explicitly asks to reply after the changes have been pushed and are visible in the PR
  • SKILL.md covers Reply Authorization Gate, Workflow, Reply Patterns and Safety Rules
  • Calls gh

What it does

Address Current Branch Review is an agent skill from epam/ai-dial-chat. Read unresolved GitHub code review threads for the pull request associated with the current branch, classify each comment, and implement and verify required code fixes. Post inline replies only when the user explicitly asks to reply after the changes have been pushed and are visible in the PR.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: A default UI for AI DIAL. The licence is Apache-2.0.

When your agent uses it

  • Explicitly asks to reply after the changes have been pushed and are visible in the PR
  • Tasks that involve Pull requests

Example prompts

  • “/address-current-branch-review”

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Read repository instructions before editing.
  2. Resolve the current pull request.
  3. Load thread-aware review data.
  4. Prevent duplicate work.
  5. Classify each active thread.
  6. Implement fix-required threads.
  7. Verify each fix.
  8. Draft a reply without posting it.
  9. Stop after implementation unless replies were explicitly requested.
  10. If and only if replies were explicitly requested, check PR visibility and post.
  11. Summarize.

What it can do on your machine

Read from SKILL.md and the folder at commit 7cb891d. 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

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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 Current Branch Review loads about 1.7k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 865 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 epam/ai-dial-chat at commit 7cb891d, republished under its Apache-2.0 licence (© epam). 865 words, ~1,696 tokens.

Download SKILL.mdSave it as .claude/skills/address-current-branch-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
address-current-branch-review
description
Read unresolved GitHub code review threads for the pull request associated with the current branch, classify each comment, and implement and verify required code fixes. Post inline replies only when the user explicitly asks to reply after the changes have been pushed and are visible in the PR.

Address Current Branch Review

Process current-branch review feedback: inspect thread state, decide whether code must change, and verify any fix. Treat posting review replies as a separate, explicitly authorized action after push.

Reply Authorization Gate

  • A request to fix, handle, address, or process review comments authorizes code changes only. It does not authorize posting GitHub comments.
  • Post replies only when the user separately and explicitly asks to reply or answer the review comments.
  • Before posting a fix reply, verify that the relevant commit is pushed and included in the PR head. Local working-tree changes or unpushed commits are never sufficient.
  • If the fix is not visible in the PR, do not post. Tell the user to push first.
  • Replies must describe the current PR state as already updated or fixed. Never post wording such as “prepared locally,” “will appear after push,” or any other future-tense visibility disclaimer.

Workflow

  1. Read repository instructions before editing.

    • Read root AGENTS.md and openspec/config.yaml.
    • Invoke nx-workspace before exploring project ownership or targets.
    • Apply any area-specific skill required by the touched files.
  2. Resolve the current pull request.

    • Read the current branch and origin repository from local git.
    • Prefer the GitHub app to find the open PR whose head matches the branch.
    • Use gh pr view only when the GitHub app cannot resolve it.
    • Stop if there is no unique open PR for the branch.
  3. Load thread-aware review data.

    • Use the GitHub app review-thread action to get is_resolved, is_outdated, path, line, and replies.
    • Fetch flat PR comments for numeric comment IDs only when the user explicitly asked to post replies.
    • Ignore resolved, outdated, approval-only, informational, bot-only, and duplicate threads.
    • Do not assume flat comments represent thread resolution state.
  4. Prevent duplicate work.

    • Read every reply already present in the thread.
    • Skip a thread if the requested change is already present in the current code and an adequate answer was already posted.
    • If code is fixed but unanswered, report that status. Post the missing reply only after explicit reply authorization and the push check.
  5. Classify each active thread.

    ClassificationAction
    fix-requiredChange code, add or update tests, and verify. Do not reply unless authorized.
    reply-onlyDraft a technical explanation. Post it only when explicitly authorized.
    ambiguousDo not guess or post; ask the user for the missing decision.
    conflictingExplain the conflict and ask before changing behavior.
  6. Implement fix-required threads.

    • Inspect the full affected file and related tests, not only the diff hunk.
    • For multi-file work, build in thin vertical slices and verify each slice (see the task rules in openspec/config.yaml).
    • Keep every change traceable to a specific review thread.
    • Preserve unrelated user changes and staged files.
    • Do not commit, push, or force-update branches unless explicitly requested.
  7. Verify each fix.

    • Use Nx through the workspace package manager.
    • Choose the smallest relevant tests first, then run project lint and build when appropriate.
    • Never claim a fix passed if the required command failed or was not run.
    • If verification fails, continue fixing and do not post a success reply.
  8. Draft a reply without posting it.

    • Match the reviewer's language when practical.
    • Keep it concise and technical.
    • For a verified fix, state what changed and the relevant check.
    • For reply-only, explain why no code change is needed and reference the existing behavior or contract.
    • Do not be defensive, over-apologetic, or vague.
    • Do not use local-only or future-tense wording.
  9. Stop after implementation unless replies were explicitly requested.

    • Summarize local changes and verification to the user.
    • Do not call any GitHub reply/comment mutation.
  10. If and only if replies were explicitly requested, check PR visibility and post.

    • Fetch the current PR head SHA immediately before posting.
    • Verify that the pushed PR head contains the relevant fix commit and that the fix appears in the PR diff.
    • If the local fix is uncommitted, unpushed, or absent from the PR diff, stop without posting.
    • Prefer the GitHub app inline reply action using the thread's top-level numeric review comment ID.
    • Map GraphQL thread comments to numeric IDs through the flat PR comment list when necessary.
    • Use gh api graphql only as a fallback.
    • Post at most one new reply per processed thread.
    • Do not resolve threads, submit a review, approve, request changes, commit, or push unless explicitly requested.
  11. Summarize.

    • List fixed threads and whether each fix is visible in the PR.
    • List replies posted only when posting was explicitly requested.
    • List reply-only threads.
    • List skipped or ambiguous threads.
    • Report verification commands and any remaining warnings.
Show full SKILL.md (118 more words)Show less

Reply Patterns

Verified and visible:

text
Updated: moved error handling to the global NotificationContext. Verified with `npm exec nx test chat` and `npm exec nx lint chat`.

No code change needed:

text
No code change is needed here: the value is provided through an app-level adapter, so the library remains unaware of the REST path and preserves isolation.

Safety Rules

  • Never treat a request to fix review feedback as permission to post a GitHub reply.
  • Never post a fix reply until the user explicitly asks for it after pushing.
  • Never post a fix reply when the change is only local or unpushed.
  • Never use “prepared locally,” “will appear after push,” or equivalent wording in a review reply.
  • Never reply before understanding the full thread and current code.
  • Never post a success reply for an unverified fix.
  • Never fabricate test results, commit SHAs, or PR visibility.
  • Never silently resolve a conversation.
  • Never answer an ambiguous behavioral request on the reviewer's behalf.
  • Never overwrite, unstage, or revert unrelated changes.

© epam, 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

SKILL.md and 1 other file in .claude/skills/address-current-branch-review of epam/ai-dial-chat.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 7cb891d

Compare with similar skills

Address Current Branch 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 Current Branch Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Address Current Branch Review this skillepam/ai-dial-chat504—~1.7kAutomated safety check: PassApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • 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
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from epam/ai-dial-chat

All 18 skills in this repo
  • Refactoring Audit

    epam/ai-dial-chat

    Deep codebase refactoring audit for AI DIAL Chat. An agent skill from epam/ai-dial-chat.

    504 GitHub stars~4.3k tokensUpdated today
    Auto-check passed
  • Create Ticket

    epam/ai-dial-chat

    Interactively create OR update GitHub issues (Bug, Feature, Task) for the current repository.

    504 GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Dep Scan

    epam/ai-dial-chat

    Runs Trivy filesystem scan against the repo root and emits structured vulnerability findings (CVE, package, versions) in the SDLC reviewer schema.

    504 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Figma

    epam/ai-dial-chat

    Design-to-code workflow for Figma designs. An agent skill from epam/ai-dial-chat.

    504 GitHub stars~997 tokensUpdated today
    Auto-check passed
  • Git Ship

    epam/ai-dial-chat

    A skill your agent uses whenever the user wants to commit, push, or ship changes in a git repository.

    504 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Responsive Design

    epam/ai-dial-chat

    Responsive (mobile + desktop) layout workflow. An agent skill from epam/ai-dial-chat.

    504 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Address Current Branch Review

What does Address Current Branch Review do?

Read unresolved GitHub code review threads for the pull request associated with the current branch, classify each comment, and implement and verify required code fixes. Address Current Branch Review is an agent skill from epam/ai-dial-chat. Read unresolved GitHub code review threads for the pull request associated with the current branch, classify each comment, and implement and verify required code fixes.

When should I use Address Current Branch Review?

Address Current Branch Review fits situations like: explicitly asks to reply after the changes have been pushed and are visible in the PR; tasks that involve Pull requests.

How do I install Address Current Branch Review in Claude Code?

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

How do I install Address Current Branch Review in Codex?

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

Can I use Address Current Branch 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 epam/ai-dial-chat --skill address-current-branch-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-current-branch-review, .gemini/skills/address-current-branch-review, .github/skills/address-current-branch-review and .opencode/skills/address-current-branch-review in your project.

What does Address Current Branch Review need to run?

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

Does Address Current Branch Review access the network?

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

Is Address Current Branch 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 Current Branch Review use?

Address Current Branch 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 Current Branch Review use?

About 1.7k tokens (SKILL.md is roughly 6.8k 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 Current Branch Review?

Skills that share tags, products or a category with Address Current Branch Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Address Current Branch Review?

epam (a GitHub organization) maintains it in epam/ai-dial-chat, which has 504 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 10, 2026.

Source: epam/ai-dial-chat on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.