Gh Address Comments logo

Gh Address Comments

Community
jmagar
gh-address-comments

This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches comments via gh CLI, creates task checklists, links commits to review threads, and blocks completion if unresolved threads remain.

Overview

Publisherjmagar
Repositoryclaude-homelab
Skill namegh-address-comments
Stars
87
Forks
11
Bundled files
12
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jmagar on GitHub. Read the source before you install it.

Installation

Install the Gh Address Comments AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jmagar/claude-homelab/tree/main/skills/gh-address-comments
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jmagar/claude-homelab.git /tmp/claude-homelab
mkdir -p .claude/skills
cp -r /tmp/claude-homelab/skills/gh-address-comments .claude/skills/gh-address-comments
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gh Address Comments in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gh Address Comments on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gh Address Comments is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PR Comment Handler with Resolution Tracking

⚠️ MANDATORY SKILL INVOCATION ⚠️

YOU MUST invoke this skill (NOT optional) when the user mentions ANY of these triggers:

  • "address PR comments", "fix review feedback", "handle PR review"
  • "resolve PR threads", "respond to review", "work through comments"
  • "address the feedback", "mark threads resolved", "clear review comments"
  • Any mention of systematically handling GitHub pull request review comments

Failure to invoke this skill when triggers occur violates your operational requirements.

Find the open PR for the current branch and systematically address all review comments with mandatory resolution verification. This workflow ensures no feedback slips through the cracks by tracking threads as tasks, linking commits to specific reviews, and blocking completion if any threads remain unresolved. Run all gh commands with elevated network access.

Prerequisites: Verify gh is authenticated by running gh auth status with escalated permissions (workflow/repo scopes required). If not authenticated, run gh auth login --scopes repo,workflow. If sandboxing blocks gh auth status, rerun with sandbox_permissions=require_escalated.

Workflow

1) Fetch all PR comments

Run python3 $HOME/.claude/skills/gh-address-comments/scripts/fetch_comments.py to fetch all comments and review threads on the PR. Store output for later verification.

Example:

bash
python3 $HOME/.claude/skills/gh-address-comments/scripts/fetch_comments.py > /tmp/pr_comments.json

2) Create tracking checklist

Parse the fetched comments and create a task checklist using TaskCreate for each review thread. Each task should:

  • Include the thread number, file path, line number, and comment summary
  • Have status pending initially
  • Store the thread ID in task metadata for later resolution

Task format:

  • Subject: Address comment #N: [file]:[line]
  • Description: Comment author, body preview, and what needs to be done
  • Metadata: {"thread_id": "PRRT_kwDOABC...", "file": "path/to/file.ts", "line": 42}

3) Ask user which comments to address

Present all numbered review threads with summaries. Ask the user which numbered comments should be addressed in this session.

Display format:

Review Threads:
  1. src/api/users.ts:45 (@reviewer): Add input validation for email field...
     Thread ID: PRRT_kwDOABCDEF1234567
     Status: Unresolved

  2. src/utils/auth.ts:128 (@reviewer): Extract this logic into a helper function...
     Thread ID: PRRT_kwDOABCDEF7654321
     Status: Unresolved

4) Apply fixes with commit linking

For each selected comment:

  1. Update task status to in_progress using TaskUpdate
  2. Apply code changes using standard tools (Edit, Write)
  3. Commit with message that references the comment number and thread ID:
    fix: address PR comment #1 - add email validation
    
    Resolves review thread PRRT_kwDOABCDEF1234567
    - Added Zod schema validation for email field
    - Added error handling for invalid formats
    
    Co-authored-by: @reviewer
  4. Update task status to completed using TaskUpdate

Commit message format:

  • First line: fix: address PR comment #N - [brief description]
  • Blank line
  • Resolves review thread [THREAD_ID]
  • Bullet points explaining the changes
  • Co-authored-by: @reviewer if substantial changes based on feedback

5) Mark threads as resolved

After committing fixes, mark the corresponding review threads as resolved using:

bash
python3 $HOME/.claude/skills/gh-address-comments/scripts/mark_resolved.py <thread_id_1> [thread_id_2] ...

Example:

bash
python3 $HOME/.claude/skills/gh-address-comments/scripts/mark_resolved.py \
  PRRT_kwDOABCDEF1234567 \
  PRRT_kwDOABCDEF7654321

6) Verify complete resolution (MANDATORY - BLOCKS IF SKIPPED)

Before declaring the PR review complete, verify all threads are addressed:

bash
python3 $HOME/.claude/skills/gh-address-comments/scripts/fetch_comments.py | \
  python3 $HOME/.claude/skills/gh-address-comments/scripts/verify_resolution.py

Exit behavior:

  • Exit 0: All threads resolved/outdated → safe to proceed
  • Exit 1: Unresolved threads found → BLOCKED until addressed

IMPORTANT: Do NOT skip this verification step. If unresolved threads are found:

  1. Ask user to explicitly acknowledge which threads to defer
  2. Create follow-up tasks for deferred threads
  3. Only proceed after user confirms understanding of what remains unresolved

Error Handling

Authentication issues: If gh hits auth/rate issues mid-run, prompt the user to re-authenticate with gh auth login, then retry.

Thread resolution failures: If mark_resolved.py fails for specific threads:

  1. Check the thread ID is correct (from fetch_comments.py output)
  2. Verify you have write permissions on the PR
  3. Ensure the thread still exists (not deleted by reviewer)

Verification failures: If verify_resolution.py reports unresolved threads:

  1. Review the listed thread IDs
  2. Either address remaining threads OR get explicit user approval to defer
  3. Document deferred threads in follow-up tasks

Notes

  • Review threads marked as "outdated" (code changed since comment) are considered addressed
  • Conversation comments (non-threaded) don't block completion but should be acknowledged
  • Always link commits to thread IDs for traceability
  • Use TaskList to track overall progress across all review threads

Additional Resources

For detailed information, see:

  • Resolution workflow deep dive: references/resolution-workflow.md
  • Command cheatsheet: references/quick-reference.md
  • GitHub API details: references/api-endpoints.md
  • Common issues: references/troubleshooting.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gh Address Comments AI skill do?

This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches comments via gh CLI, creates task checklists, links commits to review threads, and blocks completion if unresolved threads remain.

Why use Gh Address Comments on TypingMind?

Because you install it once and use it with any model. Gh Address Comments is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gh Address Comments in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jmagar/claude-homelab/tree/main/skills/gh-address-comments. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gh Address Comments?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gh Address Comments?

As many as you like. As long as a model supports skills, you can use Gh Address Comments with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gh Address Comments AI skill free?

Yes. It is published on GitHub by jmagar under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇