Stats

Actions

Tags

Help us improve

Share bugs, ideas, or general feedback.

GitHub PR Comment Replier | github-devflow

Skill

GitHub PR Comment Replier

From github-devflow

This skill should be used when the user asks to "reply to PR comments", "respond to review comments", "reply to PR

$

npx claudepluginhub hhiroshell/gh-devflow-plugins --plugin github-devflow

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/github-devflow:reply

User invocable

Model invocable

Inline context

Default effort

Tool Access

This skill is limited to the following tools:

BashReadGrepGlob

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

Reply to comments on a GitHub pull request by finding threads that need responses, generating thoughtful replies based on codebase context, and posting them directly.

SKILL.md

159 lines · ~1.3k tokens

Similar Skills

pr-respond

15

Processes PR review feedback by analyzing comments, implementing fixes, committing, pushing, replying on GitHub, and resolving threads. Triggered by /pr-respond or relevant queries.

pr-comments-address

15

Reads open GitHub PR review comments, triages by severity, applies code fixes, and drafts replies. Use when addressing PR feedback or code review.

7 tools

ravn-ai-toolkit

pr-comment-workflow

691

Guides GitHub PR comment workflows: drafts responses, creates pending reviews via gh CLI, resolves feedback by fixing code or replying per strict style rules.

Stats

LanguageShell

Parent stars0

MaintenanceExcellent

Last CommitFeb 19, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

GitHub PR Comment Replier

Reply to comments on a GitHub pull request by finding threads that need responses, generating thoughtful replies based on codebase context, and posting them directly.

Filter criteria for actionable threads:

Thread is not resolved
Latest comment was not generated by this skill (detected by "github-devflow:reply" signature)

Helper Scripts

This skill uses shared helper scripts in scripts/ at the plugin root:

Script	Purpose
`fetch-review-threads.sh`	Fetch review threads from a PR with optional filtering
`post-reply.sh`	Post a reply to a review thread

Workflow

Step 1: Fetch Actionable Threads

Use the helper script to fetch review threads that need replies:

PR_NUMBER=$ARGUMENTS
bash ${CLAUDE_PLUGIN_ROOT}/scripts/fetch-review-threads.sh $PR_NUMBER --filter-resolved --filter-skill reply

This returns JSON with:

owner, repo, prNumber: Repository context
threads: Array of threads requiring action
totalCount: Number of actionable threads

Each thread contains:

id: Thread ID for posting replies (e.g., PRRT_xxx)
isResolved: Always false (filtered)
path: File path in the repository
line: Line number in the file
comments.nodes: Array of all comments in the thread (latest comment is last)

If no actionable threads are found (totalCount: 0), report that no replies are needed.

Step 2: Analyze and Generate Replies

For each actionable thread:

Read all comments: Parse the entire comments.nodes array to understand the full conversation context
Examine the code context: Read the file at path around line
Analyze the codebase: Use Grep and Glob to understand related code and patterns
Generate a thoughtful reply: Address the reviewer's concern with specifics

When generating replies:

Be concise but thorough
Reference specific code when relevant
Acknowledge valid points
Suggest changes or improvements (but do NOT modify any files)
If suggesting a fix, explain what should be changed and why

Step 3: Post Replies

Post each reply using the helper script:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/post-reply.sh --skill reply "<thread-id>" "<reply-body>"

Or for longer replies, write to a file first:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/post-reply.sh --skill reply --file "<thread-id>" /tmp/reply.md

The script returns JSON with:

success: Boolean indicating success
comment.id: The created comment's ID
comment.url: URL to the comment

Step 4: Report Summary

After processing all threads, provide a summary:

Number of threads processed
Number of replies posted
Any errors encountered

Important Guidelines

No Code Changes

This skill must NOT modify any files. Only suggest changes in replies:

Do NOT use Write or Edit tools
Do NOT create or modify any files
Only read files for context and analysis
Suggest code changes in the reply text, not by editing files

Reply Quality

Address the specific concern raised in the comment
Provide context from the codebase when relevant
Be professional and collaborative
Keep replies focused and actionable

Codebase Analysis

Read the file mentioned in the thread's path field
Look at surrounding code for context
Check for related patterns elsewhere in the codebase
Consider the reviewer's perspective

Error Handling

If gh CLI is not authenticated, inform the user to run gh auth login
If the PR number is invalid, report the error clearly
If no actionable threads are found, report that no replies are needed
If posting a reply fails, report the error and continue with remaining threads

Script Reference

fetch-review-threads.sh

Usage: fetch-review-threads.sh <pr-number> [--filter-resolved] [--filter-skill <name>]

Options:
  --filter-resolved    Filter out resolved threads
  --filter-skill <name>  Filter out threads where the latest
                         comment contains the specified skill's signature
                         (github-devflow:<name>)

Output: JSON with repository info and thread array

post-reply.sh

Usage: post-reply.sh [--skill <name>] <thread-id> <body>
       post-reply.sh [--skill <name>] --file <thread-id> <body-file>

Options:
  --skill <name>  Include skill identifier in signature
                  (e.g., --skill reply → "github-devflow:reply")

Arguments:
  thread-id   The GraphQL ID of the review thread (e.g., PRRT_xxx)
  body        The reply message text
  body-file   Path to a file containing the reply message

Note: Automatically appends a "Claude Code" signature to identify
      AI-generated replies for filtering in subsequent runs.

Output: JSON with success status and comment details