/pr-comments
Fetch, reply to, and resolve review threads on a GitHub pull request. Use when checking what review feedback needs addressing, whether threads are resolved, replying to review comments, or clearing AI-reviewer threads after acting on them.
$ npx -y skills add bendrucker/claude --skill pr-comments --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/pr-comments
Context preview
The summary Claude sees to decide when to auto-load this skill.
Fetch, reply to, and resolve review threads on a GitHub pull request. Use when checking what review feedback needs addressing, whether threads are resolved, replying to review comments, or clearing AI-reviewer threads after acting on them.
SKILL.md
pr-comments.SKILL.mdname: github:pr-comments
description: Fetch, reply to, and resolve review threads on a GitHub pull request. Use when checking what review feedback needs addressing, whether threads are resolved, replying to review comments, or clearing AI-reviewer threads after acting on them.
argument-hint: "<pr-url> [--role author|reviewer] [--bots] [--include-resolved]"
allowed-tools:
["Bash(bun ${CLAUDE_PLUGIN_ROOT}/scripts/pr-comments.ts:*)", "Bash(bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts:*)"]PR Review Comments
Fetch review threads from a GitHub pull request. Resolved threads are excluded by default. Outdated threads are included but marked.
Usage
bun ${CLAUDE_PLUGIN_ROOT}/scripts/pr-comments.ts <pr-url> [--role author|reviewer] [--since last-review|<date>] [--bots] [--include-resolved]- `--role`: `author` fetches all unresolved threads, the feedback that needs addressing. `reviewer` fetches only unresolved threads started by the authenticated user, to check whether comments have been resolved. Defaults by whether the authenticated user is the PR author.
- `--since last-review`: threads with activity since the last relevant review. As author: the most recent review by a human other than you (bot reviews excluded). As reviewer: your most recent submitted review. An ISO date (e.g. `2025-01-15`) sets an explicit cutoff.
- `--bots`: only review-bot threads: accounts the API types as `Bot` (Copilot, CodeRabbit, Greptile) plus logins in `$CLAUDE_PLUGIN_DATA/reviewers.txt`. Use this filter to detect bots rather than hardcoding logins.
- `--include-resolved`: include resolved threads, tagged `(resolved)`, for follow-up-style flows that must surface silently resolved threads.
Output is compact markdown grouped by file with line numbers and full comment bodies. Each thread prints its node `id`, used to reply and resolve.
Replying and Resolving
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts reply <thread-id> --body "..."
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts reply <thread-id> --resolve --body "..."
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts resolve <thread-id>Pass the reply text with `--body`, `--bodyFile <path>`, or stdin. Don't resolve without a reply: a silent resolve hides why the thread closed. Prefer `reply --resolve` so the resolve carries context.
Reactions
React with a thumbs up where you would otherwise write a low-value acknowledgment reply (test coverage, a rename, an obvious guard). Stay silent where you would have stayed silent.
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts react <thread-id> --resolve
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts react <thread-id> --down --resolveThe reaction lands on the thread's first comment. Thumbs down (`--down`) is feedback to a bot reviewer whose comment was wrong or unhelpful. Never thumbs down a human, and never in an autonomous run.
Bot Reviewer Threads
On threads the `--bots` filter catches, don't converse with the bot. Push the fix and resolve the thread, or acknowledge with a thumbs up. If a reply is genuinely needed, state the resolution as a terse note for a future human reader ("Guarded with a null check"), not a message to the bot.
Read more
name: github:pr-comments
description: Fetch, reply to, and resolve review threads on a GitHub pull request. Use when checking what review feedback needs addressing, whether threads are resolved, replying to review comments, or clearing AI-reviewer threads after acting on them.
argument-hint: "<pr-url> [--role author|reviewer] [--bots] [--include-resolved]"
allowed-tools:
["Bash(bun ${CLAUDE_PLUGIN_ROOT}/scripts/pr-comments.ts:*)", "Bash(bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts:*)"]PR Review Comments
Fetch review threads from a GitHub pull request. Resolved threads are excluded by default. Outdated threads are included but marked.
Usage
bun ${CLAUDE_PLUGIN_ROOT}/scripts/pr-comments.ts <pr-url> [--role author|reviewer] [--since last-review|<date>] [--bots] [--include-resolved]- `--role`: `author` fetches all unresolved threads, the feedback that needs addressing. `reviewer` fetches only unresolved threads started by the authenticated user, to check whether comments have been resolved. Defaults by whether the authenticated user is the PR author.
- `--since last-review`: threads with activity since the last relevant review. As author: the most recent review by a human other than you (bot reviews excluded). As reviewer: your most recent submitted review. An ISO date (e.g. `2025-01-15`) sets an explicit cutoff.
- `--bots`: only review-bot threads: accounts the API types as `Bot` (Copilot, CodeRabbit, Greptile) plus logins in `$CLAUDE_PLUGIN_DATA/reviewers.txt`. Use this filter to detect bots rather than hardcoding logins.
- `--include-resolved`: include resolved threads, tagged `(resolved)`, for follow-up-style flows that must surface silently resolved threads.
Output is compact markdown grouped by file with line numbers and full comment bodies. Each thread prints its node `id`, used to reply and resolve.
Replying and Resolving
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts reply <thread-id> --body "..."
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts reply <thread-id> --resolve --body "..."
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts resolve <thread-id>Pass the reply text with `--body`, `--bodyFile <path>`, or stdin. Don't resolve without a reply: a silent resolve hides why the thread closed. Prefer `reply --resolve` so the resolve carries context.
Reactions
React with a thumbs up where you would otherwise write a low-value acknowledgment reply (test coverage, a rename, an obvious guard). Stay silent where you would have stayed silent.
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts react <thread-id> --resolve
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts react <thread-id> --down --resolveThe reaction lands on the thread's first comment. Thumbs down (`--down`) is feedback to a bot reviewer whose comment was wrong or unhelpful. Never thumbs down a human, and never in an autonomous run.
Bot Reviewer Threads
On threads the `--bots` filter catches, don't converse with the bot. Push the fix and resolve the thread, or acknowledge with a thumbs up. If a reply is genuinely needed, state the resolution as a terse note for a future human reader ("Guarded with a null check"), not a message to the bot.
My personal plugin marketplace for Claude Code, Anthropic's AI coding assistant.
Repo: bendrucker/claude
Other skills on bendrucker-claude.
- /agent-ideas
Harvest agent-tooling ideas from prominent developers.
Open skill - /cleye
Type-safe CLI argument parsing with cleye, the standard parser for this repo's Bun scripts. Use when writing or editing any script that takes arguments (flags, positional parameters, subcommands, --help) instead of reading existing scripts for the pattern.
Open skill - /coverage
Measure Bun test coverage and close gaps on a specific file. Use when adding or editing tests, when asked about coverage, or when the PostToolUse coverage hook reports uncovered lines.
Open skill - /activity
Report real device usage from ActivityWatch. Covers per-app time, window titles, and active vs idle spans. Use when asked "what apps did I use", "how long was I in X", "what did I work on today", "how much was I active vs idle", or to mine usage patterns for automation.
Open skill - /history
Report shell history from atuin's local capture. Covers what commands ran, when, where, and how they exited. Use when asked "what commands did I run", "what was I working on in the terminal", "have I ever run X", "how do I usually invoke X", or about recent shell activity,
Open skill - /bun
Bun runtime patterns. Use when running bun commands, working with package.json/bun.lock, writing TypeScript scripts under Bun, or developing Claude Code plugins.
Open skill

