fetch-pr-comments
Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes. Use when the user asks to "fetch PR comments", "show PR comments", "check PR for unresolved comments", "list revi
Install
npx skills add https://github.com/tobihagemann/turbo/tree/main/codex/skills/fetch-pr-comments
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install tobihagemann-turbo@llmmart
git clone https://github.com/tobihagemann/turbo.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole tobihagemann/turbo collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Fetch PR Comments
Fetch unresolved review comments, top-level review body comments, and PR conversation comments from a GitHub PR and present them in a readable summary. This is a read-only skill -- it does not evaluate, fix, or reply to any comments.
Step 1: Fetch Comments
Auto-detect owner, repo, and PR number from current branch if not provided. Then run scripts/fetch-pr-data.sh, which handles full pagination (review threads, inner comment pages for long threads, reviews, issue comments) and emits a single merged JSON document:
bash <skill-dir>/scripts/fetch-pr-data.sh <owner> <repo> <pr_number>
Output shape:
{
"meta": { "title", "url", "headRefName", "baseRefName" },
"reviewThreads": [ { "id", "isResolved", "isOutdated", "comments": { "nodes": [ { "author", "body", "path", "line", "originalLine", "diffHunk" } ] } } ],
"reviews": [ { "author", "body", "state" } ],
"issueComments": [ { "author", "body", "createdAt", "url" } ]
}
Filter review threads to unresolved only. Filter reviews to those with a non-empty body, excluding PENDING state (unsubmitted drafts). Filter issue comments to those with a non-empty body.
Step 2: Present Results
Display a summary header followed by comments grouped by file.
Summary header:
- PR title and link
- Branch:
head->base - Total threads / unresolved threads
Top-level review comments (if any):
Show reviews with non-empty body before the file-grouped threads:
## Review Comments
### @reviewer (CHANGES_REQUESTED)
> Review body text here
### @another-reviewer (COMMENTED)
> Another review body here
Issue comments (if any):
Show PR conversation comments after review comments, ordered by createdAt:
## Issue Comments
### @commenter (2026-04-20)
> Issue comment body here
### @another-commenter (2026-04-21)
> Another issue comment body here
Inline threads grouped by file:
For each file with unresolved threads, show:
## `path/to/file.ts`
### Line 42 (by @reviewer)
```diff
<diffHunk from first comment>
```
> Comment body here
### Line 10 (by @another-reviewer) [outdated]
```diff
<diffHunk from first comment>
```
> First comment body
>
> **@reply-author:** Reply body
Formatting rules:
- Show top-level review body comments first, grouped under "Review Comments"
- Show PR conversation comments next, grouped under "Issue Comments", ordered by
createdAt - Then group threads by file path, in the order they appear
- Within each file, order threads by line number
- Show the
diffHunkfrom the first comment in each thread as a fenced diff code block before the comment body. This is the code context the reviewer was looking at. - For the line number, use
lineif available. Fall back tooriginalLinefor outdated comments wherelineis null. - Show all comments in a thread (the first is the original review comment; subsequent ones are replies)
- Mark outdated threads with
[outdated] - Use blockquotes for comment bodies
- For threads with multiple comments, show each comment with its author
- If there are zero unresolved threads, zero review body comments, and zero issue comments, say so and stop
Then call update_plan to mark this step completed and continue with the next step of the active workflow.
Rules
- If the user wants to fix or reply to comments, direct them to use
$resolve-pr-comments.
Files (turbo)
-
scripts
-
fetch-pr-data.sh 4.5 KB
#!/usr/bin/env bash # Fetch all review threads, reviews, issue comments, and metadata for a GitHub PR. # Emits a single merged JSON document on stdout: # { # "meta": { title, url, headRefName, baseRefName }, # "reviewThreads": [ ... ], # "reviews": [ ... ], # "issueComments": [ ... ] # PR conversation comments (non-review); author, body, createdAt, url # } # # Paginates reviewThreads, reviews, and issue comments to avoid silent drops on long # PRs. For any thread whose inner comments exceed the initial page, walks the # remaining comments via node(id:) and merges them back into the thread. # # Usage: fetch-pr-data.sh <owner> <repo> <pr_number> set -euo pipefail if [ "$#" -ne 3 ]; then echo "Usage: $0 <owner> <repo> <pr_number>" >&2 exit 2 fi owner="$1" repo="$2" pr="$3" meta_query=$(cat <<'GRAPHQL' query($owner: String!, $repo: String!, $pr: Int!) { repository(owner: $owner, name: $repo) { pullRequest(number: $pr) { title url headRefName baseRefName } } } GRAPHQL ) threads_query=$(cat <<'GRAPHQL' query($owner: String!, $repo: String!, $pr: Int!, $endCursor: String) { repository(owner: $owner, name: $repo) { pullRequest(number: $pr) { reviewThreads(first: 100, after: $endCursor) { pageInfo { hasNextPage endCursor } nodes { id isResolved isOutdated comments(first: 100) { pageInfo { hasNextPage endCursor } nodes { author { login } body path line originalLine diffHunk } } } } } } } GRAPHQL ) reviews_query=$(cat <<'GRAPHQL' query($owner: String!, $repo: String!, $pr: Int!, $endCursor: String) { repository(owner: $owner, name: $repo) { pullRequest(number: $pr) { reviews(first: 100, after: $endCursor) { pageInfo { hasNextPage endCursor } nodes { author { login } body state } } } } } GRAPHQL ) issue_comments_query=$(cat <<'GRAPHQL' query($owner: String!, $repo: String!, $pr: Int!, $endCursor: String) { repository(owner: $owner, name: $repo) { pullRequest(number: $pr) { comments(first: 100, after: $endCursor) { pageInfo { hasNextPage endCursor } nodes { author { login } body createdAt url } } } } } GRAPHQL ) thread_tail_query=$(cat <<'GRAPHQL' query($thread_id: ID!, $cursor: String!) { node(id: $thread_id) { ... on PullRequestReviewThread { comments(first: 100, after: $cursor) { pageInfo { hasNextPage endCursor } nodes { author { login } body path line originalLine diffHunk } } } } } GRAPHQL ) meta=$(gh api graphql \ -f query="$meta_query" \ -f owner="$owner" -f repo="$repo" -F pr="$pr" \ --jq '.data.repository.pullRequest') threads=$(gh api graphql --paginate \ -f query="$threads_query" \ -f owner="$owner" -f repo="$repo" -F pr="$pr" \ --jq '.data.repository.pullRequest.reviewThreads.nodes[]' \ | jq -s '.') threads=$(jq -c '.[]' <<<"$threads" | while IFS= read -r thread; do has_next=$(jq -r '.comments.pageInfo.hasNextPage' <<<"$thread") if [ "$has_next" != "true" ]; then printf '%s\n' "$thread" continue fi thread_id=$(jq -r '.id' <<<"$thread") cursor=$(jq -r '.comments.pageInfo.endCursor' <<<"$thread") nodes=$(jq '.comments.nodes' <<<"$thread") while [ "$has_next" = "true" ]; do page=$(gh api graphql \ -f query="$thread_tail_query" \ -f thread_id="$thread_id" -f cursor="$cursor" \ --jq '.data.node.comments') page_nodes=$(jq '.nodes' <<<"$page") nodes=$(jq -n --argjson a "$nodes" --argjson b "$page_nodes" '$a + $b') has_next=$(jq -r '.pageInfo.hasNextPage' <<<"$page") cursor=$(jq -r '.pageInfo.endCursor // ""' <<<"$page") done jq --argjson nodes "$nodes" ' .comments.nodes = $nodes | .comments.pageInfo.hasNextPage = false | .comments.pageInfo.endCursor = null ' <<<"$thread" done | jq -s '.') reviews=$(gh api graphql --paginate \ -f query="$reviews_query" \ -f owner="$owner" -f repo="$repo" -F pr="$pr" \ --jq '.data.repository.pullRequest.reviews.nodes[]' \ | jq -s '.') issue_comments=$(gh api graphql --paginate \ -f query="$issue_comments_query" \ -f owner="$owner" -f repo="$repo" -F pr="$pr" \ --jq '.data.repository.pullRequest.comments.nodes[]' \ | jq -s '.') jq -n \ --argjson meta "$meta" \ --argjson threads "$threads" \ --argjson reviews "$reviews" \ --argjson issueComments "$issue_comments" \ '{meta: $meta, reviewThreads: $threads, reviews: $reviews, issueComments: $issueComments}'
-
-
SKILL.md 3.8 KB
--- name: fetch-pr-comments description: "Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes. Use when the user asks to \"fetch PR comments\", \"show PR comments\", \"check PR for unresolved comments\", \"list review comments\", \"what comments are on the PR\", \"show unresolved threads\", or \"summarize PR feedback\"." --- # Fetch PR Comments Fetch unresolved review comments, top-level review body comments, and PR conversation comments from a GitHub PR and present them in a readable summary. This is a read-only skill -- it does not evaluate, fix, or reply to any comments. ## Step 1: Fetch Comments Auto-detect owner, repo, and PR number from current branch if not provided. Then run `scripts/fetch-pr-data.sh`, which handles full pagination (review threads, inner comment pages for long threads, reviews, issue comments) and emits a single merged JSON document: ```bash bash <skill-dir>/scripts/fetch-pr-data.sh <owner> <repo> <pr_number> ``` Output shape: ```jsonc { "meta": { "title", "url", "headRefName", "baseRefName" }, "reviewThreads": [ { "id", "isResolved", "isOutdated", "comments": { "nodes": [ { "author", "body", "path", "line", "originalLine", "diffHunk" } ] } } ], "reviews": [ { "author", "body", "state" } ], "issueComments": [ { "author", "body", "createdAt", "url" } ] } ``` Filter review threads to unresolved only. Filter reviews to those with a non-empty body, excluding `PENDING` state (unsubmitted drafts). Filter issue comments to those with a non-empty body. ## Step 2: Present Results Display a summary header followed by comments grouped by file. **Summary header:** - PR title and link - Branch: `head` -> `base` - Total threads / unresolved threads **Top-level review comments (if any):** Show reviews with non-empty body before the file-grouped threads: ``` ## Review Comments ### @reviewer (CHANGES_REQUESTED) > Review body text here ### @another-reviewer (COMMENTED) > Another review body here ``` **Issue comments (if any):** Show PR conversation comments after review comments, ordered by `createdAt`: ``` ## Issue Comments ### @commenter (2026-04-20) > Issue comment body here ### @another-commenter (2026-04-21) > Another issue comment body here ``` **Inline threads grouped by file:** For each file with unresolved threads, show: ```` ## `path/to/file.ts` ### Line 42 (by @reviewer) ```diff <diffHunk from first comment> ``` > Comment body here ### Line 10 (by @another-reviewer) [outdated] ```diff <diffHunk from first comment> ``` > First comment body > > **@reply-author:** Reply body ```` **Formatting rules:** - Show top-level review body comments first, grouped under "Review Comments" - Show PR conversation comments next, grouped under "Issue Comments", ordered by `createdAt` - Then group threads by file path, in the order they appear - Within each file, order threads by line number - Show the `diffHunk` from the first comment in each thread as a fenced diff code block before the comment body. This is the code context the reviewer was looking at. - For the line number, use `line` if available. Fall back to `originalLine` for outdated comments where `line` is null. - Show all comments in a thread (the first is the original review comment; subsequent ones are replies) - Mark outdated threads with `[outdated]` - Use blockquotes for comment bodies - For threads with multiple comments, show each comment with its author - If there are zero unresolved threads, zero review body comments, and zero issue comments, say so and stop Then call `update_plan` to mark this step completed and continue with the next step of the active workflow. ## Rules - If the user wants to fix or reply to comments, direct them to use `$resolve-pr-comments`.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.