mcpField
S
sentry-pr-code-review

sentry-pr-code-review

github.com/getsentryTesting & quality2722.3k installsUpdated today
Repository

About sentry-pr-code-review

A workflow skill for reviewing and fixing issues raised by Seer by Sentry in GitHub pull request comments. It uses the gh CLI to find comments, assess findings against the current code, apply fixes, and report resolved or skipped items.

Key features

  1. 01Fetches Seer comments with gh CLI
  2. 02Finds open PRs with Seer findings
  3. 03Parses issue details and suggested fixes
  4. 04Verifies findings against current code
  5. 05Summarizes resolved and skipped issues

Use cases

  1. 01Reviewing Seer feedback on a pull request
  2. 02Finding open PRs with unresolved Seer comments
  3. 03Checking and fixing reported code issues

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/getsentry/sentry-for-ai --skill sentry-pr-code-review

After installing, type/sentry-pr-code-reviewin Claude Code to confirm it loaded.

Details

From the project README

All Skills > Workflow > PR Code Review

Sentry Code Review

Review and fix issues identified by Seer (by Sentry) in GitHub PR comments.

Invoke This Skill When

  • User asks to "review Sentry comments" or "fix Sentry issues" on a PR
  • User shares a PR URL/number and mentions Sentry or Seer feedback
  • User asks to "address Sentry review" or "resolve Sentry findings"
  • User wants to find PRs with unresolved Sentry comments

Prerequisites

  • gh CLI installed and authenticated
  • Repository has the Seer by Sentry GitHub App installed

Important: The comment format parsed below is based on Seer's current output. This is not an API contract and may change. Always verify the actual comment structure.

Phase 1: Fetch Seer Comments

gh api repos/{owner}/{repo}/pulls/{PR_NUMBER}/comments --paginate \
  --jq '.[] | select(.user.login == "seer-by-sentry[bot]") | {file: .path, line: .line, body: .body}'

The bot login is seer-by-sentry[bot] — not sentry[bot] or sentry-io[bot].

If no PR number is given, find recent PRs with Seer comments:

gh pr list --state open --json number,title --limit 20 | \
  jq -r '.[].number' | while read pr; do
    count=$(gh api "repos/{owner}/{repo}/pulls/$pr/comments" --paginate \
      --jq '[.[] | select(.user.login == "seer-by-sentry[bot]")] | length')
    [ "$count" -gt 0 ] && echo "PR #$pr: $count Seer comments"
  done

Phase 2: Parse Each Comment

Extract from the markdown body:

  • Bug description: Line starting with **Bug:**
  • Severity/Confidence: In <sub>Severity: X | Confidence: X.XX</sub>
  • Analysis: Inside <summary>🔍 <b>Detailed Analysis</b></summary> block
  • Suggested Fix: Inside <summary>💡 <b>Suggested Fix</b></summary> block
  • AI Prompt: Inside <summary>🤖 <b>Prompt for AI Agent</b></summary> block

Phase 3: Verify & Fix

For each issue:

  1. Read the file at the specified line
  2. Confirm issue still exists in current code (not already fixed in a later commit)
  3. Review surrounding code to assess if it's an actual issue or false positive
  4. Implement fix (use suggested fix as starting point, or write your own)
  5. Consider edge cases and regression risk

Phase 4: Summarize and Report Results

## Seer Review: PR #[number]

### Resolved
| File:Line | Issue | Severity | Fix Applied |
|-----------|-------|----------|-------------|
| path:123  | desc  | HIGH     | what done   |

### Skipped (false positive or already fixed)
| File:Line | Issue | Reason |
|-----------|-------|--------|

**Summary:** X resolved, Y skipped

Seer Review Triggers

TriggerWhen
PR set to "Ready for Review"Automatic error prediction
Commit pushed while PR is readyRe-runs prediction
@sentry review commentManual trigger for full review + suggestions
Draft PRSkipped — no review until marked ready

Troubleshooting

IssueSolution
No Seer comments foundVerify the Seer GitHub App is installed on the repo
Bot name mismatchThe login is seer-by-sentry[bot], not sentry[bot]
Comments not appearing on new PRsPR must be "Ready for Review" (not draft)
gh api returns partial resultsEnsure --paginate flag is included

Common Issue Types

CategoryExamples
Type SafetyMissing null checks, unsafe type assertions
Error HandlingSwallowed errors, missing boundaries
ValidationPermissive inputs, missing sanitization
ConfigMissing env vars, incorrect paths

Comments

Markdown supported