sentry-pr-code-review

von sentry

Überprüfe die PRs eines Projekts auf Probleme, die durch die Seer Bug Prediction in der Code-Review erkannt wurden. Verwende dies, wenn du gebeten wirst, von Sentry in PRs identifizierte Probleme zu überprüfen oder zu beheben…

npx skills add https://github.com/getsentry/sentry-agent-skills --skill sentry-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

Mehr Skills von sentry

architecture-review
sentry
Codebase-Gesundheitsprüfung auf Mitarbeiterebene. Erkennt monolithische Module, stille Fehler, Typsicherheitslücken, Testabdeckungslücken und LLM-Freundlichkeitsprobleme.
pi-agent-integration
sentry
Integrate `@mariozechner/pi-agent-core` as the agent abstraction inside another library or runtime. Use when implementing or refactoring Pi Agent wrappers,…
sentry-debug-issue
sentry
Debuggen und Beheben eines Sentry-Problems – finden Sie es (per Link, ID oder Suche), rufen Sie den vollständigen Kontext ab (Stack-Trace, Breadcrumbs, Trace, Logs), optional Seer-Root-Cause-Analyse ausführen /…
sentry-svelte-sdk
sentry
Vollständige Sentry-SDK-Einrichtung für Svelte und SvelteKit. Verwenden, wenn aufgefordert, "Sentry zu Svelte hinzuzufügen", "Sentry zu SvelteKit hinzuzufügen", "@sentry/sveltekit zu installieren" oder zu konfigurieren…
sentry-svelte-sdk
sentry
Vollständige Sentry-SDK-Einrichtung für Svelte und SvelteKit. Verwenden, wenn aufgefordert wird, "Sentry zu Svelte hinzuzufügen", "Sentry zu SvelteKit hinzuzufügen", "@sentry/sveltekit zu installieren" oder zu konfigurieren…
skill-scanner
sentry
Agent-Fähigkeiten auf Sicherheitsprobleme scannen. Verwenden, wenn aufgefordert, "eine Fähigkeit zu scannen".
prompt-optimizer
sentry
Erstellt, optimiert und verfeinert iterativ Agent-Prompts, System-Prompts, Entwickler-Prompts und wiederverwendbare Prompt-Vorlagen. Verwenden, wenn aufgefordert, eine… zu verbessern.
commit
sentry
commit — eine installierbare Fähigkeit für KI-Agenten, veröffentlicht von getsentry/sentry-docs.