Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find PRs I need to review", "show my review requests", "what needs my review", "fetch GitHub review requests", or "check team review queue".
.claude/skills/gh-review-requests/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-06 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
Fetch unread review_requested notifications for open (unmerged) PRs, filtered by a GitHub team.
Requires: GitHub CLI (gh) authenticated.
If the user has not specified a team, ask:
> Which GitHub team should I filter by? (e.g. streaming-platform)
Accept either a team slug (streaming-platform) or a display name ("Streaming Platform") — convert to lowercase-hyphenated slug before passing to the script.
bashuv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_review_requests.py --org getsentry --teams <team-slug>
To filter by multiple teams, pass a comma-separated list:
bashuv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_review_requests.py --org getsentry --teams <team slugs>
json{ "total": 3, "prs": [ { "notification_id": "12345", "title": "feat(kafka): add workflow to restart a broker", "url": "https://github.com/getsentry/ops/pull/19144", "repo": "getsentry/ops", "pr_number": 19144, "author": "bmckerry", "reasons": ["opened by: bmckerry"] } ] }
reasons will contain one or both of:
"review requested from: <Team Name>" — the team is a requested reviewer"opened by: <login>" — the PR author is a team memberDisplay results as a markdown table with full URLs:
| # | Title | URL | Reason | |---|-------|-----|--------| | 1 | feat(kafka): add workflow to restart a broker | https://github.com/getsentry/ops/pull/19144 | opened by: evanh |
If total is 0, say: "No unread review requests found for that team."
If the script fails, run manually:
bashgh api notifications --paginate
Then for each review_requested notification, check:
gh api repos/{repo}/pulls/{number} — skip if state == "closed" or merged_at is setgh api repos/{repo}/pulls/{number}/requested_reviewers — check teams[].namegh api orgs/{org}/teams/{slug}/members — check if author is a member| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 15 counted toward the lift figure. The other 8 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +26 percentage points is the difference between those two pass rates over the 15 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.