Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query GitHub pull requests with jq filtering and reusable selectors.
.claude/skills/github-github-pr-query/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 148% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 27% | 0% |
Query GitHub pull requests efficiently with built-in jq filtering.
The --jq parameter is optional. Without --jq, this skill returns schema and data size information instead of full data. Use this to avoid oversized responses and inspect structure before targeted queries.
Use --jq '.' to get all data, or use a more specific filter for targeted results.
Use this skill to query pull requests from the current repository or any specified repository.
To list pull requests from the current repository:
bash./query-prs.sh # Returns schema and data size, not full data
To get all PR data:
bash./query-prs.sh --jq '.'
To query a specific repository:
bash./query-prs.sh --repo owner/repo
Use the --jq argument to filter and transform the output:
bash# Get only open PRs ./query-prs.sh --jq '.[] | select(.state == "open")' # Get PR numbers and titles ./query-prs.sh --jq '.[] | {number, title}' # Get PRs by a specific author ./query-prs.sh --jq '.[] | select(.author.login == "username")' # Get merged PRs from last week ./query-prs.sh --jq '.[] | select(.mergedAt != null)' # Count PRs by state ./query-prs.sh --jq 'group_by(.state) | map({state: .[0].state, count: length})'
--state: Filter by state (open, closed, merged, all). Default: open--limit: Maximum number of PRs to fetch. Default: 30--repo: Repository in owner/repo format. Default: current repo--author: Filter PRs by author login--app: Filter PRs by GitHub App author--search: Apply GitHub issue/PR search syntax--jq: (Optional) jq expression for filtering/transforming output. If omitted, returns schema infoFind large PRs (many changed files):
bash./query-prs.sh --jq '.[] | select(.changedFiles > 10) | {number, title, changedFiles}'
Get PRs awaiting review:
bash./query-prs.sh --jq '.[] | select(.reviewDecision == "REVIEW_REQUIRED") | {number, title, author: .author.login}'
Get PRs authored by GitHub Actions app activity context:
bash./query-prs.sh --app github-actions --jq '.[] | {number, title, author: .author.login}'
Find in-scope review feedback (team/collaborator + trusted automation):
bash# Trusted automation is matched by login; humans are matched by association. ./query-prs.sh --jq \ '.[] | {number, title, reviews: [.reviews[]? | select(.author.login == "github-actions[bot]" or .author.login == "app/github-copilot" or .authorAssociation == "MEMBER" or .authorAssociation == "OWNER" or .authorAssociation == "COLLABORATOR")] }'
Ignore external review feedback:
bash./query-prs.sh --jq \ '.[] | {number, title, external_reviews: [.reviews[]? | select(.authorAssociation == "CONTRIBUTOR" or .authorAssociation == "FIRST_TIME_CONTRIBUTOR" or .authorAssociation == "FIRST_TIMER" or .authorAssociation == "NONE")] }'
List PRs with their labels:
bash./query-prs.sh --jq '.[] | {number, title, labels: [.labels[].name]}'
The script outputs JSON by default, making it easy to pipe through jq for additional processing.
gh) authenticatedjq for filtering (installed by default on most systems)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | fail→fail | 8,814 | 6,856 | -22% | 1 | 1 | 0% | 1,491 | 1,341 | -10% | 0 | 0 | — |
case-01 | fail→fail | 14,561 | 2,880 | -80% | 1 | 1 | 0% | 2,455 | 1,190 | -52% | 0 | 0 | — |
case-02 | fail→pass | 5,811 | 8,048 | +38% | 1 | 1 | 0% | 951 | 2,360 | +148% | 0 | 0 | — |
case-03 | fail→fail | 8,455 | 8,830 | +4% | 1 | 1 | 0% | 990 | 1,413 | +43% | 0 | 0 | — |
case-04 | fail→pass | 14,013 | 5,286 | -62% | 1 | 1 | 0% | 2,759 | 1,758 | -36% | 0 | 0 | — |
case-05 | fail→pass | 9,051 | 4,350 | -52% | 1 | 1 | 0% | 1,510 | 1,659 | +10% | 0 | 0 | — |
case-06 | fail→pass | 7,768 | 3,839 | -51% | 1 | 1 | 0% | 1,335 | 1,421 | +6% | 0 | 0 | — |
case-07 | fail→pass | 12,460 | 11,594 | -7% | 1 | 1 | 0% | 2,225 | 2,821 | +27% | 0 | 0 | — |
case-08 | fail→fail | 6,723 | 8,470 | +26% | 1 | 1 | 0% | 122 | 1,265 | +937% | 0 | 0 | — |
case-09 | fail→fail | 7,691 | 8,031 | +4% | 1 | 1 | 0% | 1,249 | 1,268 | +2% | 0 | 0 | — |
case-11 | fail→pass | 11,628 | 5,095 | -56% | 1 | 1 | 0% | 2,398 | 1,827 | -24% | 0 | 0 | — |
case-12 | fail→pass | 12,150 | 10,760 | -11% | 1 | 1 | 0% | 2,376 | 2,197 | -8% | 0 | 0 | — |
case-13 | fail→pass | 2,316 | 4,036 | +74% | 1 | 1 | 0% | 414 | 1,364 | +229% | 0 | 0 | — |
case-14 | fail→fail | 8,343 | 6,807 | -18% | 1 | 1 | 0% | 1,581 | 1,146 | -28% | 0 | 0 | — |
case-15 | fail→pass | 8,662 | 3,715 | -57% | 1 | 1 | 0% | 1,366 | 1,470 | +8% | 0 | 0 | — |
case-16 | fail→pass | 7,872 | 5,783 | -27% | 1 | 1 | 0% | 1,519 | 1,897 | +25% | 0 | 0 | — |
case-17 | fail→pass | 12,189 | 5,763 | -53% | 1 | 1 | 0% | 2,180 | 1,786 | -18% | 0 | 0 | — |
case-18 | fail→pass | 7,272 | 4,388 | -40% | 1 | 1 | 0% | 1,166 | 1,482 | +27% | 0 | 0 | — |
case-19 | fail→pass | 9,715 | 2,645 | -73% | 1 | 1 | 0% | 1,811 | 1,285 | -29% | 0 | 0 | — |
case-20 | pass→pass | 4,521 | 4,854 | +7% | 1 | 1 | 0% | 861 | 1,852 | +115% | 0 | 0 | — |
case-21 | pass→pass | 8,536 | 10,969 | +29% | 1 | 1 | 0% | 1,505 | 3,035 | +102% | 0 | 0 | — |
case-22 | pass→pass | 3,542 | 3,206 | -9% | 1 | 1 | 0% | 592 | 1,489 | +152% | 0 | 0 | — |
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. 22 cases were attempted, and 17 counted toward the lift figure. The other 5 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 +50 percentage points is the difference between those two pass rates over the 17 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.