Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Provides a GitHub pull request dashboard directly in the terminal. Use when the user wants to view PR status, check CI/CD progress, review bot comments, or merge pull requests without leaving Claude Code. Trigger with phrases like "show PR dashboard", "PR status", "check CI progress", "merge this PR", or "review pull request".
.claude/skills/jeremylongshore-gh-dash/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 166% | 0% |
| case-09 | ✓→✗ | ▼ Worse | -5% | 0% |
| case-17 | ✓→✗ | ▼ Worse | 21% | 0% |
| case-20 | ✓→✗ | ▼ Worse | -12% | 0% |
!git rev-parse --abbrev-ref HEAD 2>/dev/null || echo 'Not in a git repo' !gh auth status 2>&1 | head -1
GitHub pull request dashboard for Claude Code with CI/CD monitoring and merge capabilities.
This skill brings a complete GitHub pull request dashboard into your terminal workflow. Instead of switching to a browser to check PR status, review CI results, or merge branches, gh-dash consolidates all PR information into a single view. It displays real-time CI/CD progress with a visual progress bar, detects and summarizes bot comments (CodeRabbit, Cursor Bugbot, Coverage reporters), shows files changed with line-level statistics, and provides one-command merge operations with support for squash, merge commit, and rebase strategies.
The skill relies on the GitHub CLI (gh) for all API interactions, so it works with any GitHub repository where you have appropriate permissions. It respects branch protection rules, required reviews, and status checks, surfacing any blockers clearly before allowing merge operations.
gh pr view and gh pr checks to gather PR metadata, review status, and CI resultssquash (default), merge, rebaseThe skill produces formatted terminal output covering:
User: "What's the status of my PR?"
The skill will:
gh pr view --json title,state,reviews,statusCheckRollup,additions,deletions,changedFiles to gather data.User: "Merge this PR with squash."
The skill will:
gh pr checks.gh pr merge --squash --delete-branch to squash-merge and clean up the branch.User: "Summarize the bot comments on this PR."
The skill will:
gh api repos/{owner}/{repo}/pulls/{number}/comments.gh) must be installed and authenticated (gh auth status to verify).gh pr create or checking out the correct branch.gh command and provides installation instructions for the current platform.gh command reference| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,710 | 14,433 | +153% | 1 | 1 | 0% | 936 | 1,417 | +51% | 0 | 0 | — |
case-02 | fail→fail | 14,868 | 9,633 | -35% | 1 | 1 | 0% | 1,043 | 1,472 | +41% | 0 | 0 | — |
case-03 | fail→fail | 16,510 | 43,207 | +162% | 1 | 1 | 0% | 595 | 1,487 | +150% | 0 | 0 | — |
case-04 | pass→pass | 8,723 | 7,145 | -18% | 1 | 1 | 0% | 1,672 | 2,593 | +55% | 0 | 0 | — |
case-05 | pass→pass | 13,982 | 11,418 | -18% | 1 | 1 | 0% | 1,639 | 2,298 | +40% | 0 | 0 | — |
case-06 | fail→fail | 10,000 | 16,724 | +67% | 1 | 1 | 0% | 796 | 1,511 | +90% | 0 | 0 | — |
case-07 | pass→pass | 15,966 | 9,560 | -40% | 1 | 1 | 0% | 1,838 | 2,061 | +12% | 0 | 0 | — |
case-08 | fail→fail | 13,138 | 10,481 | -20% | 1 | 1 | 0% | 1,271 | 2,386 | +88% | 0 | 0 | — |
case-09 | pass→fail | 9,125 | 10,738 | +18% | 1 | 1 | 0% | 1,582 | 1,510 | -5% | 0 | 0 | — |
case-10 | pass→pass | 6,518 | 16,878 | +159% | 1 | 1 | 0% | 1,269 | 2,023 | +59% | 0 | 0 | — |
case-11 | fail→pass | 12,252 | 6,023 | -51% | 1 | 1 | 0% | 2,134 | 2,389 | +12% | 0 | 0 | — |
case-12 | pass→pass | 7,826 | 11,010 | +41% | 1 | 1 | 0% | 1,573 | 2,573 | +64% | 0 | 0 | — |
case-13 | pass→pass | 15,501 | 4,951 | -68% | 1 | 1 | 0% | 2,085 | 2,267 | +9% | 0 | 0 | — |
case-14 | pass→pass | 8,921 | 7,516 | -16% | 1 | 1 | 0% | 822 | 1,796 | +118% | 0 | 0 | — |
case-15 | fail→pass | 3,692 | 3,236 | -12% | 1 | 1 | 0% | 692 | 1,839 | +166% | 0 | 0 | — |
case-16 | pass→pass | 4,218 | 2,202 | -48% | 1 | 1 | 0% | 913 | 1,721 | +88% | 0 | 0 | — |
case-17 | pass→fail | 11,803 | 2,421 | -79% | 1 | 1 | 0% | 1,408 | 1,702 | +21% | 0 | 0 | — |
case-18 | fail→fail | 7,883 | 2,550 | -68% | 1 | 1 | 0% | 553 | 1,742 | +215% | 0 | 0 | — |
case-19 | pass→pass | 6,739 | 3,654 | -46% | 1 | 1 | 0% | 1,170 | 1,979 | +69% | 0 | 0 | — |
case-20 | pass→fail | 7,821 | 4,263 | -45% | 1 | 1 | 0% | 1,772 | 1,558 | -12% | 0 | 0 | — |
case-21 | pass→fail | 10,505 | 5,328 | -49% | 1 | 1 | 0% | 1,113 | 2,324 | +109% | 0 | 0 | — |
case-22 | pass→pass | 10,085 | 8,665 | -14% | 1 | 1 | 0% | 926 | 1,859 | +101% | 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 15 counted toward the lift figure. The other 7 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 -9 percentage points is the difference between those two pass rates over the 15 comparable cases. 5 cases got worse with the skill loaded, and they are 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.