Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Team-wide PR dashboard for the SDK pod. Shows open PRs touching SDK pod paths or authored by SDK roster members, sorted oldest-first, grouped by author tier (SDK Core / Platform / External) into needs-your-re-review / stale / needs-review / fully-approved, with merge-conflict and CI-red warnings. Use when checking team SDK pod PR status or invoking /qv-sdk-pr-status.
.claude/skills/tetherto-qv-sdk-pr-status/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -56% | 0% |
Thin wrapper over the shared pr-skills library, pinned to the SDK pod. PR data collection lives in .cursor/skills/_lib/pr-skills/pr-activity.mjs; this skill keeps the SDK-specific invocation.
Use when:
/qv-sdk-pr-statusgh CLI installed and authenticated (gh auth status)bashnode .cursor/skills/_lib/pr-skills/pr-status.mjs --pod sdk --mode team --authors union --tiers
--authors union — PRs that touch SDK ownedPaths or are authored by an SDK roster member--tiers — split into SDK Core / Platform/Middleware / External Contribution (opt-in; other pods stay flat unless they pass the flag)For the personal review queue, use --mode review. The script and its output format are documented in .cursor/skills/_lib/pr-skills/README.md.
Machine-readable output for daily status workflows:
bashnode .cursor/skills/_lib/pr-skills/pr-status.mjs --pod sdk --mode team --authors union --tiers --json
--pod sdk --mode team --authors union --tiers./qv-pr-review."| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,600 | 10,165 | +121% | 1 | 1 | 0% | 680 | 839 | +23% | 0 | 0 | — |
case-02 | fail→fail | 4,918 | 4,632 | -6% | 1 | 1 | 0% | 759 | 786 | +4% | 0 | 0 | — |
case-20 | fail→fail | 7,062 | 7,450 | +5% | 1 | 1 | 0% | 649 | 1,044 | +61% | 0 | 0 | — |
case-03 | fail→fail | 10,419 | 3,890 | -63% | 1 | 1 | 0% | 1,858 | 636 | -66% | 0 | 0 | — |
case-04 | pass→pass | 6,410 | 2,131 | -67% | 1 | 1 | 0% | 1,133 | 878 | -23% | 0 | 0 | — |
case-05 | fail→pass | 11,440 | 2,752 | -76% | 1 | 1 | 0% | 1,690 | 907 | -46% | 0 | 0 | — |
case-06 | fail→pass | 7,750 | 2,102 | -73% | 1 | 1 | 0% | 1,226 | 810 | -34% | 0 | 0 | — |
case-07 | fail→pass | 6,106 | 2,840 | -53% | 1 | 1 | 0% | 997 | 942 | -6% | 0 | 0 | — |
case-08 | fail→pass | 11,368 | 2,212 | -81% | 1 | 1 | 0% | 1,837 | 828 | -55% | 0 | 0 | — |
case-09 | pass→pass | 10,552 | 1,679 | -84% | 1 | 1 | 0% | 1,733 | 744 | -57% | 0 | 0 | — |
case-10 | fail→pass | 8,914 | 1,522 | -83% | 1 | 1 | 0% | 1,496 | 657 | -56% | 0 | 0 | — |
case-11 | pass→fail | 9,372 | 1,938 | -79% | 1 | 1 | 0% | 1,501 | 802 | -47% | 0 | 0 | — |
case-12 | fail→pass | 8,573 | 1,462 | -83% | 1 | 1 | 0% | 1,361 | 696 | -49% | 0 | 0 | — |
case-13 | fail→pass | 11,849 | 1,531 | -87% | 1 | 1 | 0% | 1,759 | 638 | -64% | 0 | 0 | — |
case-14 | fail→pass | 9,176 | 1,459 | -84% | 1 | 1 | 0% | 1,402 | 634 | -55% | 0 | 0 | — |
case-15 | pass→pass | 6,278 | 1,539 | -75% | 1 | 1 | 0% | 988 | 760 | -23% | 0 | 0 | — |
case-16 | pass→pass | 4,235 | 1,878 | -56% | 1 | 1 | 0% | 651 | 791 | +22% | 0 | 0 | — |
case-17 | fail→pass | 7,232 | 2,957 | -59% | 1 | 1 | 0% | 1,125 | 957 | -15% | 0 | 0 | — |
case-18 | fail→pass | 11,764 | 2,004 | -83% | 1 | 1 | 0% | 1,756 | 822 | -53% | 0 | 0 | — |
case-19 | fail→pass | 6,227 | 1,267 | -80% | 1 | 1 | 0% | 1,023 | 667 | -35% | 0 | 0 | — |
case-21 | pass→pass | 2,791 | 4,890 | +75% | 1 | 1 | 0% | 505 | 1,171 | +132% | 0 | 0 | — |
case-22 | fail→fail | 4,757 | 2,581 | -46% | 1 | 1 | 0% | 684 | 771 | +13% | 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 19 counted toward the lift figure. The other 3 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 +45 percentage points is the difference between those two pass rates over the 19 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.