Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fetch and rank open GitHub issues by community engagement, present the top 3 candidates, and plan implementation for the selected issue. Use when the user asks to "pick next issue", "next issue", "which issue should I work on", "top issues", "most popular issues", "prioritize issues", or "what should I work on next".
.claude/skills/tobihagemann-pick-next-issue/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -53% | 0% |
Rank open GitHub issues by engagement and plan the selected issue.
Run gh issue list to fetch open issues with engagement data:
bashgh issue list --state open --json number,title,url,reactionGroups,comments,labels,createdAt --limit 50
Calculate an engagement score for each issue:
reactionGroups (thumbs up, heart, hooray, etc.). Weight thumbs-up (THUMBS_UP) reactions 2x since they signal explicit demand.(weighted reactions) + commentsSort issues by engagement score descending.
Present the top 3 issues in a numbered list. For each issue, show:
If fewer than 3 open issues exist, present all of them.
If no open issues exist, inform the user and stop.
Ask the user to pick one of the presented issues (or request to see more).
If the user asks to see more, present the next 3 issues from the ranked list.
Fetch the complete issue details for the selected issue:
bashgh issue view <number> --json number,title,body,url,labels,comments,reactionGroups,assignees,milestone
Read the full issue body and comments to understand the requirements and any discussion context.
$turboplan SkillRun the $turboplan skill with the issue body as the task description. Tell turboplan that the plan must include a final implementation step: "Close issue #N or reference it in the PR with Closes #N."
gh CLI authenticated with access to the current repogh fails (not in a repo, not authenticated), inform the user and stop| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,604 | 5,499 | +53% | 1 | 1 | 0% | 512 | 891 | +74% | 0 | 0 | — |
case-02 | fail→fail | 4,010 | 21,427 | +434% | 1 | 1 | 0% | 610 | 685 | +12% | 0 | 0 | — |
case-03 | fail→fail | 4,549 | 13,430 | +195% | 1 | 1 | 0% | 680 | 2,623 | +286% | 0 | 0 | — |
case-04 | fail→pass | 7,668 | 4,570 | -40% | 1 | 1 | 0% | 1,337 | 1,429 | +7% | 0 | 0 | — |
case-05 | pass→pass | 12,173 | 2,615 | -79% | 1 | 1 | 0% | 2,115 | 964 | -54% | 0 | 0 | — |
case-06 | fail→pass | 8,562 | 1,920 | -78% | 1 | 1 | 0% | 1,385 | 752 | -46% | 0 | 0 | — |
case-07 | fail→fail | 8,149 | 1,482 | -82% | 1 | 1 | 0% | 1,157 | 702 | -39% | 0 | 0 | — |
case-08 | fail→fail | 10,066 | 1,621 | -84% | 1 | 1 | 0% | 1,484 | 712 | -52% | 0 | 0 | — |
case-09 | fail→fail | 2,420 | 2,140 | -12% | 1 | 1 | 0% | 339 | 816 | +141% | 0 | 0 | — |
case-10 | fail→pass | 6,943 | 2,474 | -64% | 1 | 1 | 0% | 1,115 | 982 | -12% | 0 | 0 | — |
case-11 | fail→pass | 8,031 | 1,938 | -76% | 1 | 1 | 0% | 1,146 | 792 | -31% | 0 | 0 | — |
case-12 | pass→pass | 12,386 | 1,968 | -84% | 1 | 1 | 0% | 2,048 | 782 | -62% | 0 | 0 | — |
case-13 | fail→fail | 3,877 | 1,765 | -54% | 1 | 1 | 0% | 548 | 747 | +36% | 0 | 0 | — |
case-14 | pass→pass | 10,951 | 2,099 | -81% | 1 | 1 | 0% | 1,910 | 808 | -58% | 0 | 0 | — |
case-15 | pass→pass | 11,152 | 2,512 | -77% | 1 | 1 | 0% | 1,704 | 795 | -53% | 0 | 0 | — |
case-16 | pass→pass | 4,786 | 2,747 | -43% | 1 | 1 | 0% | 833 | 1,006 | +21% | 0 | 0 | — |
case-17 | fail→pass | 10,301 | 2,197 | -79% | 1 | 1 | 0% | 1,747 | 821 | -53% | 0 | 0 | — |
case-18 | fail→pass | 6,341 | 2,837 | -55% | 1 | 1 | 0% | 931 | 1,010 | +8% | 0 | 0 | — |
case-19 | fail→pass | 15,781 | 3,097 | -80% | 1 | 1 | 0% | 2,377 | 1,060 | -55% | 0 | 0 | — |
case-20 | pass→pass | 3,129 | 3,545 | +13% | 1 | 1 | 0% | 469 | 1,058 | +126% | 0 | 0 | — |
case-21 | pass→pass | 5,066 | 4,221 | -17% | 1 | 1 | 0% | 825 | 1,132 | +37% | 0 | 0 | — |
case-22 | pass→fail | 4,630 | 5,883 | +27% | 1 | 1 | 0% | 646 | 828 | +28% | 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 18 counted toward the lift figure. The other 4 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 +27 percentage points is the difference between those two pass rates over the 18 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.