Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
.claude/skills/hmbown-gh-assign-issues/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | 488% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-23 | ✗→✓ | ▲ Improved | 552% | 0% |
Retarget or assign a set of Codewhale issues to a milestone and/or owners in bulk, verifying every one. The milestone (or assignee) change is the signal; do not narrate it with comments. Use gh for all GitHub calls.
release milestone such as the current vX.Y.Z, or to assign to owners.
posting public chatter.
This skill changes milestone/assignee only. It does not close, label, comment, merge, or release. Those stay with the maintainer.
gh issue edit --milestone matches byname, so a typo silently fails (or worse, no-ops). Read the real titles and note the starting open-count:
bash gh api repos/Hmbown/CodeWhale/milestones \ --jq '.[] | "\(.number)\t\(.title)\topen=\(.open_issues)\tstate=\(.state)"'
Copy the title string verbatim (e.g. the live vX.Y.Z title). If the target milestone is missing or closed, stop and ask the maintainer; do not create one.
gh issue edit will happily retarget a PR or aclosed issue, so screen first. The url reveals PR-vs-issue (/pull/ vs /issues/); skip anything not OPEN or that is a PR:
bash for N in <N1> <N2> <N3>; do # substitute the real issue numbers gh issue view "$N" --repo Hmbown/CodeWhale \ --json number,state,url,milestone \ --jq '"\(.number)\t\(.state)\t\(.url)\tmilestone=\(.milestone.title // "none")"' done
Flag any row whose url contains /pull/ (it is a PR) or whose state is not OPEN, and exclude it from the loop below.
--milestone, --add-assignee, or both:
bash for N in <N1> <N2> <N3>; do # substitute the real issue numbers if gh issue edit "$N" --repo Hmbown/CodeWhale \ --milestone "<milestone>" >/dev/null 2>&1; then echo "ok #$N -> <milestone>" else echo "FAIL #$N (PR? closed? bad milestone title?)" fi done # owners: add --add-assignee handle (do not invent logins)
Edit is idempotent: re-pointing an already-correct issue is harmless.
count rose by the number of issues you moved in (minus any you skipped). Spot-check a few with the step-2 view to confirm milestone.title is now the target.
title mismatch), the before/after open-count, and any owner assignments. No public comment is posted.
confirm each is an issue, not a PR (/pull/ in the url), before editing.
or fails silently; an invalid login errors mid-loop.
extra chatter is noise to good-faith contributors.
explicit maintainer approval (see AGENTS.md).
edit silently failed.
markers (Co-authored-by / Harvested from PR #N), or closing references.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 9,722 | 9,038 | -7% | 1 | 1 | 0% | 652 | 1,487 | +128% | 0 | 0 | — |
case-02 | fail→fail | 18,946 | 8,690 | -54% | 1 | 1 | 0% | 736 | 1,399 | +90% | 0 | 0 | — |
case-03 | fail→fail | 23,296 | 12,407 | -47% | 1 | 1 | 0% | 318 | 1,335 | +320% | 0 | 0 | — |
case-04 | fail→fail | 11,890 | 11,883 | -0% | 1 | 1 | 0% | 524 | 1,681 | +221% | 0 | 0 | — |
case-05 | fail→fail | 11,509 | 10,953 | -5% | 1 | 1 | 0% | 1,776 | 1,322 | -26% | 0 | 0 | — |
case-06 | fail→fail | 18,488 | 8,846 | -52% | 1 | 1 | 0% | 831 | 1,500 | +81% | 0 | 0 | — |
case-07 | fail→fail | 10,216 | 11,858 | +16% | 1 | 1 | 0% | 1,728 | 1,497 | -13% | 0 | 0 | — |
case-08 | fail→fail | 7,830 | 7,377 | -6% | 1 | 1 | 0% | 319 | 1,422 | +346% | 0 | 0 | — |
case-09 | pass→pass | 17,388 | 3,964 | -77% | 1 | 1 | 0% | 2,961 | 1,656 | -44% | 0 | 0 | — |
case-10 | fail→fail | 5,832 | 7,519 | +29% | 1 | 1 | 0% | 658 | 1,455 | +121% | 0 | 0 | — |
case-11 | fail→fail | 13,858 | 8,261 | -40% | 1 | 1 | 0% | 1,137 | 1,438 | +26% | 0 | 0 | — |
case-12 | fail→fail | 17,620 | 9,593 | -46% | 1 | 1 | 0% | 802 | 1,543 | +92% | 0 | 0 | — |
case-13 | pass→fail | 34,763 | 7,067 | -80% | 1 | 1 | 0% | 2,116 | 1,516 | -28% | 0 | 0 | — |
case-14 | fail→pass | 6,445 | 28,707 | +345% | 1 | 1 | 0% | 727 | 4,273 | +488% | 0 | 0 | — |
case-15 | fail→fail | 10,805 | 14,145 | +31% | 1 | 1 | 0% | 1,686 | 1,698 | +1% | 0 | 0 | — |
case-16 | fail→pass | 8,089 | 6,292 | -22% | 1 | 1 | 0% | 1,464 | 2,073 | +42% | 0 | 0 | — |
case-17 | pass→fail | 5,603 | 11,684 | +109% | 1 | 1 | 0% | 848 | 1,676 | +98% | 0 | 0 | — |
case-18 | fail→fail | 24,103 | 8,880 | -63% | 1 | 1 | 0% | 2,053 | 1,501 | -27% | 0 | 0 | — |
case-19 | pass→pass | 9,369 | 2,397 | -74% | 1 | 1 | 0% | 1,307 | 1,333 | +2% | 0 | 0 | — |
case-20 | fail→pass | 11,480 | 13,698 | +19% | 1 | 1 | 0% | 1,493 | 2,309 | +55% | 0 | 0 | — |
case-21 | fail→pass | 33,347 | 15,524 | -53% | 1 | 1 | 0% | 2,463 | 2,408 | -2% | 0 | 0 | — |
case-22 | pass→fail | 6,850 | 12,025 | +76% | 1 | 1 | 0% | 897 | 1,657 | +85% | 0 | 0 | — |
case-23 | fail→pass | 7,895 | 14,976 | +90% | 1 | 1 | 0% | 539 | 3,514 | +552% | 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. 23 cases were attempted, and 6 counted toward the lift figure. The other 17 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 6 comparable cases. 3 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 9/8/2026 | +4% |
| gemini-3.6-flash | verified | 8/7/2026 | +27% |
Other measured skills in the registry, with their headline benchmark lift.