Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Issue management for devloop — templates for goal, rule.yml, key-results, and issue lifecycle.
.claude/skills/x-cmd-issue/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 41% | 0% |
Part of devloop.
gh issue create --title "<scope>: <short description>" --body "$(cat <<'EOF'
## Goal
<one-line objective>
## Key Results
- [ ] KR-1: <verifiable outcome>
- [ ] KR-2: <verifiable outcome>
## rule.ymlgoal: "<same as above>" keyresults:
rules:
name: <name> apply: "<file pattern>" level: error desc:
## Screenshots
- Before: <image or "N/A">
- After: <image or "pending">
EOF
)"| Stage | Action | Comment content | |-------|--------|-----------------| | Created | gh issue create with template | goal, key-results, rule.yml | | In progress | Update as work proceeds | progress notes, intermediate screenshots | | Verified | x rule check passes | rule check result, after screenshot | | Closed | gh issue close | commit SHA, final verification summary |
gh issue comment <n> --body "$(cat <<'EOF'
## Verified
- rule.yml: <code block or link>
- x rule check: PASS
- Before: <image>
- After: <image>
- Commit: <sha>
EOF
)"goal and keyresults in every dev issue — no exceptions| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 10,309 | 5,953 | -42% | 1 | 1 | 0% | 1,666 | 1,536 | -8% | 0 | 0 | — |
case-02 | fail→pass | 7,701 | 3,658 | -52% | 1 | 1 | 0% | 1,313 | 1,079 | -18% | 0 | 0 | — |
case-03 | fail→pass | 9,677 | 5,839 | -40% | 1 | 1 | 0% | 1,534 | 1,542 | +1% | 0 | 0 | — |
case-04 | fail→pass | 7,933 | 4,276 | -46% | 1 | 1 | 0% | 1,181 | 1,151 | -3% | 0 | 0 | — |
case-05 | fail→pass | 8,700 | 8,715 | +0% | 1 | 1 | 0% | 1,260 | 1,773 | +41% | 0 | 0 | — |
case-06 | fail→pass | 12,536 | 6,122 | -51% | 1 | 1 | 0% | 2,050 | 1,544 | -25% | 0 | 0 | — |
case-07 | fail→pass | 19,168 | 4,518 | -76% | 1 | 1 | 0% | 795 | 1,096 | +38% | 0 | 0 | — |
case-08 | fail→pass | 8,974 | 7,178 | -20% | 1 | 1 | 0% | 1,281 | 1,745 | +36% | 0 | 0 | — |
case-09 | fail→pass | 5,039 | 4,872 | -3% | 1 | 1 | 0% | 634 | 1,266 | +100% | 0 | 0 | — |
case-10 | fail→pass | 9,846 | 3,919 | -60% | 1 | 1 | 0% | 1,452 | 1,058 | -27% | 0 | 0 | — |
case-11 | fail→pass | 15,016 | 9,124 | -39% | 1 | 1 | 0% | 2,065 | 1,892 | -8% | 0 | 0 | — |
case-12 | pass→pass | 11,822 | 3,944 | -67% | 1 | 1 | 0% | 1,609 | 934 | -42% | 0 | 0 | — |
case-13 | fail→pass | 14,361 | 3,583 | -75% | 1 | 1 | 0% | 2,063 | 833 | -60% | 0 | 0 | — |
case-14 | fail→fail | 13,594 | 3,131 | -77% | 1 | 1 | 0% | 1,410 | 918 | -35% | 0 | 0 | — |
case-15 | fail→pass | 11,303 | 3,836 | -66% | 1 | 1 | 0% | 1,469 | 1,021 | -30% | 0 | 0 | — |
case-16 | pass→pass | 17,409 | 4,777 | -73% | 1 | 1 | 0% | 2,412 | 1,113 | -54% | 0 | 0 | — |
case-17 | fail→pass | 36,468 | 3,961 | -89% | 1 | 1 | 0% | 2,332 | 989 | -58% | 0 | 0 | — |
case-18 | pass→pass | 13,239 | 6,614 | -50% | 1 | 1 | 0% | 2,067 | 1,280 | -38% | 0 | 0 | — |
case-19 | pass→pass | 15,385 | 4,105 | -73% | 1 | 1 | 0% | 1,215 | 1,049 | -14% | 0 | 0 | — |
case-20 | fail→pass | 4,811 | 2,438 | -49% | 1 | 1 | 0% | 665 | 822 | +24% | 0 | 0 | — |
case-21 | fail→pass | 10,897 | 3,650 | -67% | 1 | 1 | 0% | 1,464 | 1,040 | -29% | 0 | 0 | — |
case-22 | fail→pass | 14,740 | 2,606 | -82% | 1 | 1 | 0% | 2,123 | 821 | -61% | 0 | 0 | — |
case-23 | fail→pass | 22,923 | 3,581 | -84% | 1 | 1 | 0% | 1,977 | 778 | -61% | 0 | 0 | — |
case-24 | pass→pass | 16,920 | 10,704 | -37% | 1 | 1 | 0% | 1,625 | 2,198 | +35% | 0 | 0 | — |
case-25 | pass→pass | 13,416 | 16,186 | +21% | 1 | 1 | 0% | 2,397 | 1,738 | -27% | 0 | 0 | — |
case-26 | pass→pass | 7,486 | 5,654 | -24% | 1 | 1 | 0% | 944 | 1,284 | +36% | 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. 26 cases were attempted. The headline lift of +69 percentage points is the difference between those two pass rates over the 26 comparable cases.
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.