Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Creates GitHub issues following test-driven development principles and proper labeling conventions. This skill should be used when the user asks to "create an issue", "file a bug", or needs to document new requirements, epics, or PR-scoped tasks.
.claude/skills/fradser-create-issues/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 1265% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 895% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-23 | ✗→✓ | ▲ Improved | -9% | 0% |
Execute automated GitHub issue creation workflow for $ARGUMENTS following TDD principles and conventional commit standards.
git statusgit branch --show-currentgh issue list --state open --limit 10gh auth statusFollow TDD principles, conventional commits, and protected branch workflows. Use proper labels, auto-closing keywords, and atomic commits. See references/requirements.md for complete standards.
Goal: Assess repository state, detect templates, and determine issue scope and type.
Actions:
CONTRIBUTING.md) and follow its requirements.github/ISSUE_TEMPLATE/ directorygh issue create --list$ARGUMENTS complexityreferences/decision-logic.mdSee references/repository-templates.md for template detection and compliance details.
Goal: Create GitHub issue with proper structure, labels, and links.
Actions:
references/decision-logic.md for commands)references/issue-structure.md--label--assignee--milestone or projects using --project if requestedreferences/auto-closing-keywords.md for the full rule and keyword table.Goal: Document decisions and communicate follow-up actions.
Actions:
references/requirements.md - Full TDD and commit standardsreferences/decision-logic.md - Branch-based decisions and issue typesreferences/issue-structure.md - Title, labels, body, auto-closingreferences/auto-closing-keywords.md - Default-branch limitation and keyword tablereferences/repository-templates.md - Contributing guidelines and issue templatesreferences/examples.md - Commit message examples| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 4,145 | 9,643 | +133% | 1 | 1 | 0% | 214 | 1,141 | +433% | 0 | 0 | — |
case-02 | fail→pass | 4,899 | 22,555 | +360% | 1 | 1 | 0% | 348 | 4,749 | +1265% | 0 | 0 | — |
case-03 | fail→fail | 3,752 | 15,305 | +308% | 1 | 1 | 0% | 468 | 2,432 | +420% | 0 | 0 | — |
case-04 | fail→pass | 5,541 | 15,602 | +182% | 1 | 1 | 0% | 326 | 3,243 | +895% | 0 | 0 | — |
case-05 | pass→fail | 8,644 | 27,308 | +216% | 1 | 1 | 0% | 1,767 | 6,190 | +250% | 0 | 0 | — |
case-06 | pass→fail | 16,934 | 41,051 | +142% | 1 | 1 | 0% | 2,674 | 7,957 | +198% | 0 | 0 | — |
case-07 | pass→pass | 10,255 | 19,588 | +91% | 1 | 1 | 0% | 1,824 | 3,614 | +98% | 0 | 0 | — |
case-08 | pass→pass | 11,926 | 8,225 | -31% | 1 | 1 | 0% | 2,051 | 2,053 | +0% | 0 | 0 | — |
case-09 | pass→pass | 10,307 | 6,917 | -33% | 1 | 1 | 0% | 1,497 | 1,760 | +18% | 0 | 0 | — |
case-10 | fail→pass | 5,578 | 3,950 | -29% | 1 | 1 | 0% | 958 | 1,356 | +42% | 0 | 0 | — |
case-11 | fail→pass | 3,581 | 3,054 | -15% | 1 | 1 | 0% | 663 | 1,171 | +77% | 0 | 0 | — |
case-12 | pass→pass | 3,479 | 2,127 | -39% | 1 | 1 | 0% | 551 | 1,070 | +94% | 0 | 0 | — |
case-13 | pass→pass | 5,421 | 1,722 | -68% | 1 | 1 | 0% | 772 | 994 | +29% | 0 | 0 | — |
case-14 | pass→pass | 3,039 | 4,626 | +52% | 1 | 1 | 0% | 467 | 1,431 | +206% | 0 | 0 | — |
case-15 | pass→pass | 2,684 | 3,310 | +23% | 1 | 1 | 0% | 397 | 1,154 | +191% | 0 | 0 | — |
case-16 | pass→pass | 3,293 | 1,902 | -42% | 1 | 1 | 0% | 550 | 1,025 | +86% | 0 | 0 | — |
case-17 | pass→pass | 6,993 | 5,692 | -19% | 1 | 1 | 0% | 994 | 1,590 | +60% | 0 | 0 | — |
case-18 | pass→pass | 8,520 | 4,041 | -53% | 1 | 1 | 0% | 1,386 | 1,383 | -0% | 0 | 0 | — |
case-19 | pass→pass | 4,020 | 3,916 | -3% | 1 | 1 | 0% | 620 | 1,330 | +115% | 0 | 0 | — |
case-20 | pass→pass | 4,306 | 2,052 | -52% | 1 | 1 | 0% | 636 | 1,020 | +60% | 0 | 0 | — |
case-21 | pass→pass | 3,858 | 1,960 | -49% | 1 | 1 | 0% | 590 | 967 | +64% | 0 | 0 | — |
case-22 | pass→pass | 3,183 | 2,866 | -10% | 1 | 1 | 0% | 523 | 1,212 | +132% | 0 | 0 | — |
case-23 | fail→pass | 8,776 | 2,965 | -66% | 1 | 1 | 0% | 1,315 | 1,199 | -9% | 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 19 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 -33 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 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.