Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →GitHub操作、自動化、APIインテグレーション、およびCI/CDワークフロー。
.claude/skills/affaan-m-github-ops/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 27% | 0% |
管理 GitHub 仓库，重点关注社区健康、CI 可靠性和贡献者体验。
gh auth login 配置仓库访问权限按类型和优先级对每个议题进行分类：
类型： bug, feature-request, question, documentation, enhancement, duplicate, invalid, good-first-issue
优先级： critical（破坏性/安全相关）, high（重大影响）, medium（锦上添花）, low（外观/体验优化）
gh issue edit --add-label 应用适当的标签good-first-issue 标签duplicate 标签bash# Search for potential duplicates gh issue list --search "keyword" --state all --limit 20 # Add labels gh issue edit <number> --add-label "bug,high-priority" # Comment on issue gh issue comment <number> --body "Thanks for reporting. Could you share reproduction steps?"
gh pr checks <number>gh pr view <number> --json mergeablestale 标签，评论要求更新closed-stale 标签）bash# Find stale issues (no activity in 14+ days) gh issue list --label "stale" --state open # Find PRs with no recent activity gh pr list --json number,title,updatedAt --jq '.[] | select(.updatedAt < "2026-03-01")'
当 CI 失败时：
gh run view <run-id> --log-failedbash# List recent failed runs gh run list --status failure --limit 10 # View failed run logs gh run view <run-id> --log-failed # Re-run a failed workflow gh run rerun <run-id> --failed
准备发布时：
gh pr list --state merged --base maingh release createbash# List merged PRs since last release gh pr list --state merged --base main --search "merged:>2026-03-01" # Create a release gh release create v1.2.0 --title "v1.2.0" --generate-notes # Create a pre-release gh release create v1.3.0-rc1 --prerelease --title "v1.3.0 Release Candidate 1"
bash# Check Dependabot alerts gh api repos/{owner}/{repo}/dependabot/alerts --jq '.[].security_advisory.summary' # Check secret scanning alerts gh api repos/{owner}/{repo}/secret-scanning/alerts --jq '.[].state' # Review and auto-merge safe dependency bumps gh pr list --label "dependencies" --json number,title
在完成任何 GitHub 操作任务之前：
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 13,464 | 5,382 | -60% | 1 | 1 | 0% | 2,172 | 1,856 | -15% | 0 | 0 | — |
case-02 | fail→fail | 7,572 | 5,288 | -30% | 1 | 1 | 0% | 1,334 | 1,572 | +18% | 0 | 0 | — |
case-03 | fail→fail | 13,439 | 3,818 | -72% | 1 | 1 | 0% | 2,093 | 1,695 | -19% | 0 | 0 | — |
case-04 | fail→pass | 5,412 | 2,576 | -52% | 1 | 1 | 0% | 911 | 1,599 | +76% | 0 | 0 | — |
case-05 | fail→pass | 11,926 | 7,132 | -40% | 1 | 1 | 0% | 1,782 | 2,394 | +34% | 0 | 0 | — |
case-06 | fail→pass | 12,206 | 5,370 | -56% | 1 | 1 | 0% | 1,873 | 2,098 | +12% | 0 | 0 | — |
case-07 | fail→pass | 10,789 | 4,333 | -60% | 1 | 1 | 0% | 1,881 | 1,994 | +6% | 0 | 0 | — |
case-08 | pass→pass | 2,466 | 2,494 | +1% | 1 | 1 | 0% | 452 | 1,565 | +246% | 0 | 0 | — |
case-09 | pass→pass | 5,761 | 2,500 | -57% | 1 | 1 | 0% | 1,034 | 1,517 | +47% | 0 | 0 | — |
case-10 | fail→pass | 8,696 | 3,304 | -62% | 1 | 1 | 0% | 1,354 | 1,725 | +27% | 0 | 0 | — |
case-11 | pass→pass | 3,098 | 1,918 | -38% | 1 | 1 | 0% | 443 | 1,453 | +228% | 0 | 0 | — |
case-12 | pass→pass | 8,000 | 3,631 | -55% | 1 | 1 | 0% | 1,339 | 1,669 | +25% | 0 | 0 | — |
case-13 | fail→pass | 5,539 | 2,627 | -53% | 1 | 1 | 0% | 1,162 | 1,578 | +36% | 0 | 0 | — |
case-14 | fail→fail | 14,117 | 7,330 | -48% | 1 | 1 | 0% | 2,271 | 2,590 | +14% | 0 | 0 | — |
case-15 | pass→pass | 4,774 | 2,564 | -46% | 1 | 1 | 0% | 801 | 1,644 | +105% | 0 | 0 | — |
case-16 | pass→pass | 6,267 | 2,672 | -57% | 1 | 1 | 0% | 1,214 | 1,665 | +37% | 0 | 0 | — |
case-17 | fail→pass | 6,362 | 2,610 | -59% | 1 | 1 | 0% | 1,000 | 1,641 | +64% | 0 | 0 | — |
case-18 | pass→pass | 10,781 | 3,940 | -63% | 1 | 1 | 0% | 1,597 | 1,877 | +18% | 0 | 0 | — |
case-19 | pass→pass | 9,302 | 4,908 | -47% | 1 | 1 | 0% | 1,614 | 1,968 | +22% | 0 | 0 | — |
case-20 | pass→pass | 3,102 | 2,972 | -4% | 1 | 1 | 0% | 544 | 1,758 | +223% | 0 | 0 | — |
case-21 | pass→pass | 2,691 | 2,222 | -17% | 1 | 1 | 0% | 367 | 1,498 | +308% | 0 | 0 | — |
case-22 | pass→pass | 3,453 | 3,210 | -7% | 1 | 1 | 0% | 647 | 1,655 | +156% | 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. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 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.