Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
.claude/skills/microck-github-project-management/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 240% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 316% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 1615% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 334% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 540% | 0% |
A comprehensive skill for managing GitHub projects using AI swarm coordination. This skill combines intelligent issue management, automated project board synchronization, and swarm-based coordination for efficient project delivery.
bash# Create a coordinated issue gh issue create \ --title "Feature: Advanced Authentication" \ --body "Implement OAuth2 with social login..." \ --label "enhancement,swarm-ready" # Initialize swarm for issue npx claude-flow@alpha hooks pre-task --description "Feature implementation"
bash# Get project ID PROJECT_ID=$(gh project list --owner @me --format json | \ jq -r '.projects[0].id') # Initialize board sync npx ruv-swarm github board-init \ --project-id "$PROJECT_ID" \ --sync-mode "bidirectional"
<details> <summary><strong>Automated Issue Creation</strong></summary>
javascript// Initialize issue management swarm mcp__claude-flow__swarm_init { topology: "star", maxAgents: 3 } mcp__claude-flow__agent_spawn { type: "coordinator", name: "Issue Coordinator" } mcp__claude-flow__agent_spawn { type: "researcher", name: "Requirements Analyst" } mcp__claude-flow__agent_spawn { type: "coder", name: "Implementation Planner" } // Create comprehensive issue mcp__github__create_issue { owner: "org", repo: "repository", title: "Integration Review: Complete system integration", body: `## 🔄 Integration Review ### Overview Comprehensive review and integration between components. ### Objectives - [ ] Verify dependencies and imports - [ ] Ensure API integration - [ ] Check hook system integration - [ ] Validate data systems alignment ### Swarm Coordination This issue will be managed by coordinated swarm agents for optimal progress tracking.`, labels: ["integration", "review", "enhancement"], assignees: ["username"] } // Set up automated tracking mcp__claude-flow__task_orchestrate { task: "Monitor and coordinate issue progress with automated updates", strategy: "adaptive", priority: "medium" }
bash# Create multiple related issues using gh CLI gh issue create \ --title "Feature: Advanced GitHub Integration" \ --body "Implement comprehensive GitHub workflow automation..." \ --label "feature,github,high-priority" gh issue create \ --title "Bug: Merge conflicts in integration branch" \ --body "Resolve merge conflicts..." \ --label "bug,integration,urgent" gh issue create \ --title "Documentation: Update integration guides" \ --body "Update all documentation..." \ --label "documentation,integration"
</details>
<details> <summary><strong>Issue-to-Swarm Conversion</strong></summary>
bash# Get issue details ISSUE_DATA=$(gh issue view 456 --json title,body,labels,assignees,comments) # Create swarm from issue npx ruv-swarm github issue-to-swarm 456 \ --issue-data "$ISSUE_DATA" \ --auto-decompose \ --assign-agents # Batch process multiple issues ISSUES=$(gh issue list --label "swarm-ready" --json number,title,body,labels) npx ruv-swarm github issues-batch \ --issues "$ISSUES" \ --parallel # Update issues with swarm status echo "$ISSUES" | jq -r '.[].number' | while read -r num; do gh issue edit $num --add-label "swarm-processing" done
Execute swarm operations via issue comments:
markdown<!-- In issue comment --> /swarm analyze /swarm decompose 5 /swarm assign @agent-coder /swarm estimate /swarm start
</details>
<details> <summary><strong>Automated Issue Triage</strong></summary>
javascript// .github/swarm-labels.json { "rules": [ { "keywords": ["bug", "error", "broken"], "labels": ["bug", "swarm-debugger"], "agents": ["debugger", "tester"] }, { "keywords": ["feature", "implement", "add"], "labels": ["enhancement", "swarm-feature"], "agents": ["architect", "coder", "tester"] }, { "keywords": ["slow", "performance", "optimize"], "labels": ["performance", "swarm-optimizer"], "agents": ["analyst", "optimizer"] } ] }
bash# Analyze and triage unlabeled issues npx ruv-swarm github triage \ --unlabeled \ --analyze-content \ --suggest-labels \ --assign-priority # Find and link duplicate issues npx ruv-swarm github find-duplicates \ --threshold 0.8 \ --link-related \ --close-duplicates
</details>
<details> <summary><strong>Task Decomposition & Progress Tracking</strong></summary>
bash# Get issue body ISSUE_BODY=$(gh issue view 456 --json body --jq '.body') # Decompose into subtasks SUBTASKS=$(npx ruv-swarm github issue-decompose 456 \ --body "$ISSUE_BODY" \ --max-subtasks 10 \ --assign-priorities) # Update issue with checklist CHECKLIST=$(echo "$SUBTASKS" | jq -r '.tasks[] | "- [ ] " + .description') UPDATED_BODY="$ISSUE_BODY ## Subtasks $CHECKLIST" gh issue edit 456 --body "$UPDATED_BODY" # Create linked issues for major subtasks echo "$SUBTASKS" | jq -r '.tasks[] | select(.priority == "high")' | while read -r task; do TITLE=$(echo "$task" | jq -r '.title') BODY=$(echo "$task" | jq -r '.description') gh issue create \ --title "$TITLE" \ --body "$BODY Parent issue: #456" \ --label "subtask" done
bash# Get current issue state CURRENT=$(gh issue view 456 --json body,labels) # Get swarm progress PROGRESS=$(npx ruv-swarm github issue-progress 456) # Update checklist in issue body UPDATED_BODY=$(echo "$CURRENT" | jq -r '.body' | \ npx ruv-swarm github update-checklist --progress "$PROGRESS") # Edit issue with updated body gh issue edit 456 --body "$UPDATED_BODY" # Post progress summary as comment SUMMARY=$(echo "$PROGRESS" | jq -r ' "## 📊 Progress Update **Completion**: \(.completion)% **ETA**: \(.eta) ### Completed Tasks \(.completed | map("- ✅ " + .) | join("\n")) ### In Progress \(.in_progress | map("- 🔄 " + .) | join("\n")) ### Remaining \(.remaining | map("- ⏳ " + .) | join("\n")) --- 🤖 Automated update by swarm agent"') gh issue comment 456 --body "$SUMMARY" # Update labels based on progress if [[ $(echo "$PROGRESS" | jq -r '.completion') -eq 100 ]]; then gh issue edit 456 --add-label "ready-for-review" --remove-label "in-progress" fi
</details>
<details> <summary><strong>Stale Issue Management</strong></summary>
bash# Find stale issues STALE_DATE=$(date -d '30 days ago' --iso-8601) STALE_ISSUES=$(gh issue list --state open --json number,title,updatedAt,labels \ --jq ".[] | select(.updatedAt < \"$STALE_DATE\")") # Analyze each stale issue echo "$STALE_ISSUES" | jq -r '.number' | while read -r num; do # Get full issue context ISSUE=$(gh issue view $num --json title,body,comments,labels) # Analyze with swarm ACTION=$(npx ruv-swarm github analyze-stale \ --issue "$ISSUE" \ --suggest-action) case "$ACTION" in "close") gh issue comment $num --body "This issue has been inactive for 30 days and will be closed in 7 days if there's no further activity." gh issue edit $num --add-label "stale" ;; "keep") gh issue edit $num --remove-label "stale" 2>/dev/null || true ;; "needs-info") gh issue comment $num --body "This issue needs more information. Please provide additional context or it may be closed as stale." gh issue edit $num --add-label "needs-info" ;; esac done # Close issues that have been stale for 37+ days gh issue list --label stale --state open --json number,updatedAt \ --jq ".[] | select(.updatedAt < \"$(date -d '37 days ago' --iso-8601)\") | .number" | \ while read -r num; do gh issue close $num --comment "Closing due to inactivity. Feel free to reopen if this is still relevant." done
</details>
<details> <summary><strong>Board Initialization & Configuration</strong></summary>
bash# Get project details PROJECT_ID=$(gh project list --owner @me --format json | \ jq -r '.projects[] | select(.title == "Development Board") | .id') # Initialize swarm with project npx ruv-swarm github board-init \ --project-id "$PROJECT_ID" \ --sync-mode "bidirectional" \ --create-views "swarm-status,agent-workload,priority" # Create project fields for swarm tracking gh project field-create $PROJECT_ID --owner @me \ --name "Swarm Status" \ --data-type "SINGLE_SELECT" \ --single-select-options "pending,in_progress,completed"
yaml# .github/board-sync.yml version: 1 project: name: "AI Development Board" number: 1 mapping: # Map swarm task status to board columns status: pending: "Backlog" assigned: "Ready" in_progress: "In Progress" review: "Review" completed: "Done" blocked: "Blocked" # Map agent types to labels agents: coder: "🔧 Development" tester: "🧪 Testing" analyst: "📊 Analysis" designer: "🎨 Design" architect: "🏗️ Architecture" # Map priority to project fields priority: critical: "🔴 Critical" high: "🟡 High" medium: "🟢 Medium" low: "⚪ Low" # Custom fields fields: - name: "Agent Count" type: number source: task.agents.length - name: "Complexity" type: select source: task.complexity - name: "ETA" type: date source: task.estimatedCompletion
</details>
<details> <summary><strong>Task Synchronization</strong></summary>
bash# Sync swarm tasks with project cards npx ruv-swarm github board-sync \ --map-status '{ "todo": "To Do", "in_progress": "In Progress", "review": "Review", "done": "Done" }' \ --auto-move-cards \ --update-metadata # Enable real-time board updates npx ruv-swarm github board-realtime \ --webhook-endpoint "https://api.example.com/github-sync" \ --update-frequency "immediate" \ --batch-updates false
bash# List issues with label ISSUES=$(gh issue list --label "enhancement" --json number,title,body) # Add issues to project echo "$ISSUES" | jq -r '.[].number' | while read -r issue; do gh project item-add $PROJECT_ID --owner @me --url "https://github.com/$GITHUB_REPOSITORY/issues/$issue" done # Process with swarm npx ruv-swarm github board-import-issues \ --issues "$ISSUES" \ --add-to-column "Backlog" \ --parse-checklist \ --assign-agents
</details>
<details> <summary><strong>Smart Card Management</strong></summary>
bash# Automatically assign cards to agents npx ruv-swarm github board-auto-assign \ --strategy "load-balanced" \ --consider "expertise,workload,availability" \ --update-cards
bash# Smart card movement based on rules npx ruv-swarm github board-smart-move \ --rules '{ "auto-progress": "when:all-subtasks-done", "auto-review": "when:tests-pass", "auto-done": "when:pr-merged" }'
bash# Bulk card operations npx ruv-swarm github board-bulk \ --filter "status:blocked" \ --action "add-label:needs-attention" \ --notify-assignees
</details>
<details> <summary><strong>Custom Views & Dashboards</strong></summary>
javascript// Custom board views { "views": [ { "name": "Swarm Overview", "type": "board", "groupBy": "status", "filters": ["is:open"], "sort": "priority:desc" }, { "name": "Agent Workload", "type": "table", "groupBy": "assignedAgent", "columns": ["title", "status", "priority", "eta"], "sort": "eta:asc" }, { "name": "Sprint Progress", "type": "roadmap", "dateField": "eta", "groupBy": "milestone" } ] }
javascript// Dashboard with performance widgets { "dashboard": { "widgets": [ { "type": "chart", "title": "Task Completion Rate", "data": "completed-per-day", "visualization": "line" }, { "type": "gauge", "title": "Sprint Progress", "data": "sprint-completion", "target": 100 }, { "type": "heatmap", "title": "Agent Activity", "data": "agent-tasks-per-day" } ] } }
</details>
<details> <summary><strong>Sprint Management</strong></summary>
bash# Manage sprints with swarms npx ruv-swarm github sprint-manage \ --sprint "Sprint 23" \ --auto-populate \ --capacity-planning \ --track-velocity # Track milestone progress npx ruv-swarm github milestone-track \ --milestone "v2.0 Release" \ --update-board \ --show-dependencies \ --predict-completion
bash# Setup agile board npx ruv-swarm github agile-board \ --methodology "scrum" \ --sprint-length "2w" \ --ceremonies "planning,review,retro" \ --metrics "velocity,burndown"
bash# Setup kanban board npx ruv-swarm github kanban-board \ --wip-limits '{ "In Progress": 5, "Review": 3 }' \ --cycle-time-tracking \ --continuous-flow
</details>
<details> <summary><strong>Progress Tracking & Analytics</strong></summary>
bash# Fetch project data PROJECT_DATA=$(gh project item-list $PROJECT_ID --owner @me --format json) # Get issue metrics ISSUE_METRICS=$(echo "$PROJECT_DATA" | jq -r '.items[] | select(.content.type == "Issue")' | \ while read -r item; do ISSUE_NUM=$(echo "$item" | jq -r '.content.number') gh issue view $ISSUE_NUM --json createdAt,closedAt,labels,assignees done) # Generate analytics with swarm npx ruv-swarm github board-analytics \ --project-data "$PROJECT_DATA" \ --issue-metrics "$ISSUE_METRICS" \ --metrics "throughput,cycle-time,wip" \ --group-by "agent,priority,type" \ --time-range "30d" \ --export "dashboard"
bash# Track and visualize progress npx ruv-swarm github board-progress \ --show "burndown,velocity,cycle-time" \ --time-period "sprint" \ --export-metrics # Generate reports npx ruv-swarm github board-report \ --type "sprint-summary" \ --format "markdown" \ --include "velocity,burndown,blockers" \ --distribute "slack,email"
bash# Track board performance npx ruv-swarm github board-kpis \ --metrics '[ "average-cycle-time", "throughput-per-sprint", "blocked-time-percentage", "first-time-pass-rate" ]' \ --dashboard-url # Track team performance npx ruv-swarm github team-metrics \ --board "Development" \ --per-member \ --include "velocity,quality,collaboration" \ --anonymous-option
</details>
<details> <summary><strong>Release Planning</strong></summary>
bash# Plan releases using board data npx ruv-swarm github release-plan-board \ --analyze-velocity \ --estimate-completion \ --identify-risks \ --optimize-scope
</details>
<details> <summary><strong>Multi-Board Synchronization</strong></summary>
bash# Sync across multiple boards npx ruv-swarm github multi-board-sync \ --boards "Development,QA,Release" \ --sync-rules '{ "Development->QA": "when:ready-for-test", "QA->Release": "when:tests-pass" }' # Cross-organization sync npx ruv-swarm github cross-org-sync \ --source "org1/Project-A" \ --target "org2/Project-B" \ --field-mapping "custom" \ --conflict-resolution "source-wins"
</details>
<details> <summary><strong>Issue Dependencies & Epic Management</strong></summary>
bash# Handle issue dependencies npx ruv-swarm github issue-deps 456 \ --resolve-order \ --parallel-safe \ --update-blocking
bash# Coordinate epic-level swarms npx ruv-swarm github epic-swarm \ --epic 123 \ --child-issues "456,457,458" \ --orchestrate
</details>
<details> <summary><strong>Cross-Repository Coordination</strong></summary>
bash# Handle issues across repositories npx ruv-swarm github cross-repo \ --issue "org/repo#456" \ --related "org/other-repo#123" \ --coordinate
</details>
<details> <summary><strong>Team Collaboration</strong></summary>
bash# Distribute work among team npx ruv-swarm github board-distribute \ --strategy "skills-based" \ --balance-workload \ --respect-preferences \ --notify-assignments
bash# Generate standup reports npx ruv-swarm github standup-report \ --team "frontend" \ --include "yesterday,today,blockers" \ --format "slack" \ --schedule "daily-9am"
bash# Coordinate reviews via board npx ruv-swarm github review-coordinate \ --board "Code Review" \ --assign-reviewers \ --track-feedback \ --ensure-coverage
</details>
markdown## 🔄 Integration Task ### Overview [Brief description of integration requirements] ### Objectives - [ ] Component A integration - [ ] Component B validation - [ ] Testing and verification - [ ] Documentation updates ### Integration Areas #### Dependencies - [ ] Package.json updates - [ ] Version compatibility - [ ] Import statements #### Functionality - [ ] Core feature integration - [ ] API compatibility - [ ] Performance validation #### Testing - [ ] Unit tests - [ ] Integration tests - [ ] End-to-end validation ### Swarm Coordination - **Coordinator**: Overall progress tracking - **Analyst**: Technical validation - **Tester**: Quality assurance - **Documenter**: Documentation updates ### Progress Tracking Updates will be posted automatically by swarm agents during implementation. --- 🤖 Generated with Claude Code
markdown## 🐛 Bug Report ### Problem Description [Clear description of the issue] ### Expected Behavior [What should happen] ### Actual Behavior [What actually happens] ### Reproduction Steps 1. [Step 1] 2. [Step 2] 3. [Step 3] ### Environment - Package: [package name and version] - Node.js: [version] - OS: [operating system] ### Investigation Plan - [ ] Root cause analysis - [ ] Fix implementation - [ ] Testing and validation - [ ] Regression testing ### Swarm Assignment - **Debugger**: Issue investigation - **Coder**: Fix implementation - **Tester**: Validation and testing --- 🤖 Generated with Claude Code
markdown## ✨ Feature Request ### Feature Description [Clear description of the proposed feature] ### Use Cases 1. [Use case 1] 2. [Use case 2] 3. [Use case 3] ### Acceptance Criteria - [ ] Criterion 1 - [ ] Criterion 2 - [ ] Criterion 3 ### Implementation Approach #### Design - [ ] Architecture design - [ ] API design - [ ] UI/UX mockups #### Development - [ ] Core implementation - [ ] Integration with existing features - [ ] Performance optimization #### Testing - [ ] Unit tests - [ ] Integration tests - [ ] User acceptance testing ### Swarm Coordination - **Architect**: Design and planning - **Coder**: Implementation - **Tester**: Quality assurance - **Documenter**: Documentation --- 🤖 Generated with Claude Code
markdown<!-- .github/ISSUE_TEMPLATE/swarm-task.yml --> name: Swarm Task description: Create a task for AI swarm processing body: - type: dropdown id: topology attributes: label: Swarm Topology options: - mesh - hierarchical - ring - star - type: input id: agents attributes: label: Required Agents placeholder: "coder, tester, analyst" - type: textarea id: tasks attributes: label: Task Breakdown placeholder: | 1. Task one description 2. Task two description
yaml# .github/workflows/issue-swarm.yml name: Issue Swarm Handler on: issues: types: [opened, labeled, commented] jobs: swarm-process: runs-on: ubuntu-latest steps: - name: Process Issue uses: ruvnet/swarm-action@v1 with: command: | if [[ "${{ github.event.label.name }}" == "swarm-ready" ]]; then npx ruv-swarm github issue-init ${{ github.event.issue.number }} fi
bash# Sync with project board npx ruv-swarm github issue-board-sync \ --project "Development" \ --column-mapping '{ "To Do": "pending", "In Progress": "active", "Done": "completed" }'
bash# Specialized bug handling npx ruv-swarm github bug-swarm 456 \ --reproduce \ --isolate \ --fix \ --test
bash# Feature implementation swarm npx ruv-swarm github feature-swarm 456 \ --design \ --implement \ --document \ --demo
bash# Refactoring swarm npx ruv-swarm github debt-swarm 456 \ --analyze-impact \ --plan-migration \ --execute \ --validate
bash# Diagnose sync problems npx ruv-swarm github board-diagnose \ --check "permissions,webhooks,rate-limits" \ --test-sync \ --show-conflicts
bash# Optimize board performance npx ruv-swarm github board-optimize \ --analyze-size \ --archive-completed \ --index-fields \ --cache-views
bash# Recover board data npx ruv-swarm github board-recover \ --backup-id "2024-01-15" \ --restore-cards \ --preserve-current \ --merge-conflicts
Automatic tracking of:
bash# Analyze swarm performance npx ruv-swarm github issue-metrics \ --issue 456 \ --metrics "time-to-close,agent-efficiency,subtask-completion"
bash# Generate effectiveness report npx ruv-swarm github effectiveness \ --issues "closed:>2024-01-01" \ --compare "with-swarm,without-swarm"
github-pr-workflow - Link issues to pull requests automaticallygithub-release-management - Coordinate release issues and milestonessparc-orchestrator - Complex project coordination workflowssparc-tester - Automated testing workflows for issuesbash# 1. Create feature issue with swarm coordination gh issue create \ --title "Feature: Real-time Collaboration" \ --body "$(cat <<EOF ## Feature: Real-time Collaboration ### Overview Implement real-time collaboration features using WebSockets. ### Objectives - [ ] WebSocket server setup - [ ] Client-side integration - [ ] Presence tracking - [ ] Conflict resolution - [ ] Testing and documentation ### Swarm Coordination This feature will use mesh topology for parallel development. EOF )" \ --label "enhancement,swarm-ready,high-priority" # 2. Initialize swarm and decompose tasks ISSUE_NUM=$(gh issue list --label "swarm-ready" --limit 1 --json number --jq '.[0].number') npx ruv-swarm github issue-init $ISSUE_NUM \ --topology mesh \ --auto-decompose \ --assign-agents "architect,coder,tester" # 3. Add to project board PROJECT_ID=$(gh project list --owner @me --format json | jq -r '.projects[0].id') gh project item-add $PROJECT_ID --owner @me \ --url "https://github.com/$GITHUB_REPOSITORY/issues/$ISSUE_NUM" # 4. Set up automated tracking npx ruv-swarm github board-sync \ --auto-move-cards \ --update-metadata # 5. Monitor progress npx ruv-swarm github issue-progress $ISSUE_NUM \ --auto-update-comments \ --notify-on-completion
bash# Issue Management gh issue create --title "..." --body "..." --label "..." npx ruv-swarm github issue-init <number> npx ruv-swarm github issue-decompose <number> npx ruv-swarm github triage --unlabeled # Project Boards npx ruv-swarm github board-init --project-id <id> npx ruv-swarm github board-sync npx ruv-swarm github board-analytics # Sprint Management npx ruv-swarm github sprint-manage --sprint "Sprint X" npx ruv-swarm github milestone-track --milestone "vX.X" # Analytics npx ruv-swarm github issue-metrics --issue <number> npx ruv-swarm github board-kpis
Last Updated: 2025-10-19 Version: 2.0.0 Maintainer: Claude Code
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,298 | 8,296 | -42% | 1 | 1 | 0% | 2,547 | 8,062 | +217% | 0 | 0 | — |
case-02 | fail→fail | 3,357 | 7,005 | +109% | 1 | 1 | 0% | 547 | 8,352 | +1427% | 0 | 0 | — |
case-03 | fail→fail | 18,680 | 7,992 | -57% | 1 | 1 | 0% | 3,179 | 8,341 | +162% | 0 | 0 | — |
case-04 | fail→pass | 15,247 | 9,324 | -39% | 1 | 1 | 0% | 2,830 | 9,618 | +240% | 0 | 0 | — |
case-05 | fail→pass | 11,860 | 5,063 | -57% | 1 | 1 | 0% | 2,095 | 8,725 | +316% | 0 | 0 | — |
case-06 | pass→pass | 6,025 | 5,263 | -13% | 1 | 1 | 0% | 1,163 | 8,831 | +659% | 0 | 0 | — |
case-07 | fail→pass | 3,377 | 10,635 | +215% | 1 | 1 | 0% | 568 | 9,741 | +1615% | 0 | 0 | — |
case-08 | fail→pass | 11,098 | 2,932 | -74% | 1 | 1 | 0% | 1,914 | 8,313 | +334% | 0 | 0 | — |
case-09 | fail→pass | 7,367 | 2,888 | -61% | 1 | 1 | 0% | 1,300 | 8,319 | +540% | 0 | 0 | — |
case-10 | pass→pass | 12,120 | 8,829 | -27% | 1 | 1 | 0% | 2,355 | 9,429 | +300% | 0 | 0 | — |
case-11 | fail→fail | 12,375 | 8,849 | -28% | 1 | 1 | 0% | 2,205 | 9,533 | +332% | 0 | 0 | — |
case-12 | fail→pass | 8,807 | 5,461 | -38% | 1 | 1 | 0% | 1,387 | 8,683 | +526% | 0 | 0 | — |
case-13 | fail→pass | 13,832 | 2,421 | -82% | 1 | 1 | 0% | 2,426 | 8,200 | +238% | 0 | 0 | — |
case-14 | fail→pass | 7,036 | 2,421 | -66% | 1 | 1 | 0% | 1,232 | 8,202 | +566% | 0 | 0 | — |
case-15 | fail→pass | 9,862 | 8,380 | -15% | 1 | 1 | 0% | 1,450 | 9,246 | +538% | 0 | 0 | — |
case-16 | fail→pass | 8,801 | 2,896 | -67% | 1 | 1 | 0% | 1,608 | 8,292 | +416% | 0 | 0 | — |
case-17 | fail→pass | 14,235 | 2,684 | -81% | 1 | 1 | 0% | 2,577 | 8,242 | +220% | 0 | 0 | — |
case-18 | fail→pass | 8,714 | 2,833 | -67% | 1 | 1 | 0% | 1,466 | 8,218 | +461% | 0 | 0 | — |
case-19 | fail→pass | 27,093 | 7,165 | -74% | 1 | 1 | 0% | 4,935 | 9,085 | +84% | 0 | 0 | — |
case-20 | pass→pass | 14,286 | 12,821 | -10% | 1 | 1 | 0% | 2,530 | 10,163 | +302% | 0 | 0 | — |
case-21 | pass→pass | 4,679 | 5,995 | +28% | 1 | 1 | 0% | 870 | 8,971 | +931% | 0 | 0 | — |
case-22 | pass→fail | 13,316 | 7,353 | -45% | 1 | 1 | 0% | 2,418 | 8,324 | +244% | 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 +55 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.