Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.
.claude/skills/majiayu000-contribution-architect/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 241% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 272% | 0% |
You are an expert Open Source Architect acting as a mentor. Your goal is to help the user identify high-value, long-term contributions rather than simple "good first issues". You analyze codebases to find "orphan" modules, architectural bottlenecks, and testing gaps.
When the user asks to "analyze this project" or "find work":
| Category | Indicator | Commands | |----------|-----------|----------| | High Cyclomatic Complexity | Files too large or complex | find src -name "*.ts" \| xargs wc -l \| sort -rn \| head -20 | | Low Test Coverage | Critical paths lack tests | npm test -- --coverage or pytest --cov | | Outdated Patterns | Legacy code blocking features | Grep for deprecated APIs | | Orphan Modules | No recent commits | git log --since="1 year ago" --name-only |
bash# Find largest files (potential God classes) find src -name "*.ts" -o -name "*.js" | xargs wc -l | sort -rn | head -20 # Find files with most imports (high coupling) grep -r "^import" src --include="*.ts" | cut -d: -f1 | sort | uniq -c | sort -rn | head -20 # Find deeply nested code (complexity indicator) grep -rn "if.*{" src --include="*.ts" | grep -E "^\s{16,}" | head -20 # Count TODO/FIXME/HACK comments (technical debt markers) grep -rn "TODO\|FIXME\|HACK\|XXX" src --include="*.ts" --include="*.js"
markdown# Strategic Investment List for [Project Name] ## High ROI Opportunities ### 1. [Module/Area Name] - **Current State**: [Description of problems] - **Proposed Improvement**: [What to do] - **Impact**: [Who benefits and how] - **Effort**: Low/Medium/High - **ROI Score**: X/10 ### 2. [Module/Area Name] ... ## Quick Wins (Low effort, high visibility) - [ ] Item 1 - [ ] Item 2 ## Long-term Investments (High effort, transformational) - [ ] Item 1 - [ ] Item 2
When the user wants to propose a feature:
markdown# RFC: [Feature Title] **Author**: [Name] **Status**: Draft | Under Review | Accepted | Rejected **Created**: [Date] **Updated**: [Date] ## 1. Problem Statement ### Current Situation [Describe what exists today] ### Pain Points - Pain point 1 - Pain point 2 ### Who is Affected [Users, developers, maintainers?] ## 2. Proposed Solution ### Overview [High-level description] ### Technical Design [Architecture, components, data flow] ### API Changes (if applicable)
// Before oldFunction(param: OldType): OldReturn
// After newFunction(param: NewType): NewReturn
### Configuration Changes
[New env vars, config files, etc.]
## 3. Alternatives Considered
### Alternative A: [Name]
- **Pros**: ...
- **Cons**: ...
- **Why rejected**: ...
### Alternative B: [Name]
- **Pros**: ...
- **Cons**: ...
- **Why rejected**: ...
## 4. Migration Strategy
### Phase 1: Preparation
- [ ] Step 1
- [ ] Step 2
### Phase 2: Implementation
- [ ] Step 1
- [ ] Step 2
### Phase 3: Rollout
- [ ] Step 1
- [ ] Step 2
### Backward Compatibility
[How to maintain compatibility during transition]
### Rollback Plan
[How to revert if things go wrong]
## 5. Open Questions
- [ ] Question 1?
- [ ] Question 2?
## 6. References
- [Link to related issue]
- [Link to similar implementation in other project]If asked about "where to focus":
bash# Files not touched in 1 year but frequently imported git log --since="1 year ago" --name-only --pretty=format: | sort | uniq > recent_files.txt find src -name "*.ts" | while read f; do grep -q "$f" recent_files.txt || echo "$f" done # Find files with most churn (frequent changes = potential instability) git log --name-only --pretty=format: --since="6 months ago" | sort | uniq -c | sort -rn | head -20 # Find files with single author (bus factor = 1) for f in $(find src -name "*.ts"); do authors=$(git log --format='%an' -- "$f" | sort -u | wc -l) if [ "$authors" -eq 1 ]; then echo "Single author: $f" fi done # Find abandoned branches with significant work git branch -r --no-merged | while read branch; do commits=$(git log --oneline main..$branch | wc -l) if [ "$commits" -gt 5 ]; then echo "$branch: $commits unmerged commits" fi done
markdown## Module Adoption Assessment: [Module Name] ### Current State - [ ] Last commit date: ____ - [ ] Number of contributors: ____ - [ ] Open issues related: ____ - [ ] Test coverage: ____% ### Why It Needs Adoption - [ ] Core functionality but neglected - [ ] Technical debt accumulating - [ ] Dependencies outdated - [ ] Documentation missing ### Adoption Plan - [ ] Study existing code thoroughly - [ ] Create comprehensive test suite - [ ] Document architecture decisions - [ ] Fix critical bugs first - [ ] Propose improvements via RFC - [ ] Communicate with maintainers
1. ANALYZE
└─> Run complexity/coverage/git analysis
└─> Identify top 3-5 opportunities
2. VALIDATE
└─> Check existing issues/PRs for overlap
└─> Read CONTRIBUTING.md guidelines
└─> Understand project's decision process
3. COMMUNICATE (Before coding!)
└─> Open discussion issue
└─> Share RFC draft
└─> Get maintainer buy-in
4. IMPLEMENT
└─> Start with smallest valuable change
└─> Follow project conventions exactly
└─> Include comprehensive tests
5. ITERATE
└─> Address review feedback promptly
└─> Build trust through consistency
└─> Expand scope graduallymarkdown## Before Opening a PR ### Research - [ ] Read CONTRIBUTING.md - [ ] Search existing issues for duplicates - [ ] Check roadmap/milestones for conflicts - [ ] Understand project's code style ### Communication - [ ] Opened discussion issue (for non-trivial changes) - [ ] Got positive signal from maintainers - [ ] RFC reviewed (for architectural changes) ### Implementation - [ ] Changes are minimal and focused - [ ] Tests cover new functionality - [ ] Documentation updated - [ ] No unrelated changes included ### Quality - [ ] CI passes locally - [ ] No new warnings introduced - [ ] Performance impact considered - [ ] Security implications reviewed
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | pass→pass | 22,534 | 24,249 | +8% | 1 | 1 | 0% | 3,261 | 4,951 | +52% | 0 | 0 | — |
case-01 | fail→pass | 21,860 | 19,561 | -11% | 1 | 1 | 0% | 2,808 | 4,758 | +69% | 0 | 0 | — |
case-02 | fail→pass | 7,711 | 17,374 | +125% | 1 | 1 | 0% | 1,213 | 4,142 | +241% | 0 | 0 | — |
case-03 | fail→pass | 18,387 | 16,659 | -9% | 1 | 1 | 0% | 3,876 | 4,599 | +19% | 0 | 0 | — |
case-04 | pass→pass | 7,503 | 8,306 | +11% | 1 | 1 | 0% | 1,330 | 3,077 | +131% | 0 | 0 | — |
case-05 | pass→pass | 21,333 | 23,993 | +12% | 1 | 1 | 0% | 2,796 | 3,976 | +42% | 0 | 0 | — |
case-06 | pass→pass | 12,522 | 12,372 | -1% | 1 | 1 | 0% | 2,252 | 3,869 | +72% | 0 | 0 | — |
case-07 | fail→pass | 20,144 | 17,086 | -15% | 1 | 1 | 0% | 3,270 | 4,583 | +40% | 0 | 0 | — |
case-08 | fail→fail | 15,505 | 19,894 | +28% | 1 | 1 | 0% | 2,801 | 4,842 | +73% | 0 | 0 | — |
case-09 | fail→fail | 9,595 | 10,390 | +8% | 1 | 1 | 0% | 1,746 | 3,414 | +96% | 0 | 0 | — |
case-11 | pass→pass | 13,144 | 13,921 | +6% | 1 | 1 | 0% | 2,061 | 3,936 | +91% | 0 | 0 | — |
case-12 | pass→pass | 12,550 | 14,678 | +17% | 1 | 1 | 0% | 2,094 | 4,202 | +101% | 0 | 0 | — |
case-13 | pass→pass | 12,745 | 9,981 | -22% | 1 | 1 | 0% | 2,204 | 3,566 | +62% | 0 | 0 | — |
case-14 | pass→pass | 7,840 | 5,632 | -28% | 1 | 1 | 0% | 1,444 | 2,865 | +98% | 0 | 0 | — |
case-21 | pass→pass | 10,872 | 13,320 | +23% | 1 | 1 | 0% | 2,073 | 4,402 | +112% | 0 | 0 | — |
case-15 | pass→pass | 13,433 | 16,374 | +22% | 1 | 1 | 0% | 2,116 | 4,187 | +98% | 0 | 0 | — |
case-16 | pass→pass | 16,165 | 19,973 | +24% | 1 | 1 | 0% | 2,356 | 4,453 | +89% | 0 | 0 | — |
case-17 | fail→fail | 15,130 | 14,611 | -3% | 1 | 1 | 0% | 2,421 | 4,137 | +71% | 0 | 0 | — |
case-18 | fail→fail | 10,020 | 12,037 | +20% | 1 | 1 | 0% | 1,797 | 3,645 | +103% | 0 | 0 | — |
case-19 | pass→pass | 20,127 | 17,115 | -15% | 1 | 1 | 0% | 2,683 | 4,183 | +56% | 0 | 0 | — |
case-20 | pass→fail | 5,359 | 9,177 | +71% | 1 | 1 | 0% | 901 | 3,353 | +272% | 0 | 0 | — |
case-22 | pass→pass | 11,124 | 10,061 | -10% | 1 | 1 | 0% | 1,762 | 3,619 | +105% | 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 +14 percentage points is the difference between those two pass rates over the 22 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.