portfolio-intelligence
Portfolio Intelligence Framework
When This Activates
This skill activates for cross-project strategic questions:
- Comparing approaches across projects
- Finding where patterns exist
- Assessing overall health
- Generating PR descriptions with context
Available Intelligence
Project Overview
pm_portfolio detail=summary
Returns: Total projects, health scores, function counts, feature counts
Health Comparison
Compare code quality across all projects:
- Security issues
- Performance problems
- Dead code
- Duplicates
Health Score Guide:
| Score | Rating | Meaning |
|---|---|---|
| 90-100 | Excellent | Clean, well-maintained |
| 75-89 | Good | Minor issues |
| 60-74 | Fair | Needs attention |
| 40-59 | Poor | Significant tech debt |
| 0-39 | Critical | Major refactoring needed |
Tech Stack Analysis
Detect technologies across projects:
- React, React Native, Next.js
- TypeScript vs JavaScript
- Firebase/Firestore usage
- Framework patterns
Feature Catalog
Find which projects have which features:
- Shared features (appear in multiple projects)
- Feature dependencies
- Implementation status
Session History
Track work patterns:
- Recent sessions by project
- Observation categories (decisions, bugfixes, gotchas)
- Patterns learned
Cross-Project Search
Find code/patterns across all projects:
memory_search_all query="authentication" type=files
memory_search_all query="useAuth" type=functions
Registered Projects
| ID | Name | Type |
|---|---|---|
| gyst | GYST Mobile | React Native |
| gyst-web | GYST Website | Next.js |
| jamelna | Jamelna.com | Next.js |
| smartiegoals | Smartie Goals | Next.js |
| spread-your-ashes | Spread Your Ashes | Next.js |
| codetale | CodeTale | Next.js |
| android-gyst | Android GYST | Android/Kotlin |
| playbook | PlayBook | Next.js |
PR Description Generation
When creating PRs, the system can:
- Detect project context from git root
- Analyze branch changes (commits, files, diff)
- Get file summaries from memory
- Generate description with:
- Summary (2-3 bullet points)
- Detailed changes
- Testing checklist
- Screenshot prompts (if UI)
PR Format
## Summary
- Bullet point 1
- Bullet point 2
## Changes
- Detailed change list
## Testing
- [ ] Test case 1
- [ ] Test case 2
## Screenshots
(Add if UI changes)
Strategic Questions
Use portfolio intelligence for:
"Which project has the best auth implementation?" → Search auth patterns across projects, compare approaches
"Where should I implement feature X?" → Check existing features, identify reuse opportunities
"What tech debt should I prioritize?" → Compare health scores, identify common issues
"How do other projects handle Y?" → Cross-project search for implementations
MCP Tools
pm_portfolio- Get portfolio overviewpm_ask- Ask about priorities and projectsmemory_search_all- Search across all projectsmemory_roadmap- Project task tracking
More from jamelna-apps/claude-dash
cost-tracking
When user mentions "spending", "usage", "tokens", "API cost", "budget", "expensive", or wants to understand Claude API costs. Provides cost awareness and optimization guidance.
11page-cro
When the user mentions "conversion", "CRO", "landing page", "not converting", "bounce rate", "optimize page", or asks about improving page performance.
7session-handoff
When user says "continue", "pick up where we left off", "last time", "previous session", "what were we doing", or wants explicit session continuity. Provides structured context handoff between sessions.
4error-diagnosis
When user encounters "error", "exception", "failed", "stack trace", "crashed", or needs error categorization. Provides structured root cause analysis and prevention strategies.
4code-review
When the user mentions "review", "PR", "pull request", "code review", "check my code", "feedback on", or asks for code quality assessment.
3smart-routing
When deciding which Claude model (Opus/Sonnet/Haiku) to use, or when "route", "which model", "complex task", "multi-file", "architectural", or "deep debugging" is mentioned. Guides quality-first model selection.
3