| name | github-repo-analysis |
| description | Comprehensive GitHub repository analysis for health assessment, monetization opportunities, financial audits, competitive intelligence, and TECHNICAL DRIFT detection. Use when users ask to analyze repositories, audit GitHub portfolios, find revenue opportunities, assess repo health, evaluate monetization readiness, detect spec-vs-implementation gaps, or extract competitive insights from forks. |
GitHub Repository Analysis Skill
Perform comprehensive analysis of GitHub repositories and portfolios, including technical health assessment, technical drift detection, financial valuation, monetization strategy, and competitive intelligence extraction.
🔴 CRITICAL: Always Save Output Files
Every analysis MUST save markdown file(s) to the workspace:
Output Requirements:
├── ALWAYS generate and save .md report files
├── Use descriptive filenames: {RepoName}_{AnalysisType}.md
├── Save to workspace root or user-specified location
├── Include timestamp in report header
└── Confirm file save to user upon completion
Example Output Files:
{RepoName}_MEGA_AUDIT.md- Full comprehensive analysis{RepoName}_TECHNICAL_HEALTH.md- Technical deep-dive{RepoName}_FINANCIAL_AUDIT.md- Revenue and monetization{RepoName}_COMPETITIVE_INTEL.md- Fork and market intelligence{RepoName}_PORTFOLIO_OVERVIEW.md- Multi-repo summary{RepoName}_DRIFT_ANALYSIS.md- Spec vs implementation gaps
Core Capability: Technical Drift Detection
Technical drift is the gap between what documentation/specs claim is complete versus what is actually implemented in code. This skill identifies:
- Tasks marked complete in specs that are actually scaffolded
- Test files that are skeleton-only (detected via file size analysis)
- Infrastructure templates vs. production-ready configurations
- Missing critical components (payment systems, deployments)
- Documentation that overstates implementation status
Drift Detection Methodology
┌─────────────────────────────────────────────────────────────────────────────┐
│ TECHNICAL DRIFT DETECTION PROCESS │
├─────────────────────────────────────────────────────────────────────────────┤
│ │
│ 1. SPEC ANALYSIS 2. CODE VERIFICATION 3. DRIFT SCORING │
│ ────────────────── ──────────────────── ───────────────── │
│ • Read task lists • Verify files exist • Calculate gaps │
│ • Parse completion % • Analyze file sizes • Score by area │
│ • Extract claims • Check implementations • Generate report │
│ • Find [x] markers • Measure code density • Quantify delta │
│ │
│ Evidence Collection: │
│ ─────────────────── │
│ • File sizes (bytes) → implementation depth indicator │
│ • Directory existence → structural completeness │
│ • Code patterns → real logic vs boilerplate │
│ • Test assertions → actual coverage vs skeleton │
│ • Config values → template placeholders vs real secrets │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
File Size Heuristics for Drift Detection
| File Type | Production Size | Scaffolded | Stub/Skeleton |
|---|---|---|---|
| React Component (.tsx) | 3-15 KB | 1-3 KB | < 1 KB |
| API Route (Python) | 2-10 KB | 0.5-2 KB | < 500 bytes |
| E2E Test (.spec.ts) | 2-8 KB | 500-2000 bytes | < 500 bytes |
| Contract Test (.py) | 3-10 KB | 1-3 KB | < 1 KB |
| Worker/Job Handler | 2-6 KB | 0.5-2 KB | < 500 bytes |
| Terraform Module | 1-5 KB | 200-1000 bytes | < 200 bytes |
| Database Model | 1-5 KB | 500-1500 bytes | < 500 bytes |
| Service Class | 2-8 KB | 0.5-2 KB | < 500 bytes |
Drift Scoring Formula
Drift Score = (Claimed Completion % - Verified Completion %)
Where Verified Completion considers:
├── File Existence Weight: 20%
├── File Size Analysis: 30%
├── Implementation Depth: 25%
├── Test Coverage Reality: 15%
└── Infrastructure Readiness: 10%
Interpretation:
├── 0-10% drift → 🟢 Accurate documentation
├── 11-25% drift → 🟡 Minor overstatement
├── 26-40% drift → 🟠 Significant gaps
└── 41%+ drift → 🔴 Major discrepancy
When to Use This Skill
Standard Analysis Triggers
- User wants to analyze their GitHub repositories
- User asks about repository health, completion, or quality
- User wants monetization or revenue analysis
- User asks about financial value of their repos
- User wants competitive intelligence from forks
- User requests portfolio-wide insights
- User mentions "repo audit" or "repository analysis"
- User wants to find hidden money or revenue opportunities
Drift Detection Triggers
- User asks about "technical drift" or spec-vs-implementation gaps
- User questions if claimed completion is real
- User wants honest assessment of project readiness
- Task file shows high completion but repo seems incomplete
- README claims features that may not exist
- User asks "is this actually done?"
- User mentions "documentation may not reflect implementation"
- User wants to verify spec claims
Analysis Types
1. Portfolio Overview Analysis
Analyze ALL original (non-forked) repositories for portfolio-wide health and monetization insights.
Generates:
- Complete repository inventory with status classification
- Portfolio-wide completion and health scores (drift-adjusted)
- Monetization leaderboard ranked by revenue potential
- Technology stack distribution
- Resource allocation recommendations
Drift-Adjusted Metrics:
| Metric | Description | Drift Factor |
|---|---|---|
| Overall Health Score | 0-100 across all categories | Verified via file analysis |
| Claimed Completion | From task/spec files | Raw spec claims |
| Verified Completion | After drift analysis | Reality-adjusted |
| Monetization Readiness | Market readiness | Based on verified state |
2. Single Repository Health Check
Deep dive into one repository's health and monetization readiness.
Generates:
- Code quality and best practices audit
- Security vulnerability assessment
- Documentation completeness review
- Spec-vs-Implementation drift analysis
- Market readiness scoring (drift-adjusted)
- Competitive positioning analysis
Health Categories (with Drift Verification):
| Category | Raw Score | Verified Score | Method |
|---|---|---|---|
| Documentation | 0-100 | 0-100 | Presence + quality check |
| Test Coverage | 0-100 | 0-100 | File count + size analysis |
| Security | 0-100 | 0-100 | Config + dependency scan |
| Dependencies | 0-100 | 0-100 | Version + vulnerability |
| CI/CD | 0-100 | 0-100 | Workflow + secrets check |
3. Technical Drift Analysis (NEW)
Dedicated analysis comparing specifications to actual implementation.
Generates:
- Spec document inventory (tasks.md, README claims, CHANGELOG)
- File-by-file verification with size analysis
- Claimed vs. Verified completion matrix
- Drift percentage by category
- Remediation priority list
- Revised timeline estimates
Drift Report Structure:
╔═══════════════════════════════════════════════════════════════════════════════╗
║ TECHNICAL DRIFT REPORT ║
╠═══════════════════════════════════════════════════════════════════════════════╣
║ ║
║ Spec Source Claimed Verified Drift Status ║
║ ───────────────────────────────────────────────────────────────────────── ║
║ tasks.md 100% 65% 35% 🟠 Significant ║
║ README.md 90% 70% 20% 🟡 Minor ║
║ CHANGELOG.md 100% 80% 20% 🟡 Minor ║
║ ║
║ OVERALL DRIFT: 25% 🟡 ║
║ ║
╚═══════════════════════════════════════════════════════════════════════════════╝
4. Fork Intelligence Analysis
Extract competitive insights from forked public repositories.
Generates:
- Fork inventory with sync status
- Competitor feature matrix
- Pricing intelligence from fork sources
- Technology scouting opportunities
- Partnership potential identification
Fork Classifications:
- 🔬 Learning/Reference
- 🛠️ Active Customization
- 🤝 Contribution Preparation
- 📦 Dependency Vendoring
- 🎯 Competitive Tracking
- 🏚️ Abandoned/Unclear
5. Financial Audit (Drift-Adjusted)
Deep financial analysis with realistic projections based on verified implementation state.
Generates:
- Portfolio value estimation (based on verified completion)
- Revenue stream analysis (adjusted for actual readiness)
- Hidden money discovery
- Market opportunity sizing (TAM/SAM/SOM)
- Extended timelines if drift detected
- Investment requirements (including drift remediation)
Revenue Categories (Drift-Adjusted):
| Category | Claimed Readiness | Verified Readiness | Adjusted Projection |
|---|---|---|---|
| SaaS Subscriptions | 85% | 55% | Delayed 3-4 months |
| API Access Fees | 70% | 45% | Needs implementation |
| Enterprise Licensing | 60% | 30% | Significant work needed |
| Support Contracts | 80% | 70% | Mostly ready |
6. Mega Audit (Comprehensive + Drift-Aware)
Ultimate combined technical + financial + strategic analysis with full drift assessment.
Includes All Sections:
- Executive Command Center (Drift-Adjusted Scores)
- Technical Drift Analysis Section
- Complete Repository Inventory
- Technical Health Deep Dive
- Best Practices & Modernization
- Community & Contributor Intelligence
- Financial Deep Dive (Realistic Projections)
- Financial Projections & Modeling
- Monetization Intelligence
- Strategic Recommendations
- Detailed Per-Repo Appendix
- Fork Intelligence & Insights
Report Structure
Executive Dashboard (Drift-Aware)
╔══════════════════════════════════════════════════════════════════════════════════╗
║ PORTFOLIO COMMAND CENTER ║
║ ⚠️ DRIFT-ADJUSTED ASSESSMENT ║
╠══════════════════════════════════════════════════════════════════════════════════╣
║ ║
║ TOTAL REPOS: ____ ║
║ CLAIMED HEALTH: ____/100 [████████░░] (from specs) ║
║ VERIFIED HEALTH: ____/100 [██████░░░░] (after drift analysis) ║
║ DRIFT FACTOR: ____% [████░░░░░░] ║
║ MONETIZATION READY: ____% [█████░░░░░] (based on verified state) ║
║ 💰 12-MONTH POTENTIAL: $______________ (adjusted for completion work) ║
║ ║
╚══════════════════════════════════════════════════════════════════════════════════╝
Drift Analysis Matrix
╔═══════════════════════════════════════════════════════════════════════════════════╗
║ SPEC vs IMPLEMENTATION REALITY ║
╠═══════════════════════════════════════════════════════════════════════════════════╣
║ ║
║ Component Claimed Files Avg Size Verified Drift ║
║ ───────────────────────────────────────────────────────────────────────────── ║
║ Frontend Components 100% 18 4.2 KB 85% 15% 🟢 ║
║ API Routes 100% 12 5.8 KB 90% 10% 🟢 ║
║ Database Models 100% 10 1.8 KB 95% 5% 🟢 ║
║ E2E Tests 100% 6 1.2 KB 45% 55% 🔴 ║
║ Workers 100% 5 1.5 KB 50% 50% 🔴 ║
║ Infrastructure 100% 8 0.8 KB 35% 65% 🔴 ║
║ ───────────────────────────────────────────────────────────────────────────── ║
║ OVERALL 100% 59 2.8 KB 67% 33% 🟠 ║
║ ║
╚═══════════════════════════════════════════════════════════════════════════════════╝
Health Heatmap (Claimed vs Verified)
│ Docs │ Tests │ Security │ Deps │ CI/CD │ OVERALL │
────────────────┼───────┼───────┼──────────┼───────┼───────┼─────────┤
Claimed │ 100 │ 90 │ 95 │ 100 │ 80 │ 93 │
Verified │ 85 │ 55 │ 80 │ 90 │ 45 │ 71 │
Drift │ 15% │ 39% │ 16% │ 10% │ 44% │ 24% │
Legend: 🟢 0-15% drift | 🟡 16-30% | 🟠 31-45% | 🔴 46%+
Revenue Projections (Drift-Adjusted)
Revenue by Type (with Timeline Adjustments):
┌────────────────────────────────────────────────────────────────────────────┐
│ 💳 SaaS │██████████░░░░░░░░░░░░░░│ $___,___/yr (+ 4 mo) │
│ 🔌 API Fees │████████░░░░░░░░░░░░░░░░│ $___,___/yr (+ 6 mo) │
│ 📜 Licensing │██████░░░░░░░░░░░░░░░░░░│ $___,___/yr (+ 8 mo) │
└────────────────────────────────────────────────────────────────────────────┘
Timeline adjustments based on verified implementation state
Priority Matrix (Drift Remediation Included)
HIGH IMPACT
│
┌───────────────────┼───────────────────┐
│ QUICK WINS │ BIG BETS │
│ (Do First) │ (Plan For) │
│ │ │
│ • Fix skeleton │ • Complete │
│ tests │ workers │
│ • Add real │ • Production │
│ assertions │ deployment │
LOW ──────┼───────────────────┼───────────────────┼────── HIGH
EFFORT │ FILL-INS │ MONEY PITS │ EFFORT
│ (Delegate) │ (Avoid) │
│ │ │
│ • Doc polish │ • Major rewrites │
│ • Minor gaps │ • Unused features │
└───────────────────┼───────────────────┘
LOW IMPACT
Step-by-Step Process
Step 1: Identify Analysis Scope
- Confirm GitHub username or organization
- Determine if analyzing single repo or entire portfolio
- Clarify focus areas (health, financial, competitive, drift, or all)
- Check for spec files (tasks.md, CHANGELOG, README claims)
Step 2: Gather Repository Data
- Fetch repository list and metadata
- Identify original vs forked repositories
- Collect stars, forks, issues, PR counts
- Note last update dates and activity levels
- Identify spec/task files for drift analysis
Step 3: Perform Drift Analysis (if applicable)
- Read task/spec files and extract completion claims
- List all files that should exist per specs
- Verify file existence and measure sizes
- Calculate drift percentages by category
- Generate drift-adjusted scores
Step 4: Assess Technical Health
- Review documentation presence and quality
- Check for CI/CD pipelines
- Identify dependency versions and vulnerabilities
- Evaluate test coverage indicators (with size verification)
- Check for security policies
- Apply drift adjustments to all scores
Step 5: Analyze Financial Potential
- Estimate codebase value (LOC × industry rate)
- Identify monetization-ready features
- Research competitor pricing
- Calculate TAM/SAM/SOM for each product
- Project revenue streams
- Adjust timelines based on drift remediation needs
Step 6: Extract Competitive Intelligence
- Analyze forked repositories separately
- Identify features in forks worth adopting
- Research upstream project funding/traction
- Map competitive landscape
- Find partnership opportunities
Step 7: Generate Reports & Save Files
- Structure reports with drift-aware dashboards
- Include visual charts and progress indicators
- Per-repository appendix when needed
- ALWAYS save .md files to workspace
- Confirm file saves to user
Step 8: Recommend Actions
- Prioritize by impact and effort
- Include drift remediation in action items
- Assign realistic timeline with drift buffer
- Calculate expected ROI
- Identify quick wins for immediate action
- Create strategic roadmap
Output File Requirements
Mandatory File Saves
Every analysis MUST produce saved markdown files:
| Analysis Type | Primary Output File | Additional Files |
|---|---|---|
| Mega Audit | {Repo}_MEGA_AUDIT.md |
All 5 below |
| Technical Health | {Repo}_TECHNICAL_HEALTH.md |
- |
| Financial Audit | {Repo}_FINANCIAL_AUDIT.md |
- |
| Competitive Intel | {Repo}_COMPETITIVE_INTEL.md |
- |
| Portfolio Overview | {Repo}_PORTFOLIO_OVERVIEW.md |
- |
| Drift Analysis | {Repo}_DRIFT_ANALYSIS.md |
- |
File Naming Convention
{RepositoryName}_{AnalysisType}.md
Examples:
├── MyApp_MEGA_AUDIT.md
├── MyApp_TECHNICAL_HEALTH.md
├── MyApp_DRIFT_ANALYSIS.md
├── MyApp_FINANCIAL_AUDIT.md
└── {UserName}_PORTFOLIO_OVERVIEW.md
File Structure Template
# {Icon} {Repo Name} — {Analysis Type}
## {Subtitle}
**Generated:** {Date} | **Repository:** `{owner}/{repo}`
---
{Dashboard/Command Center}
---
## Section 1: ...
## Section 2: ...
---
*Report generated by GitHub Repository Analyst Agent*
*Analysis Date: {Date}*
Example Input
"Analyze all repositories for username octocat and give me the mega audit"
Example Output Structure
- Executive Command Center (drift-adjusted dashboard)
- Technical Drift Analysis
- Repository Inventory (table of all repos)
- Health Scorecard Matrix (claimed vs verified)
- Completion Status (with drift indicators)
- Security Posture Assessment
- Financial Deep Dive (timeline-adjusted)
- Monetization Leaderboard (based on verified state)
- Fork Intelligence (competitive insights)
- Strategic Recommendations (including remediation)
- Per-Repository Appendix (detailed breakdowns)
- Saved files confirmation
Key Formulas
Drift Calculation
Drift % = (Claimed Completion - Verified Completion) / Claimed Completion × 100
Verified Completion = Σ(Category Weight × Category Score)
Where Category Score = Files Exist × Size Score × Implementation Depth
Size Score Calculation
Size Score = min(1.0, Actual Size / Expected Minimum Size)
Example: E2E test file
- Expected Minimum: 2000 bytes
- Actual Size: 800 bytes
- Size Score: 800/2000 = 0.4 (40%)
Asset Valuation (Drift-Adjusted)
Raw Codebase Value = Lines of Code × Industry Rate ($50-150/LOC)
Completion Factor = Verified Completion % (not claimed)
Adjusted Value = Raw Value × Completion Factor
Revenue Projections (Drift-Adjusted)
Time to Revenue = Base Estimate + (Drift % × Remediation Factor)
Where Remediation Factor = 1-3 months per 20% drift
SaaS MRR = Addressable Users × Conversion Rate × ARPU
Adjusted Timeline = Original + Drift Remediation Time
Health Scoring (Verified)
Claimed Health = (Docs + Tests + Security + Deps + CI/CD) / 5
Verified Health = Claimed Health × (1 - Drift Factor)
Monetization Readiness = Verified Features / Required Features
Best Practices
- Always run drift analysis on repos with task/spec files
- Verify file sizes before trusting completion claims
- Separate claimed vs verified scores in all dashboards
- Use visual indicators (🟢🟡🟠🔴) for drift severity
- Adjust timelines based on drift remediation needs
- Provide specific dollar estimates adjusted for verified state
- Include effort estimates for drift remediation
- Rank by verified priority, not claimed priority
- Generate ASCII charts with claimed vs verified comparison
- ALWAYS save markdown files - never just display in chat
- Confirm file saves to user upon completion
- Highlight quick drift wins (skeleton tests, missing configs)
- Identify blocking gaps (payment systems, deployments)
Hand-off Triggers
To Implementation Planning Agent
When drift analysis reveals significant gaps, hand off to create remediation plan:
- Drift > 25% in any category
- Critical missing components identified
- Timeline extensions needed
To Research Agent
When competitive intelligence needs deeper market analysis:
- Fork sources need pricing research
- TAM/SAM/SOM needs validation
- Competitor features need verification
To Code Generation Agent
When drift remediation requires code:
- Skeleton tests need real assertions
- Stub implementations need completion
- Missing configurations need creation
SubAgent Invocation
This skill can be invoked via subAgent with:
Prompt: "Analyze the repository {owner}/{repo} for technical health, monetization
potential, and technical drift. Generate comprehensive audit reports and save
all results to markdown files."
Description: "GitHub repo analysis with drift detection"
Agent: "repo-analyst"
Resources
This skill draws from these analysis frameworks:
- Portfolio-wide health assessment methodology
- Technical drift detection heuristics
- File size-based implementation verification
- Fork-based competitive intelligence extraction
- SaaS and API monetization modeling
- Market sizing (TAM/SAM/SOM) frameworks
- Repository valuation formulas
- DevOps maturity models