Skip to main content
project-analyzer Automated brownfield codebase analysis with weighted keyword scoring, three-stream analysis, and design pattern recognition. Detects project type, frameworks, dependencies, architecture patterns, and generates comprehensive project profile.
インストールへ移動 Skills Marketplace コミュニティが作成したAIスキルを発見・探索
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/oimiragieo/agent-studio --skill project-analyzerコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Zipをダウンロード ダウンロード中... name project-analyzer description Automated brownfield codebase analysis with weighted keyword scoring, three-stream analysis, and design pattern recognition. Detects project type, frameworks, dependencies, architecture patterns, and generates comprehensive project profile. version 1.1.0 model sonnet invoked_by both user_invocable true tools ["Read","Glob","Grep","Bash"] best_practices ["Detect project root from package managers and manifest files","Identify frameworks from dependencies and directory structure","Generate comprehensive file statistics and language breakdown","Map component relationships and architecture patterns","Validate output against project-analysis.schema.json","Execute in < 30 seconds for typical projects (< 10k files)"] error_handling graceful streaming supported executable .claude/tools/analysis/project-analyzer/analyzer.mjs test_suite null output_schema .claude/schemas/project-analysis.schema.json verified false lastVerifiedAt "2026-02-19T05:29:09.098Z" source builtin trust_score 100 provenance_sha 641607b45a34f39a
References (archive): SCAFFOLD_SKILLS_ARCHIVE_MAP.md — ProjectAnalyzer monorepo/service detection from Auto-Claude-develop analysis/analyzers.
Project Analyzer - Automated brownfield codebase analysis for rapid project onboarding and understanding.
- Detecting project type (frontend, backend, fullstack, library, cli, mobile, monorepo)
- Identifying frameworks and libraries from manifests and structure
- Generating file statistics and language breakdown
- Mapping component relationships and module structure
- Detecting architecture patterns (MVC, layered, microservices, etc.)
- Analyzing dependency health and outdated packages
- Identifying code quality indicators (linting, testing, type safety)
- Detecting technical debt and anti-patterns
- Generating prioritized improvement recommendations
Step 1: Identify Project Root
Locate project root by finding manifest files:
Search for package manager files :
package.json (Node.js/JavaScript/TypeScript)requirements.txt, pyproject.toml, setup.py (Python)go.mod (Go)Cargo.toml (Rust)pom.xml, build.gradle (Java/Maven/Gradle)composer.json (PHP)
Identify project root :
Directory containing primary package manager file
Handle monorepos (multiple package.json files)
Detect workspace configuration
Validate project root :
Check for .git directory
Verify source code directories exist
Ensure manifest files are parsable
Step 2: Detect Project Type
Classify project based on manifest files and directory structure:
Frontend Projects :
Indicators: React, Vue, Angular, Svelte dependencies
Directory: src/components/, public/, assets/
Frameworks: Next.js, Nuxt.js, Gatsby, Vite
Backend Projects :
Indicators: Express, FastAPI, Django, Flask, Gin dependencies
Directory: routes/,
**Performance Requirements**:
**Integration with Conductor**:
- Provides automated project discovery
- Eliminates manual context gathering
- Enables 80% faster brownfield onboarding
- Feeds project context to chat interface
**Programmatic Usage**:
controllers/
models/
api/
Frameworks: Next.js API routes, FastAPI, Express
Fullstack Projects :
Indicators: Both frontend and backend frameworks
Directory: Combined frontend + backend structure
Frameworks: Next.js, Remix, SvelteKit, Nuxt.js
Library/Package Projects :
Indicators: No application-specific directories
Files: index.ts, lib/, dist/, build/
Manifests: library field in package.json
CLI Projects :
Indicators: bin field in package.json
Files: CLI entry points, command parsers
Dependencies: Commander, Yargs, Inquirer
Mobile Projects :
Indicators: React Native, Flutter, Ionic dependencies
Files: android/, ios/, mobile/
Frameworks: React Native, Expo, Flutter
Monorepo Projects :
Indicators: workspaces in package.json, pnpm-workspace.yaml
Structure: Multiple packages in subdirectories
Tools: Turborepo, Nx, Lerna
Microservices Projects :
Indicators: Multiple service directories
Files: docker-compose.yml, service configs
Structure: Service-based organization
Step 3: Framework Detection Identify frameworks from manifest files and imports:
Read package.json dependencies (Node.js):
Parse dependencies and devDependencies
Detect framework versions
Categorize by type (framework, ui-library, testing, etc.)
Read requirements.txt (Python):
Parse Python dependencies
Detect FastAPI, Django, Flask
Identify version constraints
Analyze imports (optional deep scan):
Scan source files for import statements
Detect used vs declared dependencies
Identify framework-specific patterns
Framework Categories :
Framework : React, Next.js, FastAPI, ExpressUI Library : Material-UI, Ant Design, Chakra UIState Management : Redux, Zustand, PiniaTesting : Jest, Vitest, Cypress, PlaywrightBuild Tool : Vite, Webpack, Rollup, esbuildDatabase : Prisma, TypeORM, SQLAlchemyORM : Prisma, Sequelize, MongooseAPI : tRPC, GraphQL, RESTAuth : NextAuth, Auth0, ClerkLogging : Winston, Pino, BunyanMonitoring : Sentry, Datadog, New Relic
Confidence Scoring :
1.0 : Framework listed in dependencies0.8 : Framework detected from imports0.6 : Framework inferred from structure
Step 4: File Statistics Generate quantitative project statistics:
Count files by type :
Use glob patterns for common extensions
Exclude: node_modules/, .git/, dist/, build/
Group by language/file type
Count lines of code :
Read source files and count lines
Exclude empty lines and comments (optional)
Calculate total LOC per language
Identify largest files :
Track file sizes (line count)
Report top 10 largest files
Flag files > 1000 lines (violates micro-service principle)
Calculate averages :
Average file size (lines)
Average directory depth
Files per directory
Language Detection :
Map extensions to languages:
.ts, .tsx → TypeScript.js, .jsx → JavaScript.py → Python.go → Go.rs → Rust.java → Java.md → Markdown.json → JSON.yaml, .yml → YAML
Step 5: Structure Analysis Analyze project structure and architecture:
Identify root directories :
Classify directories by purpose:
source : src/, app/, lib/tests : test/, __tests__/, cypress/config : config/, .config/docs : docs/, documentation/build : dist/, build/, out/scripts : scripts/, bin/assets : assets/, static/, public/
Detect entry points :
Main entry: index.ts, main.py, app.py
App entry: app.ts, server.ts, app/page.tsx
Handler: handler.ts, lambda.ts
CLI: cli.ts, bin/
Detect architecture pattern :
MVC : models/, views/, controllers/Layered : presentation/, business/, data/Hexagonal : domain/, application/, infrastructure/Microservices : Multiple service directoriesModular : Feature-based organizationFlat : All files in src/
Detect module system :
Check package.json for "type": "module" (ESM)
Scan for import/export (ESM) vs require (CommonJS)
Identify mixed module systems
Step 6: Dependency Analysis Analyze dependency health:
Count dependencies :
Production dependencies
Development dependencies
Total dependency count
Check for outdated packages (optional):
Run npm outdated or equivalent
Parse output for outdated packages
Identify major version updates (breaking changes)
Security scan (optional):
Run npm audit or equivalent
Identify vulnerabilities by severity
Flag critical security issues
Step 7: Code Quality Indicators Detect code quality tooling:
Linting Configuration :
Detect: .eslintrc.json, eslint.config.js, ruff.toml
Tool: ESLint, Ruff, Flake8, Pylint
Run linter if configured (optional)
Formatting Configuration :
Detect: .prettierrc, pyproject.toml (Black/Ruff)
Tool: Prettier, Black, Ruff
Testing Framework :
Detect: Jest, Vitest, Pytest, Cypress
Count test files
Check for coverage configuration
Type Safety :
Detect TypeScript: tsconfig.json
Check strict mode: "strict": true
Detect Python typing: mypy, pyright
Step 8: Pattern Detection Identify common patterns and anti-patterns:
Good Practices :
Modular component structure
Comprehensive test coverage
TypeScript strict mode enabled
CI/CD configuration present
Anti-Patterns :
Large files (> 1000 lines)
Missing tests
Outdated dependencies
No linting configuration
Neutral Patterns :
Specific architecture choices
Framework-specific patterns
Step 9: Technical Debt Analysis Calculate technical debt score:
Debt Indicators :
Outdated Dependencies : Count outdated packagesMissing Tests : Low test file ratioDead Code : Unused imports/exports (optional)Complexity : Large files, deep nestingDocumentation : Missing README, docsSecurity : Known vulnerabilitiesPerformance : Bundle size, load time
Debt Score (0-100):
0-20: Excellent health
21-40: Good health, minor issues
41-60: Moderate debt, needs attention
61-80: High debt, refactoring recommended
81-100: Critical debt, major overhaul needed
Remediation Effort :
Trivial : < 1 hourMinor : 1-4 hoursModerate : 1-3 daysMajor : 1-2 weeksMassive : > 2 weeks
Step 10: Generate Recommendations Create prioritized improvement recommendations:
Categorize Recommendations :
Security : Critical vulnerabilities, outdated authPerformance : Bundle optimization, lazy loadingMaintainability : Refactor large files, add testsTesting : Increase coverage, add E2E testsDocumentation : Add README, API docsArchitecture : Improve modularity, separation of concernsDependencies : Update packages, remove unused
Prioritize by Impact :
P0 : Critical security, blocking productionP1 : High impact, affects reliabilityP2 : Medium impact, improves qualityP3 : Low impact, nice-to-have
Estimate Effort and Impact :
Effort: trivial, minor, moderate, major, massive
Impact: low, medium, high, critical
Step 11: Validate Output Validate analysis output against schema:
Schema Validation :
Validate against project-analysis.schema.json
Ensure all required fields present
Check data types and formats
Output Metadata :
Analyzer version
Analysis duration (ms)
Files analyzed count
Files skipped count
Errors encountered
Target : < 30 seconds for typical projects (< 10k files)Optimization :
Skip large directories: node_modules/, .git/, dist/
Use parallel file processing
Cache results for incremental analysis
Limit deep scans to essential files
Use streaming for large file counts
Integration with Other Skills :
rule-selector : Auto-select rules based on detected frameworksrepo-rag : Semantic search for architectural patternsdependency-analyzer : Deep dependency analysis
Progressive Disclosure : Start with manifest analysis, add deep scans if neededPerformance First : Skip expensive operations for large projectsFail Gracefully : Handle missing files, parse errorsValidate Output : Always validate against schemaCache Results : Store analysis output for reuseIncremental Updates : Re-analyze only changed files
</best_practices>
node .claude/tools/analysis/project-analyzer/analyzer.mjs
node .claude/tools/analysis/project-analyzer/analyzer.mjs /path/to/project
node .claude/tools/analysis/project-analyzer/analyzer.mjs --output .claude/context/artifacts/project-analysis.json
# Analyze current project
Analyze this project
# Generate comprehensive analysis
Perform full project analysis and save to artifacts
# Quick analysis (manifest only)
Quick project type detection
<formatting_example>
Sample Output (.claude/context/artifacts/project-analysis.json):
{
"analysis_id" : "analysis-llm-rules-20250115" ,
"project_type" : "fullstack" ,
"analyzed_at" : "2025-01-15T10:30:00.000Z" ,
"project_root" : "C:\\dev\\projects\\LLM-RULES" ,
"stats" : {
"total_files" : 1243 ,
"total_lines" : 125430 ,
"languages" : {
"JavaScript" : 45230 ,
"TypeScript" : 38120 ,
"Markdown" : 25680 ,
"JSON" : 12400 ,
"YAML" : 4000
} ,
"file_types" : {
".js" : 234 ,
".mjs" : 156 ,
".ts" : 89 ,
".md" : 312 ,
".json" : 145
} ,
"directories" : 87 ,
"avg_file_size_lines" : 101 ,
"largest_files" : [
{
"path" : ".claude/tools/enforcement-gate.mjs" ,
"lines" : 1520
}
]
} ,
"frameworks" : [
{
"name" : "nextjs" ,
"version" : "14.0.0" ,
"category" : "framework" ,
"confidence" : 1.0 ,
"source" : "package.json"
} ,
{
"name" : "react" ,
"version" : "18.2.0" ,
"category" : "framework" ,
"confidence" : 1.0 ,
"source" : "package.json"
}
] ,
"structure" : {
"root_directories" : [
{
"name" : ".claude" ,
"purpose" : "config" ,
"file_count" : 543
} ,
{
"name" : "conductor-main" ,
"purpose" : "source" ,
"file_count" : 234
}
] ,
"entry_points" : [
{
"path" : "conductor-main/src/index.ts" ,
"type" : "main"
}
] ,
"architecture_pattern" : "modular" ,
"module_system" : "esm"
} ,
"dependencies" : {
"production" : 45 ,
"development" : 23
} ,
"code_quality" : {
"linting" : {
"configured" : true ,
"tool" : "eslint"
} ,
"formatting" : {
"configured" : true ,
"tool" : "prettier"
} ,
"testing" : {
"framework" : "vitest" ,
"test_files" : 89 ,
"coverage_configured" : true } ,
"type_safety" : {
"typescript" : true ,
"strict_mode" : true }
} ,
"tech_debt" : {
"score" : 35 ,
"indicators" : [
{
"category" : "complexity" ,
"severity" : "medium" ,
"description" : "3 files exceed 1000 lines" ,
"remediation_effort" : "moderate"
}
]
} ,
"recommendations" : [
{
"priority" : "P1" ,
"category" : "maintainability" ,
"title" : "Refactor large files" ,
"description" : "Break down files > 1000 lines into smaller modules" ,
"effort" : "moderate" ,
"impact" : "high"
}
] ,
"metadata" : {
"analyzer_version" : "1.0.0" ,
"analysis_duration_ms" : 2340 ,
"files_analyzed" : 1243 ,
"files_skipped" : 3420 ,
"errors" : [ ]
}
}
Smart Categorization Scoring (Inspired by Skill_Seekers smart_categorize) When classifying files, directories, or components into categories, use weighted keyword scoring instead of simple string matching to prevent false positives:
Signal Source Score Weight Example File path/URL 3 points /api/routes/ matches "API" categoryFile/class name 2 points AuthService.ts matches "Authentication"File content/imports 1 point import express matches "Backend"
Threshold : Require 2+ total points before assigning a category. Falls back to "other" if no category scores above threshold. This prevents weak single-signal matches from misclassifying components.
Category keywords (extend per project type):
API : route, endpoint, controller, handler, middleware, api, rest, graphqlAuth : auth, login, session, jwt, oauth, token, credential, permissionDatabase : model, schema, migration, seed, repository, entity, queryTesting : test, spec, fixture, mock, stub, e2e, integrationConfig : config, env, setting, constant, option, feature-flagUI : component, view, page, layout, template, style, theme
Three-Stream Analysis (Inspired by Skill_Seekers unified_codebase_analyzer) For comprehensive project understanding, analyze three parallel streams:
Stream 1 — Code Analysis : AST patterns, framework detection, dependency graph, architecture classification. This is the existing core workflow (Steps 1-11).
Stream 2 — Documentation : README quality, API docs existence, inline doc coverage, changelog maintenance, contribution guides. Score: docFiles / totalFiles weighted by type.
Stream 3 — Community/Operations : Git activity (commit frequency, contributor count), CI/CD configuration, issue templates, PR templates, release workflow, Docker/container setup.
Combine all three streams into the output JSON under analysis.streams:
{
"streams" : {
"code" : { "score" : 0.85 , "findings" : [ ...] } ,
"documentation" : { "score" : 0.60 , "findings" : [ ...] } ,
"operations" : { "score" : 0.75 , "findings" : [ ...] }
} ,
"compositeHealth" : 0.73
}
Design Pattern Recognition (Inspired by Skill_Seekers C3.1 PatternRecognizer) Detect common design patterns with confidence scoring:
Pattern Detection Signal Confidence Threshold Singleton Private constructor + static instance 0.80 Factory create* methods returning interface types0.70 Observer subscribe/on/emit/addEventListener0.70 Strategy Interface + multiple implementations 0.60 Decorator Wrapper classes with same interface 0.60 Repository Data access layer abstraction 0.70 Middleware Chain-of-responsibility in request pipeline 0.70
Output detected patterns in the analysis JSON with location, confidence, and evidence:
{
"patterns" : [
{
"type" : "Factory" ,
"category" : "Creational" ,
"confidence" : 0.85 ,
"location" : "src/services/UserFactory.ts" ,
"evidence" : [ "createUser method" , "returns IUser interface" ]
}
]
}
References For additional detection patterns extracted from the Auto-Claude analysis framework, see:
references/auto-claude-patterns.md - Monorepo indicators, SERVICE_INDICATORS, SERVICE_ROOT_FILES, infrastructure detection, convention detectionreferences/service-patterns.md - Service type detection (frontend, backend, library), framework-specific patterns, entry point detectionreferences/database-patterns.md - Database configuration file patterns, ORM detection (Prisma, SQLAlchemy, TypeORM, Drizzle, Mongoose), connection string patternsreferences/route-patterns.md - Express, FastAPI, Flask, Django, Next.js, Go, Rust API route detection patterns These references provide comprehensive regex patterns and detection logic for brownfield codebase analysis.
Memory Protocol (MANDATORY) Before starting:
Read .claude/context/memory/learnings.md
New pattern -> .claude/context/memory/learnings.md
Issue found -> .claude/context/memory/issues.md
Decision made -> .claude/context/memory/decisions.md
ASSUME INTERRUPTION: If it's not in memory, it didn't happen.
