From specialist-agent
Generates a developer guide for unfamiliar codebases by scanning structure, mapping architecture, detecting conventions, analyzing key modules, and providing setup instructions.
npx claudepluginhub herbertjulio/specialist-agent --plugin specialist-agentThis skill is limited to using the following tools:
Understand any codebase in minutes. Generates a developer guide with architecture, conventions, key modules, and getting-started instructions.
Analyzes unfamiliar codebases to generate structured onboarding guides with architecture maps, key entry points, conventions, and starter CLAUDE.md. Use for new projects or initial Claude Code setup.
Analyzes unfamiliar codebases to generate structured onboarding guides with architecture maps, key entry points, conventions, and starter CLAUDE.md.
Delivers codebase onboarding via project discovery, architecture walkthrough, key files list, naming conventions, dependency graph, code tour, and summary report. For new team members or orientation.
Share bugs, ideas, or general feedback.
Understand any codebase in minutes. Generates a developer guide with architecture, conventions, key modules, and getting-started instructions.
Target: $ARGUMENTS
@scout for quick checks instead)Scan the project root:
Read: package.json / pyproject.toml / go.mod / Cargo.toml
Read: README.md (if exists)
Read: ARCHITECTURE.md / CLAUDE.md / CONTRIBUTING.md (if exist)
Scan: Top-level directory structure
Extract:
Map the project structure:
Identify:
- Source root (src/, app/, lib/)
- Module/feature boundaries
- Shared utilities
- Configuration files
- Test structure
- CI/CD setup
Generate architecture diagram:
src/
├── modules/ → Feature modules (users, orders, products)
│ └── [module]/
│ ├── types/ → TypeScript interfaces
│ ├── services/ → Business logic
│ ├── hooks/ → State management
│ └── components/ → UI components
├── shared/ → Shared utilities
├── config/ → App configuration
└── app/ → App entry and routing
Detect coding conventions by reading actual files:
| Convention | How to Detect |
|---|---|
| Naming | Read 3-5 files, check function/variable naming |
| File structure | Map actual directory patterns |
| State management | Find store/state imports (Redux, Zustand, Pinia, etc.) |
| API layer | Find HTTP client usage (axios, fetch, etc.) |
| Testing | Find test files, check framework (Jest, Vitest, etc.) |
| Styling | Find CSS/styled imports (Tailwind, CSS Modules, etc.) |
| Error handling | Find try/catch patterns, error boundaries |
| Imports | Check for path aliases, barrel exports |
For each major module/feature:
Module: [name]
├── Purpose: [what it does]
├── Files: [count]
├── Dependencies: [what it imports from]
├── Dependents: [what imports from it]
├── Entry point: [main file]
└── Tests: [yes/no, coverage estimate]
Focus on the 3-5 most important modules.
Compile everything into an actionable guide.
Before claiming onboarding is complete:
| Excuse | Reality |
|---|---|
| "README explains everything" | READMEs are often outdated. Verify against actual code. |
| "Architecture is obvious" | Obvious to maintainers, not newcomers. Map it explicitly. |
| "Too many files to analyze" | Focus on top 3-5 modules. Don't skip the mapping step. |
| "No tests to analyze" | That IS the finding. Report it in the guide. |
| "Conventions aren't consistent" | Document the inconsistencies. It's useful for the developer. |
──── /onboard ────
Project: [name]
Stack: [language + framework + key libraries]
Architecture:
[directory tree diagram]
Conventions:
Naming: [camelCase / snake_case / PascalCase]
State: [Redux / Zustand / Pinia / Context]
API: [axios / fetch / tRPC]
Testing: [Jest / Vitest / Playwright]
Styling: [Tailwind / CSS Modules / styled-components]
Key Modules:
1. [module] - [purpose] ([X files])
2. [module] - [purpose] ([X files])
3. [module] - [purpose] ([X files])
Getting Started:
Install: [command]
Dev: [command]
Test: [command]
Build: [command]
Notes:
- [important observations]
- [potential gotchas]
- [missing documentation areas]