skene-growth 0.1.2

PLG analysis toolkit for codebases - analyze code, detect growth opportunities, generate documentation

skene-growth

PLG (Product-Led Growth) analysis toolkit for codebases. Analyze your code, detect growth opportunities, and generate documentation of your stack.

Quick Start

No installation required - just run with uvx:

# Analyze your codebase
uvx skene-growth analyze . --api-key "your-gemini-api-key"

# Or set the API key as environment variable
export SKENE_API_KEY="your-gemini-api-key"
uvx skene-growth analyze .

Get a free Gemini API key at: https://aistudio.google.com/apikey

What It Does

skene-growth scans your codebase and generates a growth manifest containing:

• Tech Stack Detection - Framework, language, database, auth, deployment
• Growth Hubs - Features with growth potential (signup flows, sharing, invites, billing)
• GTM Gaps - Missing features that could drive user acquisition and retention

With the --docs flag, it also collects:

• Product Overview - Tagline, value proposition, target audience
• Features - User-facing feature documentation with descriptions and examples

Installation

Option 1: uvx (Recommended)

Zero installation - runs instantly (requires API key):

uvx skene-growth analyze . --api-key "your-gemini-api-key"
uvx skene-growth generate
uvx skene-growth inject
uvx skene-growth validate ./growth-manifest.json

Note: The analyze command requires a Gemini API key. Get one free at https://aistudio.google.com/apikey

Option 2: pip install

pip install skene-growth

CLI Commands

analyze - Analyze a codebase

Requires a Gemini API key (set via --api-key, SKENE_API_KEY env var, or config file).

# Analyze current directory
uvx skene-growth analyze . --api-key "your-gemini-api-key"

# Using environment variable
export SKENE_API_KEY="your-gemini-api-key"
uvx skene-growth analyze .

# Analyze specific path with custom output
uvx skene-growth analyze ./my-project -o manifest.json

# With verbose output
uvx skene-growth analyze . -v

# Use a specific model
uvx skene-growth analyze . --model gemini-2.5-pro

# Enable docs mode (collects product overview and features)
uvx skene-growth analyze . --docs

Output: ./skene-context/growth-manifest.json

The --docs flag enables documentation mode which produces a v2.0 manifest with additional fields for generating richer documentation.

generate - Generate documentation

# Generate docs from manifest (auto-detected)
uvx skene-growth generate

# Specify manifest and output directory
uvx skene-growth generate -m ./manifest.json -o ./docs

Output: Markdown documentation in ./skene-docs/

inject - Generate growth loop injection plan

# Generate injection plan using built-in growth loops
uvx skene-growth inject

# Use custom growth loops from CSV
uvx skene-growth inject --csv loops.csv

# Specify manifest
uvx skene-growth inject -m ./manifest.json

Output: ./skene-injection-plan.json

validate - Validate a manifest

uvx skene-growth validate ./growth-manifest.json

config - Manage configuration

# Show current configuration
uvx skene-growth config

# Create a config file in current directory
uvx skene-growth config --init

Configuration

skene-growth supports configuration files for storing defaults:

Configuration Files

Location	Purpose
./.skene-growth.toml	Project-level config (checked into repo)
~/.config/skene-growth/config.toml	User-level config (personal settings)

Sample Config File

# .skene-growth.toml

# API key for LLM provider (can also use SKENE_API_KEY env var)
# api_key = "your-gemini-api-key"

# LLM provider to use (default: gemini)
provider = "gemini"

# Default output directory
output_dir = "./skene-context"

# Enable verbose output
verbose = false

Configuration Priority

Settings are loaded in this order (later overrides earlier):

1. User config (~/.config/skene-growth/config.toml)
2. Project config (./.skene-growth.toml)
3. Environment variables (SKENE_API_KEY, SKENE_PROVIDER)
4. CLI arguments

Python API

CodebaseExplorer

Safe, sandboxed access to codebase files:

from skene_growth import CodebaseExplorer

explorer = CodebaseExplorer("/path/to/repo")

# Get directory tree
tree = await explorer.get_directory_tree(".", max_depth=3)

# Search for files
files = await explorer.search_files(".", "**/*.py")

# Read file contents
content = await explorer.read_file("src/main.py")

# Read multiple files
contents = await explorer.read_multiple_files(["src/a.py", "src/b.py"])

Analyzers

from pydantic import SecretStr
from skene_growth import ManifestAnalyzer, CodebaseExplorer
from skene_growth.llm import create_llm_client

# Initialize
codebase = CodebaseExplorer("/path/to/repo")
llm = create_llm_client(
    provider="gemini",
    api_key=SecretStr("your-api-key"),
    model_name="gemini-2.0-flash",
)

# Run analysis
analyzer = ManifestAnalyzer()
result = await analyzer.run(
    codebase=codebase,
    llm=llm,
    request="Analyze this codebase for growth opportunities",
)

# Access results (the manifest is in result.data["output"])
manifest = result.data["output"]
print(manifest["tech_stack"])
print(manifest["growth_hubs"])

Growth Loop Catalog

from skene_growth import GrowthLoopCatalog

catalog = GrowthLoopCatalog()

# Get all loops
all_loops = catalog.get_all()

# Get by category
referral_loops = catalog.get_by_category("referral")
activation_loops = catalog.get_by_category("activation")

# Get specific loop
invite_loop = catalog.get_by_id("user-invites")

# Load custom loops from CSV
catalog.load_from_csv("my-loops.csv")

Documentation Generator

from skene_growth import DocsGenerator, GrowthManifest

# Load manifest
manifest = GrowthManifest.parse_file("growth-manifest.json")

# Generate docs
generator = DocsGenerator()
context_doc = generator.generate_context_doc(manifest)
product_doc = generator.generate_product_docs(manifest)

Injection Planner

from skene_growth import InjectionPlanner, GrowthLoopCatalog, GrowthManifest

manifest = GrowthManifest.parse_file("growth-manifest.json")
catalog = GrowthLoopCatalog()
planner = InjectionPlanner()

# Generate quick plan (no LLM required)
plan = planner.generate_quick_plan(manifest, catalog)

# Save plan
planner.save_plan(plan, "injection-plan.json")

Growth Manifest Schema

The growth-manifest.json output contains:

{
  "version": "1.0",
  "project_name": "my-app",
  "description": "A SaaS application",
  "tech_stack": {
    "framework": "Next.js",
    "language": "TypeScript",
    "database": "PostgreSQL",
    "auth": "NextAuth.js",
    "deployment": "Vercel"
  },
  "growth_hubs": [
    {
      "feature_name": "User Invites",
      "file_path": "src/components/InviteModal.tsx",
      "detected_intent": "referral",
      "confidence_score": 0.85,
      "growth_potential": ["viral_coefficient", "user_acquisition"]
    }
  ],
  "gtm_gaps": [
    {
      "feature_name": "Social Sharing",
      "description": "No social sharing for user content",
      "priority": "high"
    }
  ],
  "generated_at": "2024-01-15T10:30:00Z"
}

Docs Mode Schema (v2.0)

When using --docs flag, the manifest includes additional fields:

{
  "version": "2.0",
  "project_name": "my-app",
  "description": "A SaaS application",
  "tech_stack": { ... },
  "growth_hubs": [ ... ],
  "gtm_gaps": [ ... ],
  "product_overview": {
    "tagline": "The easiest way to collaborate with your team",
    "value_proposition": "Simplify team collaboration with real-time editing and sharing.",
    "target_audience": "Remote teams and startups"
  },
  "features": [
    {
      "name": "Team Workspaces",
      "description": "Create dedicated spaces for your team to collaborate on projects.",
      "file_path": "src/features/workspaces/index.ts",
      "usage_example": "<WorkspaceCard workspace={workspace} />",
      "category": "Collaboration"
    }
  ],
  "generated_at": "2024-01-15T10:30:00Z"
}

Built-in Growth Loops

The catalog includes these growth loop templates:

Loop	Category	Description
User Invites	Referral	Users invite others to join
Social Sharing	Acquisition	Share content on social media
Onboarding Completion	Activation	Guide users to key actions
Usage Streaks	Retention	Encourage regular usage
Upgrade Prompts	Revenue	Prompt upgrades at limits
User-Generated Content	Acquisition	Content that attracts users
Re-engagement Notifications	Retention	Bring back inactive users

Environment Variables

Variable	Description
SKENE_API_KEY	API key for LLM provider (Gemini)
SKENE_PROVIDER	LLM provider to use (default: gemini)

Requirements

• Python 3.11+
• Gemini API key (required for analyze command) - Get one free at https://aistudio.google.com/apikey

License

MIT