SaaS Product Decision Assistant for Openclaw

A fully automated research and evaluation tool that analyzes SaaS product concepts across 9 dimensions to generate interactive HTML feasibility reports.

bettermen
v1.0.0
Jun 16, 2026
0
419
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install saas-decision

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install saas-decision using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is SaaS Product Decision Assistant?

The SaaS Product Decision Assistant is a professional technical analysis skill designed to automate the initial discovery, validation, and benchmarking of SaaS ideas. By leveraging the extensible framework of Openclaw Skills, this tool acts as an autonomous market researcher and system architect. It simplifies the highly fragmented process of assessing software-as-a-service market feasibility, allowing startup founders, product managers, and developers to validate high-impact ideas within minutes.

By taking a user-defined product category and target positioning, the assistant triggers deep parallel searches, extracts live industry data, evaluates pricing models (such as subscription and usage-based tiers), and computes key financial projections (including MRR, ARR, LTV, and CAC). It bridges the gap between high-level business ideas and engineering execution by mapping out exact technical feasibility requirements, legal compliance points, and multi-tenant hosting architectures.

SaaS Product Decision Assistant Use Cases

  • Validate new SaaS startup or product concepts prior to writing any source code.
  • Conduct automated competitive analysis to uncover pricing, feature gaps, and marketing strategies.
  • Produce comprehensive, presentation-ready HTML reports detailing the business viability and risk factors of a SaaS concept.
  • Formulate technical implementation roadmaps, including multi-tenant database isolation strategies and third-party SaaS infrastructure options.

How SaaS Product Decision Assistant Works

  1. Concept Intake: The user triggers the assistant by inputting their desired SaaS product sector and basic market positioning.
  2. Parallel Searching: The skill fires concurrent queries utilizing WebSearch across three targeted batches: market trends, user personas/pricing, and tech stack/growth strategies.
  3. Targeted Scraping: Using WebFetch, the agent retrieves core raw contents of high-value industry blogs, competitor pricing matrices, and technical architectural schemas.
  4. Multi-Dimensional Matrix Assessment: The assistant parses the gathered text, scoring the idea across 9 distinct technical and financial SaaS benchmarks.
  5. Report Formulation: The evaluated data structures are formatted into a JSON payload and processed via a report_generator.py execution layer to yield a localized, interactive, and beautifully designed HTML dashboard.

SaaS Product Decision Assistant Setup

Ensure that your local execution environment has Python configured along with the necessary binaries and permissions.

Command-Line Execution

You can run the Python script directly to parse structured analytical payloads into ready-to-view dashboards:

# Run the Python-based report generator
python ./scripts/report_generator.py \
  --name "AI Customer Support SaaS" \
  --category "Customer Relations" \
  --output "./reports/ai-support-feasibility.html" \
  --scores '{"market_demand": 85, "user_profile": 80, "pain_points": 75, "competition": 70, "monetization": 85, "acquisition": 75, "marketing": 80, "cost_structure": 70, "tech_feasibility": 90}' \
  --market-demand '{"score": 85, "market_size": "$15 Billion by 2026", "cagr": "14%"}'

Programmatic Integration

To call the underlying generator interface natively in your custom developer pipeline:

import sys
sys.path.insert(0, './scripts')
from report_generator import generate_report

data = {
    "name": "E-commerce Personalization Engine",
    "category": "Marketing Tech",
    "scores": {"market_demand": 82, "user_profile": 78, "pain_points": 80, "competition": 65, "monetization": 75, "acquisition": 70, "marketing": 72, "cost_structure": 80, "tech_feasibility": 85},
    "market_demand": {"score": 82, "size": "$8B", "trends": "High demand for AI personalizers"}
}

html_content = generate_report(data)
with open('ecommerce_saas_report.html', 'w', encoding='utf-8') as f:
    f.write(html_content)

SaaS Product Decision Assistant Data Schema & Taxonomy

The assistant leverages structured metrics to score and visualize technical viability. Key evaluations are organized into the following schema:

Weighted Multi-Dimensional Evaluation Matrix

Assessment Category Weight Evaluated Standard
Market Demand 15% Sub-sector TAM/SAM estimates, historical digital penetration, annual growth curves
User Profile 10% ICP definition, internal buyer personas, B2B purchasing decision chain, pricing tier tolerability
Pain Points 10% Customer friction frequency, severity, friction cost, current manual alternative limits
Competition 15% Direct and indirect competitors, market saturation levels, potential features gap
Monetization 15% Pricing tiers (Usage, Flat-rate Subscription, Freemium), ARPU and LTV trajectory models
Acquisition 10% Feasible CAC models, PLG conversion funnels, scalable organic growth paths
Marketing 15% Search traffic potential (SEO), strategic brand differentiation, positioning channels
Cost Structure 5% Multi-tenant cloud hosting, operational R&D ratios, third-party APIs dependencies
Tech Feasibility 5% Logical vs database instance isolation models, baseline tech stack recommendations

Grading Levels

  • Score >= 80: Strongly Recommended (High demand, clear monetization path, low entry friction).
  • Score 65-79: Proceed with Caution (Healthy viability, but demands clear product differentiation).
  • Score 50-64: Temporarily Hold (Requires deeper customer discovery or MVP proof-of-concept validation).
  • Score < 50: Not Recommended (High operational hurdles, weak pricing power, or oversaturated markets).

SaaS Product Decision Assistant Advanced Features

  • Auto-calculated SaaS Metrics: Forecasts CAC, LTV, MRR, and ARR metrics utilizing pre-trained SaaS benchmark models and competitor pricing databases.
  • Extensible Python Engine: Seamlessly tweak assessment weights or append new data endpoints via custom modifications to report_generator.py.
  • Multi-Tenant System Modeling: Recommends optimal databases (e.g., PostgreSQL with Row-Level Security vs isolated schema models) aligned with customer regulatory demands.
  • Cross-Agent Integration: Works alongside broader Openclaw Skills to trigger secondary automated workflows, such as automated boilerplate code generation or automated landing page creation based on the generated MVP roadmap.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*