A fully automated research and evaluation tool that analyzes SaaS product concepts across 9 dimensions to generate interactive HTML feasibility reports.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install saas-decision
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
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).
Get the raw skill files in a ZIP archive.
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.
report_generator.py execution layer to yield a localized, interactive, and beautifully designed HTML dashboard.Ensure that your local execution environment has Python configured along with the necessary binaries and permissions.
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%"}'
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)
The assistant leverages structured metrics to score and visualize technical viability. Key evaluations are organized into the following schema:
| 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 |
report_generator.py.Loading
This skill enables AI agents to provision, configure, and manage Alibaba Cloud PAI Resource Groups and VPC bindings through a highly controlled, secure Aliyun CLI execution pattern.

An automated decision-support system that evaluates AI Agent ideas across eight key dimensions and generates a professional, interactive HTML feasibility report.

A multi-dimensional performance diagnostics tool that synthesizes business metrics, renewal rates, and campaign targets into a priority-ranked gap analysis.

An AI-powered market intelligence agent that automates competitor benchmarking, SWOT strategies, positioning mapping, and action roadmaps.

A highly structured AI agent skill designed to provide safe, real-time verified assistance for Alibaba Cloud Realtime Compute for Flink optimization, SQL generation, and troubleshooting.

An AI agent skill that transforms narration scripts into full-screen, interactive web presentations built on Vite, React, and TypeScript.








































