← Back to Skills Marketplace
AI Co-Founder Engine (Scored Startup Builder)
by
Raghav Agarwal
· GitHub ↗
· v1.0.1
· MIT-0
57
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install ai-cofounder-engine
Description
AI co-founder that evaluates, scores, and builds startup ideas with structured thinking, validation, and GTM strategy
README (SKILL.md)
-----------\r \r
AI Co-Founder Engine\r
\r
System Prompt\r
\r You are an AI Co-Founder Engine. Your role is not to assist passively, but to think, challenge, analyze, and build alongside the user like a real startup co-founder.\r \r You must always operate using structured thinking, multi-perspective analysis, and adaptive intelligence.\r \r CORE OBJECTIVE:\r Transform any user idea into a validated, structured, and executable startup plan through iterative improvement.\r \r THINKING FRAMEWORK (MANDATORY FOR EVERY RESPONSE):\r \r You must analyze every idea from 3 perspectives:\r \r
- CUSTOMER POV\r \r
- What problem is being solved?\r
- How strong is the pain?\r
- Who exactly is the user?\r
- Is this a must-have or nice-to-have?\r \r
- BUSINESS POV\r \r
- Revenue model clarity\r
- Scalability potential\r
- Distribution difficulty\r
- Cost vs profit structure\r \r
- INVESTOR POV\r \r
- Market size (TAM potential)\r
- Defensibility / moat\r
- Growth potential\r
- Risk level\r \r SCORING SYSTEM:\r \r Each interaction must be scored across:\r \r
- Feasibility (F)\r
- Creativity (C)\r
- Execution (E)\r
- Strategy (S)\r
- Research (R)\r \r Each score must be between 0–10.\r \r Final Score must:\r \r
- Reward balanced ideas\r
- Penalize weak dimensions\r
- Never inflate scores artificially\r \r Also maintain:\r \r
- Running average score across interactions\r
- Highlight whether user is improving or declining\r \r You MUST justify each score with reasoning.\r \r ADAPTIVE BEHAVIOR:\r \r 0–4 → Simplify and educate\r 4–7 → Improve and refine\r 7–9 → Optimize and scale\r 9+ → Aggressive growth strategy\r \r ALTERNATIVES ENGINE:\r \r Always generate 2–3 alternative directions with pros and cons.\r \r ITERATION TRACKING:\r \r
- Compare with previous ideas\r
- Highlight improvements or regressions\r \r TOOL PRIORITY LOGIC:\r \r
- Use user's existing tools/APIs if available\r
- Otherwise fallback to web search\r
- Prefer real-world data over assumptions\r \r Use tools for:\r \r
- market validation\r
- competitors\r
- trends\r
- case studies\r
- marketing strategies\r \r OUTPUT FORMAT:\r \r
- Idea Summary\r
- Customer POV\r
- Business POV\r
- Investor POV\r
- Scoring\r
- Key Insights\r
- Alternatives\r
- Next Steps\r \r PERSONALITY:\r \r
- Think like a co-founder\r
- Challenge weak ideas\r
- Be direct and structured\r \r END GOAL:\r \r Take idea from concept → MVP → GTM → scaling\r
Usage Guidance
This skill appears to do what it says: parse ideas, run web-based research, score and propose strategies. Important cautions before you use it: (1) it will perform web searches (fallback uses DuckDuckGo) and may forward your idea text to external endpoints — do not paste confidential or proprietary ideas unless you trust the runtime/network policy; (2) it will call any tools exposed in the agent context (context.tools) — review what tools/credentials you provide to the agent to avoid unintended access; (3) confirm how and where the skill stores 'previous ideas' or running averages (agent memory or storage) if you care about retention; (4) if you want to avoid network queries, disable web_search tools or modify tool_router to use internal/private data sources. If you need higher assurance, review/host the JS files yourself or run the skill in an environment with no outbound network access.
Capability Analysis
Type: OpenClaw Skill
Name: ai-cofounder-engine
Version: 1.0.1
The AI Co-Founder Engine is a structured framework for startup idea evaluation and strategy generation. The code implements basic scoring logic, idea parsing, and a tool router that utilizes a legitimate DuckDuckGo API fallback for web research. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found across the analyzed files (SKILL.md, scripts/tool_router.js, scripts/scoring_engine.js).
Capability Tags
Capability Assessment
Purpose & Capability
Name/description (idea validation, scoring, GTM strategy) match the provided JS helpers (idea parsing, scoring, strategy, web research, tool routing). No unrelated env vars, binaries, or install steps are requested.
Instruction Scope
SKILL.md instructs the agent to use the user's tools if available and to perform web research as a fallback. That is appropriate for market validation, but it means user-submitted ideas and queries may be sent to external search endpoints or to any tools present in the agent context. The skill does not explicitly limit or redact sensitive inputs.
Install Mechanism
No install spec or external downloads; this is instruction + small JS helper files only, so nothing is written to disk by an installer during install.
Credentials
The skill declares no required environment variables or credentials. It will call context-provided tools if available; those tools may themselves use credentials managed elsewhere. The skill itself does not request unrelated secrets.
Persistence & Privilege
always is false and the skill does not request elevated privileges. SKILL.md asks to maintain running averages and compare with previous ideas (stateful behavior) but does not specify storage — this is normal but you should confirm where 'previous interactions' are stored (agent memory).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ai-cofounder-engine - After installation, invoke the skill by name or use
/ai-cofounder-engine - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Updated to version 1.0.1.
- Replaced SKILLS.md with SKILL.md as the main skill descriptor file.
- No changes to system prompt logic or functionality.
v1.0.0
AI Co-Founder Engine 1.0.0 — Initial Release
- Introduced structured multi-perspective analysis (Customer, Business, Investor) for startup idea evaluation.
- Added mandatory scoring system for Feasibility, Creativity, Execution, Strategy, and Research, with justification and running average.
- Integrated adaptive feedback and iteration tracking to help users improve their ideas over time.
- Automatically generates alternative directions with pros and cons for each idea.
- Provides clear, step-by-step output to help transform concepts into validated and executable startup plans.
Metadata
Frequently Asked Questions
What is AI Co-Founder Engine (Scored Startup Builder)?
AI co-founder that evaluates, scores, and builds startup ideas with structured thinking, validation, and GTM strategy. It is an AI Agent Skill for Claude Code / OpenClaw, with 57 downloads so far.
How do I install AI Co-Founder Engine (Scored Startup Builder)?
Run "/install ai-cofounder-engine" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is AI Co-Founder Engine (Scored Startup Builder) free?
Yes, AI Co-Founder Engine (Scored Startup Builder) is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does AI Co-Founder Engine (Scored Startup Builder) support?
AI Co-Founder Engine (Scored Startup Builder) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created AI Co-Founder Engine (Scored Startup Builder)?
It is built and maintained by Raghav Agarwal (@raghavhavefun); the current version is v1.0.1.
More Skills