- Home
- Skills
- Agents & Orchestration
- First Principles Engine
More screenshots
Works with the AI Agents you already use
First Principles Engine
Force any claim or decision through rigorous first-principles deconstruction. Strip assumptions, rebuild from real fundamentals, and surface the strongest counterarguments.
$9.99
First Principles Engine
Example session with this skill installed
Should we raise our SaaS prices 20% next quarter? Run first principles.
- Read your context and instructions
- Compiled the first principles engine
**Rebuilt Insight** A 20% price increase is only justified if your current price is significantly below the value delivered *and* your customers have low price sensitivity or high switching costs. Most SaaS companies underprice relative to value, but a flat 20% across the board is lazy. Segment first. **Assumptions Stripped** - Necessary: Customers receive measurable value; you have retention data. - Optional: “Everyone else is raising prices” (irrelevant). - Likely false: A single percentage works for all segments; current price is optimal. **Fundamentals Used** - Willingness-to-pay and value delivered (not cost-plus or competitor matching) - Price elasticity and switching costs - Segment differences (power users vs casual) **Uncertainty & Strongest Counter** High confidence that undifferentiated increases hurt expansion revenue more than they help. Strongest counter: if you have very high net retention and almost no churn from price, the risk is lower than it looks. **What Would Change My Mind** Clear data showing low elasticity in the segments that matter + evidence that current price is leaving significant money on the table. **Next Test** Run a 10–15% increase on new customers only for 30–45 days and measure conversion + early retention before touching existing customers.
Connects securely to your tools. The creator never sees your data.
About this skill
Most “first principles” thinking is theater. People (and AIs) say the words, then quietly keep the same assumptions, analogies, and industry dogma. First Principles Engine makes that harder. It forces a clear, non-optional sequence: 1. Surface the real claim or goal 2. Explicitly strip assumptions and label them 3. Drop to actual fundamentals (incentives, mechanisms, physics, base rates) 4. Rebuild only from what survives 5. Quantify uncertainty and generate the strongest realistic counterarguments 6. Deliver the insight with the risks still visible Includes domain guidance for business, product, personal decisions, science/forecasting, and institutions. Built for founders, operators, investors, and serious thinkers who want cleaner reasoning instead of flattering answers. Works with any SKILL.md-compatible agent (Claude Code, Cursor, Codex, VS Code Copilot, Gemini CLI, and more).
- Does not replace domain expertise - Cannot guarantee better real-world outcomes — only more honest reasoning - Works best on decisions that have real constraints - Light mode is fast; Full mode is deeper and longer - Quality depends on the underlying model
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 22 days ago