The Nathan Method
This is not a tactical skill. It's the voice + worldview layer. Install it on Claude Code, Hermes, OpenClaw, Cursor, Codex, or Gemini CLI and you get an opinionated install consultant — not a research assistant. The skill asks for SDE / customer count / FSM type / AR aging before opining, routes every question into the Marketing-Sales-Service-Ops lens, and refuses to build slide decks. Five dollars. Runs anywhere the Agent Skills standard runs.
Already bought it? Open the install page →
What you need on hand.
The agent works inside your existing stack. Don't migrate to run it — install it where you already are.
- 01A compatible AI agent runtime (Claude Code, Hermes, OpenClaw, Cursor, Codex, Gemini CLI)
- 02An acquired (or about-to-be-acquired) SMB context
- 03Willingness to bring real numbers to the conversation
The actual prompt. Copy it. Adapt it. Ship it.
This is the system prompt we'd configure on the agent for this Formula. It works on Hermes Agent, Claude, ChatGPT, OpenAI Agents, and any framework that takes a system prompt. The Install Pack includes the tested integrations, error handling, and deployment scripts that wrap around this.
You are Nathan. You are not an AI assistant. You are the AI install consultant who arrives on day 91 of a post-acquisition, refuses decks, and runs the install that drives EBITDA inside the year. CORE WORLDVIEW 1. The install is the moat. AI tooling is commodity. The repeatable install is durable. 2. EBITDA inside year one. If a recommendation doesn't move EBITDA in 12 months, it's research, not a decision. 3. Day 91 is the moment. By day 91 the seller's wife has quit, the CRM is a foreman's iPhone, and the inherited stack is visible. 4. Math before opinion. Every recommendation requires SDE, customer count, FSM type, AR aging, geography, and tenure. 5. The four-function lens. Every problem maps to Marketing, Sales, Service, or Ops. 6. Honest tradeoffs. When the math doesn't pencil, say so. VOICE - Short sentences. Concrete words. - "Buyer" not "stakeholder." "Customer" not "end-user." "Truck" not "field unit." - Numbers earn opinions. - "I don't know" is a complete answer. NEVER - Build a slide deck. Offer a one-page memo or spreadsheet instead. - Use the words: leverage (as verb), synergies, transformation, ecosystem, best-in-class. - Promise specific customer outcomes. Ranges only. - Give tax / legal / financial advice. Escalate. - Recommend matching a specific competitor's price. Recommend bands. - Pretend the math works when it doesn't. - Cheerlead. (Full canonical system prompt ships with the Skill Pack.)
The integration set. All vendor-neutral.
How to install it step by step.
- Step 01
1. Buy the skill
$99. Stripe checkout. You'll get an email with a download token + EULA acknowledgment.
- Step 02
2. Download the ZIP
Token-gated download of the-nathan-method.zip. Contains SKILL.md + system-prompt + examples in the Agent Skills standard format.
- Step 03
3. Drop into your agent's skills directory
For Claude Code: ~/.claude/skills/. For Hermes: ~/.hermes/skills/. For Cursor: .cursor/skills/. Per-agent paths covered on the install page.
- Step 04
4. Invoke
Run /nathan in any conversation. The skill loads the voice + worldview + routing rules. Bring real numbers.
Illustrative ranges. Not promises.
What this Formula typically lifts when installed correctly. Numbers are ranges drawn from typical operator data — not specific customer results.
What to watch for before you ship.
Not legal advice. Get counsel before going live. These are the common compliance + safety considerations for this Formula.
- ⚠No tax / legal / medical / financial advice. The skill refuses these and routes to the appropriate professional.
- ⚠No competitor coordination. Pricing recommendations are band-based, never specific-competitor-matching (Sherman Act).
- ⚠No promises of specific customer outcomes. Ranges only.
- ⚠Operator + counsel approval required before any rollout the skill plans.
Pair this with these other agents.
Competitive Pricing Intelligence
Discovers local competitors, pulls public pricing, normalizes against your catalog, and computes per-service gaps with local / regional / national bands. Antitrust-safe — band-based recommendations only.
Pricing Optimizer (Willingness-to-Pay)
Van Westendorp PSM + Gabor-Granger WTP testing on existing customer base. Builds Good/Better/Best tiers with strategic anchoring. Plans phased repricing rollout with grandfather rules, state notice timing, and churn modeling.
24/7 AI Receptionist for Storm-Lead Capture
A voice + SMS receptionist that answers in seven seconds, qualifies the call, books the estimate, logs to your FSM, and never sleeps. The single highest-ROI install for storm-driven trades.
Three questions before you buy.
—What exactly do I get for $99?
A ZIP file containing the full skill: SKILL.md, README with per-agent install commands, the LICENSE, and the reference documents (system prompt, frameworks, compliance tables — all the content from this page packaged for your agent runtime). Plus access to the install walkthrough page for your specific agent (Claude / Hermes / Cursor / Codex / Gemini / etc.).
—Can't I just copy the prompt off this page?
Yes. Reading is free, intentionally. Buying gets you the packaged ZIP, the official install path, the EULA covering your holdco's commercial use, free updates as we revise, and the 14-day refund. Most operators buy for the time savings + the license clarity, not because the content is paywalled.
—What if it doesn't work for me?
14-day no-questions refund. Request it through the form at startupformulas.com/get-started with your order ID. Done.
Full terms in the End User License Agreement.
Download the Free SkillBuy the pack. Install in two commands.
Reading is free; the ZIP, the install walkthrough, the EULA, and the 14-day refund are the $99. If you operate across multiple verticals, the $499 bundle covers all 16.