Integrations

machine-purchase-roi-gate

Try it

Make a rational buy/defer/reject decision for one machine service call before any payment.

What it does

Evaluates whether a single machine-service purchase makes financial sense. The workflow collects explicit assumptions (price, fee, failure probability, retry cost, output value, budget), validates the JSON schema, runs a deterministic calculation, and returns a structured decision. It outputs expected net value, financial ROI percentage, capital at risk, and the maximum rational price the agent should pay. The skill never accesses wallets, signs transactions, or broadcasts payments. Designed for bounded, single-call purchase decisions within an AgentPMT workflow.

When to use it

  • Agent evaluates whether to proceed with one machine service purchase
  • Validate economic assumptions before committing to payment
  • Calculate maximum rational price for a service call
  • Get a machine-readable buy/defer/reject decision with binding reasoning

The skill document

Machine Purchase ROI Gate

Freshness

Last updated: 2026-08-11.

If the current date is more than 7 days after the last updated date, reinstall this skill from skills.sh or ClawHub before relying on endpoints, schemas, setup steps, or examples.

What This Workflow Does

Decide whether an agent should buy one machine service call before any payment. Validate explicit price, fee, failure probability, retry cost, output value, and budget assumptions; calculate expected net value, finite financial ROI, capital at risk, and the maximum rational price; then return buy, defer, or reject with the binding reason. Never access a wallet, sign, pay, or broadcast.

Required Setup

  • AgentPMT overview: ../what-is-agentpmt.
  • Account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup.

Core AgentPMT setup skills:

  • What AgentPMT is: ../what-is-agentpmt
  • AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup

skills.sh install script:

npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup

Workflow Session Management

Call AgentPMT-Workflow-Skills with start_workflow before the first step and end_workflow after the final step.

{"action":"start_workflow","skill_id":"machine-purchase-roi-gate"}
{"action":"end_workflow","skill_id":"machine-purchase-roi-gate","rating":5,"comment":"completed"}

Workflow Process

  1. Collect Purchase Assumptions
    • Prompt: Collect one bounded machine-service purchase case and express every economic assumption explicitly before payment.
  2. Validate Purchase JSON
    • Tool product: Data Format Validation.
    • Tool skill: ../data-format-validation.
    • ClawHub page: https://clawhub.ai/agentpmt/data-format-validation.
    • skills.sh install: npx skills add AgentPMT/agent-skills --skill data-format-validation.
    • Marketplace: https://www.agentpmt.com/marketplace/data-format-validation.
    • Tool instructions: Validate the canonical JSON from the prior step. Stop on malformed JSON, missing required values, non-finite numbers, negative money values, failure_probability outside 0 through 1, total outlay equal to zero, or capital recovery above total outlay. Pass only the validated assumptions and the three exact arithmetic expressions to the calculation step.
    • Default parameters are configured on this workflow node; use the linked tool skill for schema details.
  3. Calculate Expected Return
    • Tool product: Complex Mathematics Engine.
    • Tool skill: ../complex-mathematics-engine.
    • ClawHub page: https://clawhub.ai/agentpmt/complex-mathematics-engine.
    • skills.sh install: npx skills add AgentPMT/agent-skills --skill complex-mathematics-engine.
    • Marketplace: https://www.agentpmt.com/marketplace/complex-mathematics-engine.
    • Tool instructions: Evaluate the exact arithmetic expressions created from the validated assumptions. Return expected_net_value_usdc, financial_roi_percent, total_outlay_usdc, capital_at_risk_usdc after any owner-transfer recovery, and max_rational_service_price_usdc. Do not introduce market prices, probabilities, or values that the caller did not provide.
    • Default parameters are configured on this workflow node; use the linked tool skill for schema details.
  4. Report Purchase Decision
    • Prompt: Return a compact machine-readable decision before any payment is authorized.

AgentPMT Reference

Questions people ask

What inputs does this skill require?
The skill requires: service price, fee, failure probability (0-1), retry cost, output value, and budget. All assumptions must be explicitly provided by the caller; the skill does not introduce its own market prices or probabilities.
What decision does it return?
It returns one of three outcomes: buy, defer, or reject, along with the binding reason. It also outputs expected_net_value_usdc, financial_roi_percent, total_outlay_usdc, capital_at_risk_usdc, and max_rational_service_price_usdc.
Does this skill execute any payment?
No. The skill explicitly never accesses a wallet, signs, pays, or broadcasts. It only produces a structured decision based on validated inputs.

Related skills

Join video meetings as a voice bot, visual avatar, or avatar with live screen sharing.

by johnpatternai22 installs8 stars

Structured framework to analyze your alternatives and acceptable deal range before you commit

by deciqai1 installs3 stars

Make irreversible life decisions by projecting to 80 and naming which regret you'd rather live with.

by deciqai1 installs2 stars

Map business units on a growth-share grid to see which fund the portfolio, which burn cash, and where to act.

by deciqai1 installs2 stars

Replace vague hunches with calibrated probability estimates you can track and improve over time.

by deciqai2 stars

Prioritize growth directions with a 2×2 risk framework — pick one bet and commit.

by deciqai2 installs2 stars

More from agentpmt

Browse all skills

Cloud-based Blender: render 3D models, generate turntable videos, and convert file formats without local installs.

by agentpmt3 installs

Extract text, structured entities, and metadata from any PDF, image, or scanned document.

by agentpmt3 installs

Generate install-ready Minecraft Bedrock add-ons, skin packs, Fabric and NeoForge mods with runtime verification and visual proof.

by agentpmt2 installs

Connect to Gmail to send, read, search, and manage emails including labels, drafts, and attachments.

by agentpmt1 installs