More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Universal Multi Agent Negotiation

    0

    A reusable negotiation workflow for simulating two parties and producing a transparent negotiation report.

    Free

    Security scanned
    Universal Multi Agent Negotiation

    Universal Multi Agent Negotiation

    Example session with this skill installed

    Simulate a 3-round negotiation between a SaaS startup (Party A) and a cloud provider (Party B) for a 12-month contract focusing on monthly cost and uptime SLA. A's max budget is $5k/mo.

    • Read your context and instructions
    • Compiled the universal multi agent

    Negotiation Report

    Scenario: Hypothetical simulation. One AI agent plays both parties. No real parties are contacted and nothing here is binding.

    • Parties: Party A (SaaS startup, buyer) and Party B (cloud provider, seller)
    • Topic: 12-month cloud hosting contract, monthly cost and uptime SLA
    • Rounds completed: 3 of 3
    • Outcome: Verified simulated agreement

    Party positions

    Party A (SaaS startup)

    • User-provided: hard maximum of $5,000/month. Term is 12 months.
    • Assumed: wants the highest SLA the budget allows, since downtime hurts its customers.

    Party B (cloud provider)

    • User-provided: no constraints specified.
    • Assumed (hypothetical): prefers higher revenue and a full 12-month commitment, and higher SLA tiers cost more to deliver. For this simulation I assumed B's lowest acceptable prices are roughly $4,600 at 99.9%, $4,900 at 99.95%, and $5,500 at 99.99%. These are soft positions I invented, not facts about any real provider.

    Units: Uptime is measured monthly. In a 30-day month, 99.9% allows about 43 minutes of downtime, 99.95% about 22 minutes, and 99.99% about 4 minutes.

    Negotiation history

    Round 1

    • A proposes: $3,800/mo, 99.99% uptime.
    • B rejects. The price is far below what a 99.99% tier costs to deliver.
    • B counters: $6,200/mo, 99.99%.
    • A's evaluation: Violates the $5,000 cap, so A cannot accept. A signals flexibility on the SLA.

    Round 2

    • A proposes: $4,500/mo, 99.95%.
    • B rejects. The price is still below its floor for that tier.
    • B counters: $5,400/mo, 99.95%.
      A's evaluation: Violates the $5,000 cap, so A rejects without relaxing the constraint. Issues still open: price gap of about $900 at 99.95%.

    Round 3

    A proposes: $4,900/mo, 99.95% uptime, 12-month term. This is a concession toward B's price and stays under A's cap. A argues the 12-month commitment lowers B's churn risk.

    • B's evaluation: At or above its assumed floor for that tier, with committed revenue.
    • B accepts the exact terms.
    • A confirms acceptance of the same terms.

    Final terms (both parties explicitly accepted)

    IssueAgreed value
    Monthly cost$4,900
    Uptime SLA99.95% monthly
    Term12 months
    Total contract value$58,800

    Constraint check

    ConstraintStatus
    A: monthly cost ≤ $5,000Satisfied ($4,900)
    B: any hard constraintsNot specified, so not verified. B's floor is an assumption.
    Both parties accepted identical termsYes
    No mandatory issue unresolvedYes (cost and SLA both settled)

    Remaining issues and assumptions

    Not negotiated: SLA remedies (service credits for breaches), exclusions such as maintenance windows, exit terms, and price escalation after 12 months. Real contracts would need these.

    • Assumed: B's price floors, A's SLA priority, and monthly uptime measurement.
    • No market pricing was researched. Real-world rates for comparable tiers may differ.

    Summary

    Both sides started far apart. The cost-versus-SLA trade-off settled it: A gave up 99.99% for 99.95%, and B gave up $1,300/mo from its opening price in exchange for a full-term commitment. A's budget cap was never relaxed. The result is a simulated agreement only, with no legal force.

    I can rerun this with different B constraints, add service credits as a third issue, or change the round limit.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Universal Multi-Agent Negotiation

    Prepare for important negotiations through structured AI-powered simulations between two parties.

    What it does

    • Simulates negotiations between two parties with different objectives, priorities and constraints.
    • Structures opening proposals, counteroffers and negotiation rounds.
    • Evaluates stated hard constraints, preferences and potential compromises.
    • Tracks concessions and changes in each party's position.
    • Checks whether both parties explicitly accept the same final terms.
    • Produces a structured negotiation report with outcomes and unresolved issues.

    How it works

    1. Describe the two parties and what they are negotiating.
    2. Provide the requirements and priorities you know.
    3. Answer any clarifying questions about missing information.
    4. Let your AI agent simulate the negotiation through proposals and counteroffers.
    5. Review the negotiation history, agreement status and final report.

    You can provide a short description or detailed negotiation requirements. If information is missing, the agent can ask questions or proceed with clearly identified hypothetical assumptions.

    Use cases

    • Buyer and supplier negotiations.
    • Business partnerships and revenue-sharing agreements.
    • Employment and salary negotiations.
    • International trade simulations.
    • Contract and procurement discussions.

    Requirements

    Works through a compatible AI agent that supports the SKILL.md standard and Agensi skill integration. No separate Python server, Docker setup, Ollama installation or external API key is required for this version.

    Limitations

    This skill produces hypothetical negotiation simulations. Both parties are simulated by one connected AI agent, not independent real-world representatives. Constraint evaluation relies on the agent's reasoning and is not a deterministic guarantee. It does not provide legal advice, contact real negotiating parties or independently verify market data.

    • Produces hypothetical negotiation simulations, not legally binding agreements.
    • One connected AI agent simulates both negotiating parties; they are not independent real-world agents.
    • Constraint and agreement checks are reasoning-based, not deterministic programmatic validation.
    • Does not independently verify real-world prices, supplier costs, market data or legal requirements.
    • Missing information may require clarification or clearly labelled hypothetical assumptions.
    • Does not contact real negotiating parties or execute contracts.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    No special permissions declared or detected

    Listed2 days ago

    What's inside

    Frequently Asked Questions

    The skill uses a structured multi-round negotiation workflow with opening proposals, counteroffers, concessions and explicit acceptance checks. It evaluates stated constraints and records why proposals are accepted or rejected. These checks rely on the AI agent's reasoning and are not guaranteed programmatic enforcement.

    You receive the Universal Multi-Agent Negotiation workflow, supporting reference instructions and example negotiation data. The skill guides your compatible AI agent through party setup, proposals, counteroffers, concessions and a structured final negotiation report.

    No. This version runs through a compatible AI agent that supports the SKILL.md standard and Agensi integration. No separate Python server, Docker, Ollama installation or external API key is required.

    Yes. The skill can handle multiple negotiation issues simultaneously, such as price, delivery timelines, warranty periods, payment terms and service levels. It tracks proposals and concessions across the issues and reports the final outcome.

    No. The skill does not independently retrieve real-time market prices or supplier cost data. It works with information you provide and may use clearly labelled hypothetical assumptions when information is missing. You can supply external research or market quotes to inform the simulation.

    New in Agents & Orchestration