Atlas / Skills / wondelai / Negotiation

NegotiationCAUTION

skills/wondelai/negotiation

Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.

Verdict
CAUTION
Grade
B
Trust score
89 /100
Version
1.5.0
Hosts
—
License
MIT
Stars
2,377
01

Overview

Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.

Read from source at commit c502026d022aOBSERVED · 2026-10-10
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: negotiation
description: 'Prepare and execute negotiations using tactical empathy, calibrated questions, and the Ackerman method. Use when the user mentions "salary negotiation", "contract terms", "handling objections", "mirroring and labeling", "difficult conversation", "deal terms", "BATNA", "anchoring", "how do I ask for a raise", "get a better deal", or "they wont budge on price". Also trigger when preparing for a vendor negotiation, resolving a pricing dispute, or navigating a high-stakes conversation where both sides need to feel heard. Covers accusation audits, Black Swan discovery, and the "Thats Right" technique. For persuasion in product and marketing, see influence-psychology.'
license: MIT
metadata:
  author: wondelai
  version: "1.5.0"
---

# Negotiation

Tactical empathy-based negotiation framework from FBI hostage negotiator Chris Voss. Understand the emotional drivers behind decisions and use proven techniques to build rapport, uncover hidden information, and reach better outcomes.

## Core Principle

**People want to be understood and feel safe.** The most effective path to "yes" runs through empathy, active listening, and emotional intelligence -- not logic, arguments, or compromise. Treat every negotiation as a discovery process: your assumptions are hypotheses to test, and the other side's needs (respect, security, autonomy) matter more than their stated positions. Never split the difference -- no deal is better than a bad deal.

## Scoring

**Goal: 10/10.** Score 1 point per satisfied Quick Diagnostic row (6 rows), plus up to 4 points for execution quality: emotions labeled out loud (+1), "That's right" earned not "You're right" (+1), no "Why?" / no splitting the difference / no chasing "yes" (+1), at least one Black Swan surfaced (+1). Bands: **9-10** = audit delivered, calibrated questions and BATNA prepared, "That's right" achieved, Black Swans hunted; **5-6** = some prep but arguing the position or chasing "yes"; **<=3** = no audit, no BATNA, splitting the difference. Always state the current score and the specific gaps to reach 10/10.

## Framework

### 1. Tactical Empathy

**Core concept:** Consciously imagine yourself in the counterpart's situation, then vocalize their perspective to create trust and openness.

**Why it works:** When people feel understood, brain chemistry shifts toward trust and cooperation, short-circuiting defensive reactions. Empathy is not agreement -- you can understand their position while advocating your own.

**Key insights:**
- Before responding, ask: "What is their world like right now?"
- Articulate their situation, pressures, and fears before stating your position
- Empathy must be genuine, not performed -- people detect fakeness instantly
- Unconditional positive regard: respect them as a person regardless of disagreement
- Emotions are contagious -- stay calm and positive; slow pace enables clear thinking

**Product applications:**

| Context | Application | Example |
|---------|-------------|---------|
| **Customer support** | Acknowledge frustration before solving | "I understand this outage is affecting your team's deadline" |
| **Sales calls** | Voice the prospect's pressures | "It sounds like you're under pressure to show results this quarter" |
| **Pricing conversations** | Acknowledge budget constraints upfront | "I know adding another tool to the stack feels risky right now" |

**Copy patterns:**
- "I understand you're dealing with..."
- "It seems like this is creating pressure for your team..."
- "Before we talk about next steps, I want to make sure I understand where you're coming from..."

See [references/techniques.md](references/techniques.md) for the full 21-technique reference -- each section below points to the part you need at the moment you need it. Open it now for The Power of Apology and Pause, which has no section here.

### 2. Mirroring

**Core concept:** Repeat the last 1-3 critical words your counterpart said, with a curious, upward-inflecting tone, then go silent.

**Why it works:** Mirroring signals deep listening, creating familiarity and rapport. It prompts elaboration without direct questions, revealing more than the counterpart intended to share.

**Key insights:**
- Repeat the key or emotion-laden words back as a gentle question
- Wait silently (4+ seconds) for them to expand
- Works in person, on the phone, and in written communication
- The simplest technique, but often the most effective for information gathering

**Product applications:**

| Context | Application | Example |
|---------|-------------|---------|
| **Discovery calls** | Mirror key concerns to get elaboration | Client: "The timeline is tight." You: "The timeline is tight?" |
| **User interviews** | Encourage deeper explanation of pain | User: "It's just frustrating." You: "Frustrating?" |
| **Objection handling** | Reflect to find the root cause | "Doesn't fit your budget?" |

**Copy patterns:**
- "[Key phrase they used]?" (with question mark)
- "You mentioned [their exact words]..."
- "When you say [mirror], what does that look like?"

### 3. Labeling

**Core concept:** Identify and verbalize the counterpart's emotions or perspective using neutral phrases: "It seems like...", "It sounds like...", "It looks like..."

**Why it works:** Naming emotions validates them -- labeling negative emotions diffuses their power, labeling positive emotions reinforces them. The tentative phrasing gives room to correct you, which deepens the conversation either way.

**Key insights:**
- Always use third-person phrasing ("It seems like..."), never "I think you..."
- After labeling, be silent -- let them respond
- A wrong label still pays: their correction is valuable information
- Watch for emotional shifts that signal you've hit the mark

**Product applications:**

| Context | Application | Example |
|---------|-------------|---------|
| **Customer complaints** | Name the frustration before solving | "It sounds like you feel let down by 
03

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (5)

MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/37signals-way
.agents/skills/37signals-way
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/architecture-optimization
.agents/skills/architecture-optimization
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/blue-ocean-strategy
.agents/skills/blue-ocean-strategy
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/clean-architecture
.agents/skills/clean-architecture
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/clean-code
.agents/skills/clean-code
Why it matters. link not followed

Gates applied: no_behavioural_pass.

Audited 2026-10-10 · audit v0.4.1 · source sha c502026d022afull audit observations/trust-audit/skill/wondelai__negotiation.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-10c502026d022aCAUTIONB89first audit
05

Questions

What does the Negotiation skill do?

Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.

Is Negotiation safe to install?

With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.

What can Negotiation access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (c502026d022a), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement