# Empathy Mapping

> >

- **Type:** Skill
- **Install:** `agentstack add skill-skyf0xx-better-thinking-empathy-mapping`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [skyf0xx](https://agentstack.voostack.com/s/skyf0xx)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [skyf0xx](https://github.com/skyf0xx)
- **Source:** https://github.com/skyf0xx/better-thinking/tree/master/skills/empathy-mapping
- **Website:** https://zenbin.org/p/better-thinking

## Install

```sh
agentstack add skill-skyf0xx-better-thinking-empathy-mapping
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Empathy Mapping

Reconstruct what another party sees, hears, thinks, feels, and needs, from their position rather than from your own assumptions about them.

## Why

Predicting others' behavior or designing for their needs from your own vantage systematically imports your own priorities and blind spots. Deliberately reconstructing their actual situation catches what a self-referential guess misses.

## Use when / Don't use when

- **Use when:** designing for users; preparing for a negotiation or difficult conversation; predicting a stakeholder's reaction.
- **Don't use when:** direct data — an actual interview, actual observed behavior — is available; use that over a constructed map.

## Inputs → Outputs

- **Inputs:** a specific other party — an individual, role, or persona.
- **Outputs:** a structured picture of what they perceive, think, feel, and need, distinguished from what you assume or wish they thought.

## Principles

- Ground the map in actual evidence about this party where available — a map built on stereotype is worse than useless.
- Separate what they say from what they likely think or feel — these often diverge.
- Their needs are usually more stable and more legitimate than their stated positions — map both, but weight needs higher for solution design.
- The map is a hypothesis to test against real behavior, not a conclusion.

## Procedure

1. Specify the party precisely — a real individual or a well-evidenced persona, not a vague stereotype.
2. What do they see and hear: their actual environment, information, and context.
3. What do they think and feel: their likely internal state, informed by evidence, not projection.
4. What do they say and do: their observable behavior and statements, including where these seem to conflict with the thinks/feels layer.
5. What do they need: the underlying need behind their stated wants.
6. Use the map to generate hypotheses; verify against real interaction where possible, and flag which parts of the map remain unverified.

## Common mistakes

- Building the map from assumption or stereotype instead of evidence.
- Conflating what they say with what they need.
- Treating the finished map as settled fact rather than a testable hypothesis.

## Examples

- A UX research persona built from interview data.
- Preparing for a negotiation with an unfamiliar counterparty.
- A policy designed around a mapped constituency's actual situation.

## Related

- [[active-listening]] — the real-time counterpart used once actual interaction begins.
- [[stakeholder-mapping]] — the group-level version of this same reconstruction.
- [[interview-synthesis]] — the mechanism for grounding this map in real evidence.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [skyf0xx](https://github.com/skyf0xx)
- **Source:** [skyf0xx/better-thinking](https://github.com/skyf0xx/better-thinking)
- **License:** MIT
- **Homepage:** https://zenbin.org/p/better-thinking

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-skyf0xx-better-thinking-empathy-mapping
- Seller: https://agentstack.voostack.com/s/skyf0xx
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.