# parley

> Use this tool when you need to facilitate cross-session conversations between peer agents, enabling them to share knowledge and context across multiple turns. Parley solves the problem of isolated agent interactions by providing a shared memory, allowing agents to ask each other questions and build on previous conversations. It takes in natural language inputs and outputs relevant information from other projects, making it ideal for use cases that require collaborative agent dialogue.

Canonical page: https://skillsregistry.net/skills/mischasigtermans-parley  
JSON: https://api.skillsregistry.net/v1/skills/mischasigtermans-parley

## Description

Cross-session peer agents for Claude Code. Ask one project what another knows, with full context and memory across turns.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [GitHub](https://github.com/mischasigtermans/parley)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "mischasigtermans-parley"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mischasigtermans-parley` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mischasigtermans-parley/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt