# Elicitly

> ai.elicitly/elicitly — ai-elicitly-elicitly. Use this tool when you need to refine AI agent performance through human oversight and feedback, solving issues of accuracy and reliability in AI decision-making. It provides a human-in-the-loop interface for confirming and forming dialogs, along with a capability doctor for expert input. This tool is ideal for use cases requiring precise AI output and iterative improvement, accepting AI-generated responses as input and producing validated outputs.

Canonical page: https://skillsregistry.net/skills/ai-elicitly-elicitly  
JSON: https://api.skillsregistry.net/v1/skills/ai-elicitly-elicitly

## Description

Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 0.4.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.elicitly%2Felicitly)
- **Repository:** <https://github.com/elicitly/elicitly>

## 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": "ai-elicitly-elicitly"
    }
  }
}
```

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