# AgentForge

> Use this tool when you need to refine informal development task descriptions into high-quality prompts for AI coding agents. AgentForge solves the problem of suboptimal prompt creation, providing detailed and optimized outputs that improve AI coding efficiency. It takes in informal task descriptions as input and outputs refined prompts, ideal for use cases where clear and effective communication with AI agents is crucial.

Canonical page: https://skillsregistry.net/skills/agentforge  
JSON: https://api.skillsregistry.net/v1/skills/agentforge

## Description

AgentForge converts informal development task descriptions into detailed, high-quality prompts optimized for AI coding agents such as Claude Code, Cursor, and Codex. The service uses a proprietary Prompt Engine and Judge Engine trained on thousands of real scenarios to score and refine prompts across twelve quality dimensions. A free daily preview is available, with subscription plans for unlimited access and auto-refinement.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentforge)
- **Repository:** <https://github.com/sciscale-studio/agentforge-mcp>

## 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": "agentforge"
    }
  }
}
```

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