# agentforge-mcp

> Use this tool when you need to refine vague coding requests into precise, well-structured prompts for AI agents, solving issues of ambiguity and misinterpretation. It takes rough requests as input and outputs high-quality, scored prompts, calibrated on over 1,000 real coding cases. Ideal for use when working with coding agents to ensure accurate and efficient task execution.

Canonical page: https://skillsregistry.net/skills/sciscale-studio-agentforge-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sciscale-studio-agentforge-mcp

## Description

Turn rough requests into rigorously structured prompts for any coding agent. Quality-scored to ≥90/100 across 12 dimensions, calibrated on 1,000+ real coding cases.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-25

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/e03n1uxf4j)
- **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": "sciscale-studio-agentforge-mcp"
    }
  }
}
```

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