# goal-engine

> Use this tool when you need to implement persistent goal-tracking in agentic CLIs, enabling agents to work towards a condition across multiple turns. It solves problems of task persistence and external evaluation, allowing for efficient run-until-done loops. The goal-engine takes in a goal condition and agent output, and returns an evaluation of progress towards the goal, facilitating continuous task execution until completion.

Canonical page: https://skillsregistry.net/skills/melihzafer-mcp-goal  
JSON: https://api.skillsregistry.net/v1/skills/melihzafer-mcp-goal

## Description

Provides persistent goal-tracking with external evaluation for agentic CLIs, enabling run-until-done loops where an agent works across turns until a condition is met.

## 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:** other
- **Updated:** 2026-06-12

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hxrbirgxd4)
- **Repository:** <https://github.com/melihzafer/mcp-goal>

## 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": "melihzafer-mcp-goal"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/melihzafer-mcp-goal` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/melihzafer-mcp-goal/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