Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Goal Engine

ASecurity

Use for mission: define, prioritize, --tick, progress, scan.

5 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentspythongobashapiperformance

Works with

cliapi

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add openamer/openamer --skill goal-engine --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Goal Engine?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Goal Engine
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/openamer-goal-engine/badge)](https://www.skillsdirectory.com/skills/openamer-goal-engine)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: goal-engine
description: 'Use for mission: define, prioritize, --tick, progress, scan.'
tags:
  - missions
  - goals
  - tasks
  - prioritization
  - auto-execution
  - autonomous
usage: |
  Nutze `goal-engine.py` für selbstständige Missionsplanung und Task-Ausführung.
  Daten liegen in `.goal-engine/missions.json` im Home-Verzeichnis.
  Der Cron-Job läuft alle 30 Minuten und führt den nächsten Task aus.
---

# Goal Engine — Autonomous Mission Planning

Vollständiges System für selbstständige Missions-Definition, Auto-Task-Generierung, Priorisierung und Self-Execution.

## CLI-Übersicht

```bash
# Mission definieren (auto-generiert Goals + Tasks)
python scripts/goal-engine.py --define 'Mission Name' 'Beschreibung'

# Alle Missionen nach Priorität sortiert anzeigen
python scripts/goal-engine.py --list

# Automatische Priorisierung (nach Impact + Dringlichkeit)
python scripts/goal-engine.py --prioritize

# Wichtigsten nächsten Task anzeigen
python scripts/goal-engine.py --next

# Nächsten Task automatisch ausführen (self-execution tick)
python scripts/goal-engine.py --tick

# Fortschrittsreport anzeigen
python scripts/goal-engine.py --progress

# Mission/Goal/Task als erledigt markieren
python scripts/goal-engine.py --complete <id>

# Analyse: Scripts, Skills, offene Tasks, Gaps
python scripts/goal-engine.py --scan

# Manuelles Goal hinzufügen
python scripts/goal-engine.py --add-goal <mission_id> 'Beschreibung'

# Manuellen Task hinzufügen
python scripts/goal-engine.py --add-task <goal_id> 'Beschreibung' --priority 4 --script log-analyzer.py
```

## Datenstruktur

```
~/.goal-engine/
├── missions.json    # Alle Missionen mit Goals, Tasks, Prioritäten
└── goal-engine.log  # Aktivitätslog
```

### missions.json Schema

```json
{
  "missions": [
    {
      "id": "m_abc12345",
      "name": "OpenAmer #1",
      "description": "OpenAmer zum besten AI Agent auf Windows machen",
      "priority": 5,
      "status": "active",
      "created": "2026-08-22T00:00:00",
      "deadline": null,
      "goals": [
        {
          "id": "g_abc12345",
          "description": "Analyse & Grundlagen",
          "progress": 0,
          "status": "pending",
          "tasks": [
            {
              "id": "t_abc12345",
              "description": "Analysiere Logs auf Fehler-Patterns",
              "status": "pending",
              "priority": 5,
              "script_hint": null
            }
          ]
        }
      ]
    }
  ]
}
```

## Auto-Task-Generierung

Der `--define` Befehl analysiert die Missionsbeschreibung auf Schlüsselwörter:

| Schlüsselwörter          | Generierte Goals                  |
|--------------------------|-----------------------------------|
| Stabilität, Crash, Robust | Analyse, Implementierung          |
| Performance, Speed        | Optimierung, Überwachung          |
| Integration, API          | Integration, Implementierung      |
| Überwachung, Monitor      | Überwachung, Analyse              |
| Automatisierung, Workflow | Implementierung, Integration      |

Pro Goal werden 2-3 Tasks generiert (zufällig aus Template-Pools).

## Priorisierungslogik (`--prioritize`)

Jede Mission bekommt eine Priorität (1-5) basierend auf:

1. **Impact**: Anzahl offener Tasks (mehr = höherer Impact)
2. **Dringlichkeit**: Alter der Mission (je älter, desto dringender)
3. **Deadline**: Falls gesetzt → näher am Termin = höhere Priorität
4. **Progress-Boost**: Falls ≥80% erledigt → +1 Priorität (Abschluss fördern)

Die Priorität wird als `★`-Sterne in der Liste dargestellt.

## Self-Execution Tick (`--tick`)

Der Tick führt den wichtigsten nächsten Task aus:

1. Findet den Task mit der höchsten Priorität (Mission-Prio × Task-Prio)
2. Markiert ihn als `running`
3. Sucht nach einem passenden Script (anhand `script_hint` oder Keyword-Matching)
4. Falls kein Script gefunden → Fallback-Analyse
5. Subprocess mit 300s Timeout
6. Markiert als `done` oder `failed`
7. Aktualisiert Goal-Progress
8. Cron-Job führt `--tick` alle 30 Minuten aus

## Exit-Codes

| Code | Bedeutung              |
|------|------------------------|
| 0    | Erfolg / nichts zu tun |
| 1    | Keine offenen Tasks    |
| 2    | Fehler / ID nicht gef. |

## Cron-Job

Ein Cron-Job (addiert via `jobs.json` im OpenAmer-Cron-Verzeichnis) führt `--tick` alle 30 Minuten aus:

```json
{
  "id": "goal_engine_tick",
  "name": "Goal Engine Tick",
  "script": "goal-engine.py --tick",
  "schedule": { "kind": "cron", "expr": "*/30 * * * *" }
}
```

## Workflow

1. **Mission definieren**: `--define 'Name' 'Beschreibung'`
2. **Priorisieren**: `--prioritize` (automatisch nach Impact + Dringlichkeit)
3. **Tick starten**: `--tick` oder Cron macht das automatisch alle 30min
4. **Fortschritt checken**: `--progress` (mit ETA und Blockers)
5. **Abschließen**: `--complete <id>` (Mission, Goal oder Task)
6. **Scannen**: `--scan` (Scripts, Skills, Gaps analysieren)

## Fehlerbehebung

- **Script findet kein passendes Script**: Manuell via `--add-task <goal_id> 'Task' --script <name.py>` verknüpfen
- **missions.json beschädigt**: Wird automatisch zurückgesetzt (leere Liste)
- **Cron läuft nicht**: `--scan` zeigt ob Goal-Engine Cron-Job fehlt
- **Task timeout**: Standard 300s, kann in der `subprocess.run()`-Zeile angepasst werden

Attribution

openameropenamer
View sourceSee grades on GitHubMore from openamer →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →