autonomous-execution

Trigger ARAYA workflows from natural language without explicit run commands.

3|Updated May 28, 2026

Search Tags:#workflow #routing #ai #orchestration #observability #persistence #autonomous

Ready to run

npx skills add https://github.com/mahg-es/araya --skill autonomous-execution-mahg-es

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: autonomous-execution
Source: https://github.com/mahg-es/araya/tree/main/skills/autonomous-execution
Command: npx skills add https://github.com/mahg-es/araya --skill autonomous-execution-mahg-es

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Natural language should trigger ARAYA execution. Commands become optional. Delegation progress is visible. Run records persist for audit.

Core Features & Use Cases

Natural Language Triggers: ARAYA recognizes intent from natural language and starts the appropriate workflow without /araya run.
Delegation Observability: During execution, The Professor sees: current run ID, current phase, current agent, completed tasks / total tasks, blocked tasks (if any).
Run Persistence: Every run creates .araya/runs/{run_id}/run.json containing run metadata, start/end times, workflow, agents, status, artifacts, errors, and outcome.
Provider-Aware Routing: Before delegation, check rate-limit history, recent usage, known failures to avoid providers near quota.
Usability Gate: A feature is complete only when it can be used, solves a real problem, can be demonstrated end-to-end, and reduces manual work.

Quick Start

Invoke natural language execution by speaking a command such as 'Manu, assess mahg-pms' to trigger the appropriate workflow.

Frequently Asked Questions about autonomous-execution

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I trigger AI workflows using natural language commands?▼

You can trigger AI workflows by speaking a natural language command such as 'Manu, assess mahg-pms'. The system recognizes your intent and starts the appropriate workflow automatically without needing explicit run commands.

What information is visible during multi-agent delegation observability?▼

During multi-agent delegation observability, you can see the current run ID, execution phase, active agent, completed tasks versus total tasks, and any blocked tasks. This provides real-time visibility into your workflow execution progress.

How are AI workflow run records persisted for long-term audit trails?▼

Every workflow run creates a persistent record stored in .araya/runs/{run_id}/run.json. This file contains run metadata, start and end times, workflow details, agents, status, artifacts, errors, and the final outcome for long-term audit trails.

How does provider-aware routing prevent hitting API rate limits during orchestration?▼

Provider-aware routing checks rate-limit history, recent usage, and known failures before delegation. This avoids routing tasks to providers near their quota, ensuring continuous AI workflow orchestration without hitting API rate limits.

What are the requirements for a feature to pass the usability gate in autonomous execution?▼

To pass the usability gate in autonomous execution, a feature must be usable, solve a real problem, be demonstrable end-to-end, and reduce manual work. These criteria ensure features provide practical value.

Does autonomous-execution require explicit run commands to start ARAYA workflows?▼

No, autonomous-execution does not require explicit run commands to start ARAYA workflows. It applies natural language triggers to recognize intent and initiate execution automatically, making commands optional.