skills.rest
epieczko
epieczkoCOMMUNITY
Explore all skills by this author →
GitHub

agent.run

Execute Betty agents by loading manifests, generating prompts, invoking Claude API, and logging results.

2|Updated Oct 22, 2025
Search Tags:#automation#workflow#logging#agent#orchestration#Claude API
One-click install
npx skills add https://github.com/epieczko/betty --skill agent-run
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent.run
Source: https://github.com/epieczko/betty/tree/main/skills/agent.run
Command: npx skills add https://github.com/epieczko/betty --skill agent-run

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) components.

What problem does it solve?

This Skill executes registered Betty agents by orchestrating the complete lifecycle: loading manifests, generating Claude-friendly prompts, invoking the Claude API (or simulating), executing planned skills, and logging all results. It supports both iterative and oneshot reasoning modes, providing a reliable execution engine for agent-based automation.

Core Features & Use Cases

  • Load agent manifests from path or agent name
  • Generate Claude-optimized system prompts with capabilities and workflow patterns
  • Optional Claude API integration (with mock fallback for development)
  • Support for both iterative and oneshot reasoning modes
  • Skill selection and execution orchestration
  • Comprehensive execution logging to agent_logs/<agent>_<timestamp>.json
  • Structured JSON output for programmatic integration
  • Error handling with detailed diagnostics and telemetry

Quick Start

Run an agent by name: python3 skills/agent.run/agent_run.py api.designer "Design a REST API for user management"

Frequently Asked Questions about agent.run

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

FAQPage Schema
How do I orchestrate and execute Betty agents end-to-end?▼

Agent orchestration loads manifests, generates Claude-optimized prompts, invokes the Claude API (with mock fallback), executes planned skills, and logs results. Run agents by name with a task description using the agent.run Skill to automate agent workflows.

Can I use agent.run with both iterative and oneshot reasoning modes?▼

Yes. Agent orchestration supports both iterative and oneshot reasoning modes, handling manifest validation, skill execution, and comprehensive logging for each mode to adapt to your workflow requirements.

What gets logged when an agent runs?▼

Structured JSON output logs to agent_logs/<agent>_<timestamp>.json with complete execution results, skill selections, API interactions, and error diagnostics for auditability and programmatic integration.

Do I need to call the Claude API directly, or can agent.run handle it?▼

Agent orchestration integrates with the Claude API but includes mock fallback for development and testing. You can run agents without live API calls or enable Claude integration for production workflows.

What dependencies does agent.run require?▼

Agent orchestration requires PyYAML to load and validate agent manifests. Ensure PyYAML is installed before executing agents to enable manifest parsing and workflow configuration.

Related Skills

Explore More Software Engineering Skills→
epieczkoepieczko

Skill Define

Validate and register skill manifests against the official schema.

Community
Basic
thiagofinchthiagofinch
79

executor

Orchestrate autonomous operations across ClickUp, N8N, and Google Drive.

Community
Advanced
terrazul-aiterrazul-ai

create-agent

Create Claude agent definitions with YAML frontmatter, system prompts, and templates.

Official
Advanced
ichuanichuan
1

deploy-caddy-reverse-proxy

Deploy Caddy reverse proxy with Let's Encrypt SSL and systemd integration.

Community
Advanced