Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/Oracle Agent Spec Expert
Design framework-agnostic AI agents using Oracle's Open Agent Specification for portable, interoperable agentic systems with JSON/YAML definitions
Passed 18 of 21 test cases with the skill, and 5 of 21 without it.
and 28 more in the full report
14 fixed5 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
A data pipeline defined as a WorkflowNode in Oracle Agent Spec needs to specify an explicit failure recovery behavior when a step encounters an error. What field and value configure automatic step retries?
| Checked | Without skill | With skill |
|---|---|---|
| Includes error_handling field in WorkflowNode definition | Missed | Passed |
| Sets error_handling value to retry | Missed | Passed |
The instructions your model reads when the skill loads.
Master Oracle's Open Agent Specification (Agent Spec) to design framework-agnostic, declarative AI agents that can be authored once and deployed across multiple frameworks and runtimes.
Framework-agnostic declarative language for defining agentic systems, building blocks for standalone agents and structured workflows, plus composition patterns for multi-agent systems.
Key Innovation: Decouple design from execution - write agents once, run anywhere.
Release: Technical report published October 2025 (arXiv:2510.04173)
The Problem: Fragmented agent development - each framework requires different implementation.
The Solution: Unified representation - Agent Spec defines structure and behavior in JSON/YAML that any compatible runtime can execute.
Benefit: Author agents once → Deploy across frameworks → Reduce redundant development.
Agent Spec defines conceptual building blocks (components) that make up agent-based systems.
Key Property: All components are trivially serializable to JSON/YAML.
Purpose: Text generation via LLM
Definition:
type: LLMNode
name: "text_generator"
model: "claude-sonnet-4-5"
system_prompt: "You are a helpful assistant"
test cases passed, vs 5 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.