Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/building-agents-core
Core concepts for goal-driven agents - architecture, node types, tool discovery, and workflow overview.
Passed 15 of 20 test cases with the skill, and 4 of 20 without it.
and 12 more in the full report
12 fixed4 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am defining a node that takes structured research data and formats it into a summary paragraph without calling any external tools or functions. Which node type should be assigned?
| Checked | Without skill | With skill |
|---|---|---|
| sets the node type field to llm_generate | Missed | Passed |
The instructions your model reads when the skill loads.
Foundational knowledge for building goal-driven agents as Python packages.
Agents are built as Python packages:
exports/my_agent/
├── __init__.py # Package exports
├── __main__.py # CLI (run, info, validate, shell)
├── agent.py # Graph construction (goal, edges, agent class)
├── nodes/__init__.py # Node definitions (NodeSpec)
├── config.py # Runtime config
└── README.md # Documentation
Key Principle: Agent is visible and editable during build
Success criteria and constraints (written to agent.py)
goal = Goal(
id="research-goal",
name="Technical Research Agent",
description="Research technical topics thoroughly",
success_criteria=[
SuccessCriterion(
id="completeness",
description="Cover all aspects of topic",
test cases passed, vs 4 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.