Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/hive-concepts
Core concepts for goal-driven agents - architecture, node types (event_loop, function), tool discovery, and workflow overview.
Passed 22 of 22 test cases with the skill, and 6 of 22 without it.
and 33 more in the full report
16 fixed6 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
If a research node is the target of a revision feedback loop, what parameter on NodeSpec controls how many total times that node can be re-entered during a graph run?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies max_node_visits as the parameter controlling maximum node re-entries. | Missed | Passed |
| Recommends setting max_node_visits greater than 1 for feedback loop target nodes. | 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 6 / 22 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.