Best practices, patterns, and examples for building goal-driven agents. Includes pause/resume architecture, hybrid workflows, anti-patterns, and handoff to testing.
SkillScore95Maintained
Automatic
◆AI Engineer pack
Last verified 8/18/2026
What it changes
Passed 21 of 22 test cases with the skill, and 7 of 22 without it.
Without skill32%
With skill95%
Checks it passed that the model alone missed
Rejects deferring file writes to a final export call.
Recommends using mcp__agent-builder__test_node for node validation.
Recommends writing files immediately to disk during agent construction.
and 14 more in the full report
14 fixed7 passed either way1 still failing0 broke
Pass-rate lift
+64 pp
Tokens
+110%
Agent turns
0%
Response time
-48%
Model gemini-3.6-flashMeasured 8/18/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
When defining entry points for resuming an agent after a pause node named 'await-approval', what key format should be used in the entry points dictionary?
What was checked, without and with the skill
Checked
Without skill
With skill
Formats the entry point dictionary key as the pause node ID suffixed with '_resume'.
Missed
Passed
case-14 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md486 linessingle file
Building Agents - Patterns & Best Practices
Design patterns, examples, and best practices for building robust goal-driven agents.
Prerequisites: Complete agent structure using building-agents-construction.
Practical Example: Hybrid Workflow
How to build a node using both direct file writes and optional MCP validation:
# 1. WRITE TO FILE FIRST (Primary - makes it visible)
node_code = '''
search_node = NodeSpec(
id="search-web",
node_type="llm_tool_use",
input_keys=["query"],
output_keys=["search_results"],
system_prompt="Search the web for: {query}",
tools=["web_search"],
)
'''
Edit(
file_path="exports/research_agent/nodes/__init__.py",
old_string="# Nodes will be added here",
new_string=node_code
)
print("✅ Added search_node to nodes/__init__.py")
print("📁 Open exports/research_agent/nodes/__init__.py to see it!")
# 2. OPTIONALLY VALIDATE WITH MCP (Secondary - bookkeeping)
validation = mcp__agent-builder__test_node(
node_id="search-web",
test_input='{"query": "python tutorials"}',
mock_llm_response='{"search_results": [...mock results...]}'
)
print(f"✓ Validation: {validation['success']}")