pulumi-neo
Manages cloud infrastructure through natural language conversations with Pulumi Neo, an AI agent for platform engineers. Enables infrastructure analysis, resource provisioning, stack deployment, and configuration management via conversational AI. Use when creating Neo tasks, requesting infrastructure analysis, automating cloud deployments, managing infrastructure as code (IaC), provisioning AWS/Azure/GCP resources, or managing infrastructure through natural language prompts.
100
Does it follow best practices?
Validation for skill structure
Evaluation results
98%
43%Automate Daily Infrastructure Health Checks with Pulumi Neo
Non-blocking task creation and org detection
Uses Python script
0%
100%
No-poll flag present
0%
100%
Org auto-detection
100%
100%
Stack name provided
0%
100%
Stack project provided
0%
100%
Task ID captured
100%
75%
PULUMI_ACCESS_TOKEN referenced
100%
100%
Org fallback handling
100%
100%
Infra analysis message
100%
100%
README prerequisites
100%
100%
Without context: $0.2922 · 1m 45s · 14 turns · 21 in / 5,898 out tokens
With context: $0.5108 · 1m 30s · 19 turns · 3,741 in / 4,735 out tokens
100%
78%Build a Pulumi Neo Task Monitor with Approval Handling
Approval detection via event inspection
Event-based approval detection
40%
100%
Checks agentResponse type
0%
100%
Checks tool_calls in eventBody
0%
100%
Matches approval_request function name
0%
100%
Extracts approval_request_id from arguments
0%
100%
Correct Accept header
0%
100%
Correct events endpoint
0%
100%
Does NOT rely on task status
90%
100%
monitor_output.json produced
87%
100%
Scans events in reverse
0%
100%
Without context: $0.3149 · 1m 34s · 18 turns · 22 in / 5,552 out tokens
With context: $0.5490 · 1m 30s · 19 turns · 10,978 in / 5,399 out tokens
100%
60%Create a Pulumi Neo Integration Library
Entity context and direct API request construction
Correct base URL
0%
100%
Accept header value
0%
100%
Stack entity has name field
25%
100%
Stack entity has project field
30%
100%
Repository forge field present
0%
100%
Valid forge values
62%
100%
GitLab forge demonstrated
100%
100%
entity_diff structure
0%
100%
No pull_request add via API
100%
100%
message.type field
0%
100%
test_payloads runs without credentials
100%
100%
Without context: $0.7195 · 3m 22s · 34 turns · 138 in / 11,407 out tokens
With context: $0.8087 · 2m 15s · 26 turns · 11,202 in / 8,109 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.