create-infrastructure
Generate Harness Infrastructure Definition YAML for deployment targets and create via MCP. Use when user says "create infrastructure", "infrastructure definition", "k8s cluster config", "deployment target", or wants to configure where workloads run.
65
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/claude/skills/create-infrastructure/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly defines its scope within the Harness ecosystem and provides explicit trigger guidance. Its main weakness is that the 'what' portion could be more specific about the concrete actions it performs beyond generating YAML and creating via MCP. Overall it performs well across all dimensions.
Suggestions
Expand the specificity of capabilities by listing more concrete actions, e.g., 'configure Kubernetes namespaces, set release names, define connector references, specify cloud provider settings'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Harness Infrastructure Definition YAML) and mentions some actions ('generate', 'create via MCP'), but doesn't list multiple specific concrete actions like configuring specific resource types, setting up namespaces, or defining connectors. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate Harness Infrastructure Definition YAML for deployment targets and create via MCP) and 'when' (explicit 'Use when' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'create infrastructure', 'infrastructure definition', 'k8s cluster config', 'deployment target', and the conceptual phrase 'where workloads run'. These cover multiple natural ways a user might phrase their request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Harness Infrastructure Definition YAML, which is a distinct niche. The trigger terms like 'infrastructure definition' and 'k8s cluster config' in the Harness context are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid reference skill with excellent actionability — every infrastructure type has a complete, ready-to-use YAML template and the MCP invocation is clearly specified. The main weaknesses are the lack of explicit validation steps in the workflow (e.g., verify connector exists before creating infrastructure) and the monolithic structure that inlines all 9 infrastructure types rather than splitting common vs. advanced types across files.
Suggestions
Add an explicit validation step in the workflow, e.g., 'Verify connector exists by calling harness_get with resource_type connector before creating infrastructure' to create a feedback loop for the most common failure modes.
Consider splitting less common infrastructure types (Pdc, Asg, GoogleCloudFunctions, AzureWebApp) into a separate INFRA_TYPES_REFERENCE.md file, keeping only the top 3-4 most common types inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with template-driven content, but the sheer number of infrastructure type templates (9 types) makes it lengthy. The examples section at the bottom is somewhat redundant given the templates already demonstrate each type. However, it avoids explaining basic concepts Claude would know. | 2 / 3 |
Actionability | Each infrastructure type has a complete, copy-paste-ready YAML template with realistic field values. The MCP call parameters are explicitly specified, and the troubleshooting section provides specific error codes with concrete fixes. | 3 / 3 |
Workflow Clarity | The 4-step workflow at the top is clear and sequenced, and prerequisites are mentioned. However, there are no explicit validation checkpoints — no step to verify the connector/environment exists before proceeding, and no feedback loop for handling creation failures despite the troubleshooting section listing common errors. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers for each infrastructure type, but all 9 templates are inline in a single file, making it quite long. The less common types (Pdc, GoogleCloudFunctions, Asg) could be split into a reference file, with the main skill covering only the most common types. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- harness/harness-ai
- Commit
a000afa
- Reviewed
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.