create-environment
Generate Harness Environment YAML for deployment targets and create via MCP. Supports PreProduction and Production types with environment variables, manifest overrides, and multi-environment setup (dev, staging, prod). Use when asked to create an environment, set up staging, configure production, define deployment targets, or manage environment overrides. Trigger phrases: create environment, deployment environment, setup dev, setup staging, setup production, environment variables, environment overrides.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong skill description that clearly articulates what the skill does (generate Harness Environment YAML with specific capabilities), when to use it (explicit 'Use when' clause with multiple scenarios), and includes a comprehensive set of trigger phrases. The description is specific to the Harness platform, making it highly distinctive, and covers natural language variations users would employ.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate Harness Environment YAML, create via MCP, supports PreProduction and Production types, environment variables, manifest overrides, and multi-environment setup with specific examples (dev, staging, prod). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate Harness Environment YAML, create via MCP, supports PreProduction/Production types with env vars and manifest overrides) and 'when' (explicit 'Use when...' clause plus a dedicated 'Trigger phrases' section listing specific scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create environment', 'deployment environment', 'setup dev', 'setup staging', 'setup production', 'environment variables', 'environment overrides'. These are phrases users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Harness-specific environment YAML generation via MCP. The mention of Harness, specific environment types (PreProduction/Production), and manifest overrides makes it very unlikely to conflict with generic environment or deployment skills. | 3 / 3 |
Total | 12 / 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 skill provides solid, actionable YAML templates and MCP tool usage for creating Harness environments. Its main weaknesses are the lack of validation checkpoints in the workflow (e.g., checking if an environment exists before creating, verifying manifest paths) and some mild redundancy in the examples and performance notes sections. Overall it's a functional skill that could be tightened and improved with explicit verification steps.
Suggestions
Add an explicit validation step to the workflow: list existing environments before creating to avoid DUPLICATE_IDENTIFIER errors, and integrate this as a numbered step rather than relegating it to troubleshooting.
Remove or consolidate the 'Examples' section (vague bullet points) and 'Performance Notes' into the main workflow steps where they're actionable, reducing redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like 'Examples' with vague bullet points that don't add value, and 'Performance Notes' that partially restate obvious things. The multi-environment setup section is somewhat redundant given the main structure already shows the pattern. | 2 / 3 |
Actionability | Provides complete, copy-paste ready YAML structures, concrete MCP tool calls with specific parameters, and covers all variable types (String, Number, Secret). The examples are fully formed and executable. | 3 / 3 |
Workflow Clarity | The 4-step instruction sequence is clear, but there are no validation checkpoints between generating YAML and pushing via MCP. The troubleshooting section mentions DUPLICATE_IDENTIFIER but doesn't integrate a check-before-create step into the workflow. For a create operation that could fail, a verification step (e.g., list first, then create) should be explicit in the workflow. | 2 / 3 |
Progressive Disclosure | Content is reasonably structured with clear sections, but everything is inline in a single file. The multi-environment setup and overrides examples could be split into referenced files for a cleaner overview. However, given no bundle files exist, the inline approach is acceptable but slightly long. | 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.