CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude/skills/create-environment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Actionable and well-structured, with executable YAML and concrete MCP tool calls, but held back by redundant repetition of the Production-safeguards note, a largely duplicated multi-environment example, and a missing post-create verification step for the batch multi-environment workflow.

Suggestions

State the Production-safeguards behavior once (e.g., in Environment Types) and remove the repeats in Performance Notes and Troubleshooting, keeping Troubleshooting focused on the DUPLICATE_IDENTIFIER remediation.

Compress the Multi-Environment Setup example to only the fields that differ per environment (name, identifier, type, variable values) instead of re-rendering three near-identical YAML blocks.

Add an explicit post-create verification step for batch creation, e.g., 'After creating all environments, call harness_list to confirm each identifier exists' — this also gives the batch workflow the missing validation checkpoint.

DimensionReasoningScore

Conciseness

Mostly efficient with no explanations of known concepts, but the Production-safeguards point is repeated three times ('Live production environments (enables additional safeguards)', 'it enables additional safeguards like deployment freezes', 'Production type enables deployment freeze and approval guardrails') and the Multi-Environment Setup section re-renders near-identical YAML from Environment Structure.

3 / 5

Actionability

Provides complete copy-paste YAML and exact MCP tool invocations ('Call MCP tool: harness_create' with 'resource_type: environment', org_id, project_id, body), covering single-env, multi-env, and override cases. Minor gaps: 'body: <environment YAML>' is a placeholder, and the multi-environment flow never states whether to issue three separate harness_create calls.

4 / 5

Workflow Clarity

The 4-step Instructions sequence is clear and there is a pre-flight check ('Verify that manifest override paths exist in the referenced repository before creating') plus DUPLICATE_IDENTIFIER remediation, but the batch multi-environment creation workflow has no post-create verification checkpoint — the batch-operation validation cap applies.

3 / 5

Progressive Disclosure

No bundle files exist and the body is well-organized with clear sections (Instructions, Environment Structure, Environment Types, Multi-Environment Setup, Creating via MCP, Examples, Performance Notes, Troubleshooting), with content appropriately placed inline for a single-task skill; the redundant sections are the only organization gap.

4 / 5

Total

14

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly states capabilities, the use-when clause, and concrete trigger phrases in third person. Minor improvements possible: drop the overly generic 'environment variables' trigger or scope it ('Harness environment variables'), and mention list/update coverage if those operations are in scope.

DimensionReasoningScore

Specificity

Lists several concrete actions — '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)' — but has minor coverage gaps: the list and update operations covered in the body are absent from the description.

4 / 5

Completeness

Clearly answers both what ('Generate Harness Environment YAML... create via MCP. Supports PreProduction and Production types with environment variables, manifest overrides, and multi-environment setup') and when ('Use when asked to create an environment, set up staging, configure production, define deployment targets, or manage environment overrides'), with concrete trigger phrases appended.

5 / 5

Trigger Term Quality

Explicit trigger phrases ('create environment, deployment environment, setup dev, setup staging, setup production, environment variables, environment overrides') give good natural-keyword coverage, but common variations like 'new environment', 'create prod', or 'environment configuration' are missing.

4 / 5

Distinctiveness Conflict Risk

The Harness/MCP environment niche ('Harness Environment YAML', 'deployment targets') is mostly distinct, but the generic 'environment variables' trigger phrase creates minor overlap risk with env-var or secrets-management skills.

4 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

harness/harness-ai

Path

plugins/claude/skills/create-environment/SKILL.md

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.