Name: create-policy
Rating: 75.2 (1 reviews)
Author: harness

create-policy

Create OPA governance policies for Harness via MCP. Define policies that enforce compliance rules on pipelines, services, environments, feature flags, artifacts, code repositories, templates, SBOM, security tests, Terraform, GitOps, connectors, secrets, and more. Use when asked to create, write, fix, or explain an OPA policy, Rego rule, deny rule, governance policy, compliance rule, or policy-as-code for any Harness entity. Trigger phrases: create policy, OPA policy, governance policy, compliance rule, rego policy, deny rule, enforce policy, security policy, supply chain governance.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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.

The content is highly actionable and well-structured for progressive disclosure, with executable MCP calls, complete Rego examples, and a clean reference-file layout. The main weakness is mild redundancy between the Performance Notes and Troubleshooting sections that could be tightened.

Suggestions

De-duplicate the package-naming convention and 'validate syntax before submitting' guidance, which appears in both Performance Notes and Troubleshooting, into a single canonical location.

Make the Step 3 verification checkpoint explicit by instructing to confirm the new policy appears in a 'policy' list (and is attached to a policy_set) before reporting success.

Consider moving the four full 'Common Policy Patterns' Rego examples into the relevant entity reference files to keep SKILL.md as a lean overview, retaining only one or two representative inline examples.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with terse steps and minimal, complete code, but the 'Performance Notes' and 'Troubleshooting' sections repeat guidance (package naming convention and 'validate syntax before submitting' each stated twice) and four full Rego examples are inlined that could live in a reference file.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: concrete MCP tool calls with parameters (harness_create/harness_list with resource_type values), complete Rego code blocks with package declarations and msg returns, and a resource-type operations table covering the common cases.	5 / 5
Workflow Clarity	The three-step sequence (Identify, Create, Verify) includes an explicit verification checkpoint in Step 3 plus error-recovery troubleshooting, but the post-create validation is somewhat implicit (it lists compliance results without instructing to confirm the policy appears before proceeding), leaving a minor validation gap.	4 / 5
Progressive Disclosure	The body is a clear overview that pushes detailed schemas and patterns to 18 well-signaled, one-level-deep reference files (all verified present in references/), each with a one-line description, with only overview-level examples and a resource table kept inline.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is exemplary: it concisely states concrete capabilities, provides an explicit 'Use when' clause with natural trigger phrases, and carves out a distinct Harness-specific niche with low conflict risk. Voice is consistently third person with no over-claims.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions (create, write, fix, explain) and comprehensively enumerates the target entities (pipelines, services, environments, feature flags, artifacts, code repositories, templates, SBOM, security tests, Terraform, GitOps, connectors, secrets), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Clearly states what the skill does ('Create OPA governance policies for Harness via MCP...enforce compliance rules on...') and explicitly when to use it ('Use when asked to create, write, fix, or explain...'), with concrete trigger phrases answering both what and when.	5 / 5
Trigger Term Quality	Includes an explicit 'Trigger phrases:' list of nine natural phrases (create policy, OPA policy, governance policy, compliance rule, rego policy, deny rule, enforce policy, security policy, supply chain governance) plus synonyms in the 'Use when' clause, giving comprehensive coverage of terms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Harness OPA governance policies via MCP) with triggers tied to Harness-specific entities like SBOM, feature flags, GitOps, and Terraform, making overlap with unrelated skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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-policy/SKILL.md
Commit: 23e9b8b

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.