Name: create-secret
Rating: 99.2 (1 reviews)
Author: harness

create-secret

Generate Harness Secret definitions and manage secrets via MCP v2 tools. Supports SecretText, SecretFile, SSHKey, and WinRmCredentials types with configurable secret managers (Harness built-in, HashiCorp Vault, AWS Secrets Manager, Azure Key Vault, GCP Secret Manager). Use when asked to create a secret, store credentials, manage API keys, set up SSH keys, configure WinRM credentials, rotate secrets, or reference secrets in pipelines. Trigger phrases: create secret, secret text, secret file, SSH key, API key, password, credentials, secret manager, store secret.

1.10x

Quality

100%

Does it follow best practices?

Impact

96%

1.10x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

100%

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

A well-structured, actionable skill body that combines executable MCP calls and YAML with a validated workflow, scoped one-level references, and useful error/troubleshooting tables. It respects Claude's competence without padding and splits detail appropriately into the reference file.

Dimension	Reasoning	Score
Conciseness	The body is lean and task-specific — tool tables, executable YAML, MCP calls, naming regex, and error tables — with no padding explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides fully executable guidance: parameterized MCP tool calls, copy-paste YAML specs, a concrete identifier regex, and worked pipeline-reference examples.	3 / 3
Workflow Clarity	A four-step Instructions sequence includes an explicit Step 4 'Verify Creation' validation checkpoint, complemented by Error Handling and Troubleshooting sections that describe recovery feedback loops.	3 / 3
Progressive Disclosure	SKILL.md acts as an overview with one clearly-signaled one-level-deep reference ('consult references/secret-types.md') for advanced types and manager configuration; the referenced file exists and is well-organized.	3 / 3
	Total	12 / 12 Passed

Description

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.

A strong, third-person description that concretely enumerates capabilities and supported types/managers and provides an explicit 'Use when' trigger clause plus natural trigger phrases. It is distinct to the Harness secret-management domain and unlikely to misfire.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Generate Harness Secret definitions', 'manage secrets', 'store credentials', 'manage API keys', 'set up SSH keys', 'configure WinRM credentials', 'rotate secrets', 'reference secrets') plus the supported types and managers, matching the score-3 anchor.	3 / 3
Completeness	Clearly states both what ('Generate... and manage secrets via MCP v2 tools' with types/managers) and when ('Use when asked to create a secret, store credentials...'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Explicit 'Trigger phrases' cover natural user terms ('create secret', 'API key', 'password', 'credentials', 'SSH key', 'store secret') with good variation coverage, matching the score-3 example.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to Harness Secret definitions via MCP v2 tools with Harness-specific identifiers, giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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-secret/SKILL.md
Commit: a48c95a

Reviewed: 22 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.