Name: create-secret
Rating: 79.2 (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

68%

Does it follow best practices?

Impact

96%

1.10x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/claude/skills/create-secret/SKILL.md

Quality

Content

37%

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

This appears to be a partial skill file (likely the second half) containing examples, error handling, and troubleshooting but missing the core workflow instructions and MCP tool call examples. The examples are natural language prompts rather than executable tool calls, reducing actionability. The content would benefit significantly from a clear step-by-step workflow with validation checkpoints for secret creation.

Suggestions

Add a clear numbered workflow (determine requirements → check existing → create → verify) with explicit MCP tool call syntax at each step, including validation after creation.

Replace the natural language example prompts with concrete, executable harness_create() tool call examples showing actual parameters and expected responses.

Add a feedback loop for error recovery: after creation, verify with harness_get and include guidance on what to do if verification fails.

Move the detailed troubleshooting sections (SSH Key Connection Failures, External Secret Manager Errors) to a referenced troubleshooting file to keep the main skill lean.

Dimension	Reasoning	Score
Conciseness	The content is moderately efficient but includes some sections that could be tightened. The examples section with five usage examples is somewhat verbose, and the troubleshooting section covers scenarios Claude could likely reason about. However, the tables and structured content are reasonably compact.	2 / 3
Actionability	The examples show invocation patterns but are slash-command descriptions rather than executable MCP tool calls. The actual MCP tool call syntax (harness_create, harness_list, etc.) is missing from this portion of the skill, and the examples read more like natural language prompts than concrete executable guidance.	2 / 3
Workflow Clarity	This content fragment lacks any sequenced workflow steps. There is no create-then-verify process, no numbered steps, and no validation checkpoints. The error handling and troubleshooting sections exist but are reactive rather than proactive workflow guidance. For secret creation (a potentially destructive/sensitive operation), the absence of a clear workflow with validation is a significant gap.	1 / 3
Progressive Disclosure	The content is organized into clear sections (Examples, Error Handling, Troubleshooting, Security Best Practices) which aids navigation. However, there are no references to external files for detailed content, and the troubleshooting section is quite long inline. The reference to `/audit-report` skill is a nice cross-reference, but no bundle files support progressive disclosure.	2 / 3
	Total	7 / 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.

This is an excellent skill description that hits all the marks. It provides specific capabilities, comprehensive trigger terms, explicit 'Use when' guidance, and is clearly scoped to Harness secret management. The description is well-structured, uses third person voice throughout, and balances detail with conciseness.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: generate Harness Secret definitions, manage secrets via MCP v2 tools, supports specific types (SecretText, SecretFile, SSHKey, WinRmCredentials), and names specific secret managers (HashiCorp Vault, AWS Secrets Manager, Azure Key Vault, GCP Secret Manager).	3 / 3
Completeness	Clearly answers both 'what' (generate Harness Secret definitions, manage secrets, supports specific types and secret managers) and 'when' (explicit 'Use when...' clause listing specific scenarios like creating secrets, storing credentials, managing API keys, etc.).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'create secret', 'secret text', 'secret file', 'SSH key', 'API key', 'password', 'credentials', 'secret manager', 'store secret'. These are terms users would naturally use when needing this functionality.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche: Harness-specific secret management with named secret types and specific secret manager integrations. The combination of 'Harness', specific secret types, and named cloud secret managers makes it very unlikely to conflict with other 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: harness/harness-ai
Commit: fc23d5d

Reviewed: 17 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.