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.
76
64%
Does it follow best practices?
Impact
96%
1.10xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/claude/skills/create-secret/SKILL.mdQuality
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 an excellent skill description that covers all key dimensions thoroughly. It provides specific capabilities, explicit trigger guidance with a 'Use when...' clause, natural trigger phrases, and is clearly scoped to Harness secret management, making it highly distinguishable from other skills. The description is well-structured, concise, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and types: 'Generate Harness Secret definitions', 'manage secrets via MCP v2 tools', and enumerates specific secret types (SecretText, SecretFile, SSHKey, WinRmCredentials) along with supported secret managers (HashiCorp Vault, AWS Secrets Manager, etc.). | 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 scenarios like creating secrets, storing credentials, managing API keys, rotating secrets, referencing secrets in pipelines). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say, explicitly listed: 'create secret', 'secret text', 'secret file', 'SSH key', 'API key', 'password', 'credentials', 'secret manager', 'store secret'. These are highly natural phrases a user would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: Harness-specific secret management with named secret types and specific secret manager integrations. The Harness platform context and MCP v2 tooling make it very unlikely to conflict with generic credential or secret skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
29%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 the latter half of a skill document, containing examples, error handling, troubleshooting, and best practices, but missing the core instructional content (tool definitions, YAML schemas, and step-by-step workflow). As evaluated standalone, it lacks actionable tool invocations, clear workflow sequencing, and proper progressive disclosure structure. The content that is present is reasonably well-organized in tables but doesn't constitute a complete, actionable skill.
Suggestions
Include the core workflow steps (determine requirements, check existing secrets, create secret, verify creation) with concrete MCP tool call examples and expected responses in this content.
Add explicit validation checkpoints in the workflow, such as verifying the secret manager exists before creation and confirming the secret was created successfully with harness_get.
Move detailed troubleshooting and error handling to a separate reference file and keep the main skill focused on the creation workflow with a clear reference link.
Replace the natural language example prompts with concrete tool invocation examples showing exact parameters and expected output structures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes some redundancy. The examples section with natural language prompts is useful but verbose, and the troubleshooting/security sections contain advice Claude likely already knows (e.g., 'never output secret values in pipeline logs'). The error handling table is well-structured but some entries explain obvious concepts. | 2 / 3 |
Actionability | The skill provides example prompts and an error handling table, but lacks the concrete executable MCP tool calls and YAML definitions that would make it fully actionable. The examples show what to ask for but not the actual tool invocations or expected outputs. The main SKILL.md content (with the tool calls and YAML specs) appears to be cut off, leaving this portion as supplementary material without the core executable guidance. | 2 / 3 |
Workflow Clarity | This content fragment contains no clear multi-step workflow or sequenced process. The examples section shows individual use cases but no step-by-step creation workflow with validation checkpoints. The troubleshooting sections list diagnostic steps but these are reactive, not proactive workflow validation. | 1 / 3 |
Progressive Disclosure | The content appears to be a fragment (examples, error handling, troubleshooting, and best practices sections) without the core skill instructions. There are no references to external files for detailed content, and no bundle files are provided. The reference to 'references/secret-types.md' and '/audit-report' skill appear in the content but the overall structure is disorganized as a standalone document. | 1 / 3 |
Total | 6 / 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.