manage-delegates
Monitor and manage Harness Delegates via MCP. List delegates and check health status, manage delegate registration tokens (create, revoke, delete), and find which delegates are associated with a token. Use when asked about delegate status, delegate health, delegate connectivity, delegate tokens, or troubleshooting delegate issues. Trigger phrases: delegate status, delegate health, list delegates, delegate token, delegate connectivity, delegate troubleshooting, delegate down.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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 clearly articulates specific capabilities (listing delegates, checking health, managing tokens), provides explicit 'Use when' guidance, and includes a comprehensive list of trigger phrases. It uses proper third-person voice throughout and targets a distinct niche (Harness Delegate management) that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: list delegates, check health status, manage delegate registration tokens (create, revoke, delete), and find which delegates are associated with a token. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (monitor and manage Harness Delegates, list delegates, check health, manage tokens) and 'when' (explicit 'Use when...' clause with specific trigger scenarios plus a dedicated trigger phrases list). | 3 / 3 |
Trigger Term Quality | Includes an explicit list of natural trigger phrases covering common variations: 'delegate status', 'delegate health', 'list delegates', 'delegate token', 'delegate connectivity', 'delegate troubleshooting', 'delegate down'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to Harness Delegates and delegate token management via MCP. The domain is narrow and well-defined, making it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with concrete MCP tool calls and useful troubleshooting guidance. Its main weaknesses are the repetitive step-by-step format for what are essentially independent CRUD operations (which inflates token count), and the lack of explicit validation checkpoints before destructive operations like token revocation and deletion. The troubleshooting section adds genuine operational value beyond simple API reference.
Suggestions
Add explicit validation before destructive operations: before revoking/deleting a token, instruct to first run get_delegates to check which delegates will be affected, and confirm with the user.
Condense the repetitive MCP call patterns (Steps 3-7) into a compact reference table with columns for operation, tool, resource_type, required params, and optional params — this would significantly reduce token count while preserving actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but has some redundancy. Steps 3-7 follow a very repetitive pattern that could be condensed into a reference table. The performance notes and troubleshooting sections add genuine value, but the step-by-step format for simple CRUD operations is somewhat verbose when a table or compact listing would suffice. | 2 / 3 |
Actionability | Every operation has a concrete, copy-paste-ready MCP tool call with exact parameters specified. The resource types table, examples section, and troubleshooting steps all provide specific, actionable guidance that Claude can directly execute. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and well-labeled, but the numbered steps imply a linear workflow when these are actually independent operations. More critically, destructive operations (revoke, delete) lack explicit validation checkpoints — there's no 'verify which delegates use this token before revoking' step built into the revoke/delete workflow, though the troubleshooting section hints at this concern. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections (instructions, resource types table, examples, troubleshooting), but it's a single monolithic file. The repetitive MCP call patterns for each operation could be condensed, and the troubleshooting section could potentially be a separate reference file. However, given no bundle files exist, the single-file approach is reasonable for this scope. | 2 / 3 |
Total | 9 / 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.