Manage ThousandEyes synthetic monitoring with MCP tools. Use when a user wants to list, inspect, create, update, delete, or validate synthetic tests; deploy application templates; or choose the right ThousandEyes monitoring approach across Network and Application Synthetics and Browser Synthetics.
87
81%
Does it follow best practices?
Impact
95%
1.28xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 a strong skill description that clearly identifies the product domain (ThousandEyes), lists specific CRUD operations and additional capabilities, and includes an explicit 'Use when' clause with comprehensive trigger scenarios. The description is concise, uses third-person voice correctly, and provides enough specificity to distinguish it from other monitoring or testing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: list, inspect, create, update, delete, validate synthetic tests; deploy application templates; choose monitoring approach. These are clear, actionable verbs tied to specific objects. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage ThousandEyes synthetic monitoring with MCP tools) and 'when' (explicit 'Use when' clause covering list, inspect, create, update, delete, validate tests, deploy templates, or choose monitoring approach). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'ThousandEyes', 'synthetic monitoring', 'MCP tools', 'synthetic tests', 'application templates', 'Network and Application Synthetics', 'Browser Synthetics'. Good coverage of domain-specific terms a user would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: ThousandEyes is a specific product, and the description targets synthetic monitoring specifically. Very unlikely to conflict with other skills due to the product-specific terminology and well-defined scope. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured operational skill with a clear multi-step workflow, strong safety guardrails for destructive operations, and good product-domain mapping. Its main weaknesses are verbosity (repetition across sections) and lack of concrete inline examples—tool call payloads, confirmation message templates, or response snippets would significantly improve actionability. The progressive disclosure strategy is sound in design but the main file carries too much detail that could be offloaded to the referenced files.
Suggestions
Add 1-2 concrete inline examples showing an actual MCP tool call payload and a sample confirmation summary to improve actionability without relying entirely on examples.md.
Consolidate repeated guidance (e.g., confirmation requirements appear in Required Behavior #3, Workflow step 5, and Guardrails) into a single authoritative location to reduce token usage.
Move the detailed test-type-to-field mapping (section 4.3) into reference.md and keep only a brief summary table in SKILL.md to improve conciseness and progressive disclosure.
Provide the referenced bundle files (reference.md, examples.md) or note their expected structure so the skill's progressive disclosure can be fully validated.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured but verbose for what it conveys. Many points are repetitive across sections (e.g., confirmation requirements are stated in Required Behavior, Workflow step 5, and Guardrails). The detailed enumeration of test types and fields, while useful, could be more compact—especially since much of this is already delegated to reference.md. | 2 / 3 |
Actionability | The skill provides specific tool names, field requirements, and a clear decision tree for mapping user requests to test types. However, it lacks any concrete executable examples—no sample MCP tool calls, no example payloads, no example confirmation summaries. It describes what to do rather than showing it, relying entirely on external files (examples.md, reference.md) for concrete illustrations. | 2 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints: discover before write, confirm before execution, inspect before update, and report after completion. Feedback loops are present (e.g., inspect current test if unclear, ask user to disambiguate if multiple matches, prefer instant-test before persistent changes). Destructive operations have clear guardrails requiring both test_id and test_type. | 3 / 3 |
Progressive Disclosure | The skill references reference.md and examples.md with clear signals for when to load each, which is good progressive disclosure design. However, no bundle files were provided, so we cannot verify these references resolve to real content. Additionally, the SKILL.md itself is quite long (~180 lines) and inlines substantial detail about test types, field requirements, and validation rules that could arguably live in reference.md, making the main file heavier than ideal. | 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.
a4497e7
Table of Contents
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.