thousandeyes-network-data-from-traceid
Obtain ThousandEyes Network & App Synthetics data given a trace ID. Use when a user has a `traceId`, ThousandEyes MCP is available, and one or more Observability Platform integrations or equivalent tooling paths are available to query every relevant Observability Platform for the trace, extract `tracestate` or `w3c.tracestate`, decode the embedded ThousandEyes permalink, recover the ThousandEyes account/test/agent/execution identifiers, and fetch the matching ThousandEyes network data.
88
81%
Does it follow best practices?
Impact
100%
1.81xAverage score across 3 eval scenarios
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 a strong, highly specific skill description that clearly defines a narrow domain (ThousandEyes network data retrieval via trace IDs) with explicit trigger conditions and a detailed workflow of concrete actions. The 'Use when' clause is comprehensive, specifying prerequisites (traceId, MCP availability, observability platform integrations). The only minor weakness is that the description is quite long and dense, which could slightly reduce readability, but it sacrifices nothing in terms of precision and disambiguability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: obtain ThousandEyes data given a trace ID, query Observability Platforms for the trace, extract tracestate/w3c.tracestate, decode embedded ThousandEyes permalink, recover account/test/agent/execution identifiers, and fetch matching network data. | 3 / 3 |
Completeness | Clearly answers both 'what' (obtain ThousandEyes Network & App Synthetics data, query observability platforms, decode permalinks, fetch network data) and 'when' (explicit 'Use when' clause specifying a user has a traceId, ThousandEyes MCP is available, and observability platform integrations are present). | 3 / 3 |
Trigger Term Quality | Includes highly specific natural keywords a user would mention: 'traceId', 'ThousandEyes', 'tracestate', 'w3c.tracestate', 'permalink', 'network data', 'Observability Platform', 'MCP'. These are the exact terms a user working in this domain would use. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely niche and specific to ThousandEyes Network & App Synthetics data retrieval via trace IDs. The combination of ThousandEyes, tracestate decoding, and MCP availability makes it highly unlikely to conflict with other skills. | 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 procedural skill with clear workflow sequencing, explicit halt conditions, and good guardrails for a multi-step, multi-system correlation task. Its main weaknesses are the lack of concrete executable examples for the parsing/decoding steps and some redundancy between the workflow steps and guardrails. The progressive disclosure is reasonable but unverifiable without the referenced bundle files.
Suggestions
Add a concrete, executable example of parsing the `te=` member from a W3C tracestate string and URL-decoding it to extract `accountId`, `testId`, `agentId`, and `executionTime`—this is the most error-prone step and would benefit from a copy-paste-ready snippet.
Deduplicate constraints that appear in both the workflow steps and the guardrails section (e.g., URL-decoding requirement, not inventing identifiers) to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy—several guardrails restate constraints already covered in the workflow steps (e.g., URL-decoding, not inventing identifiers). Some steps could be tightened, but it largely avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides specific tool names (e.g., `get_network_app_synthetics_metrics`, `get_path_visualization_results`) and clear parameter mappings (`__a` → `accountId`, etc.), which is good. However, there are no executable code snippets or concrete examples of parsing the `te=` member from tracestate, URL-decoding, or extracting query parameters—these are described rather than demonstrated. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced across five numbered phases with explicit validation checkpoints: checking tool availability before starting, comparing identifiers across platforms for confirmation, stopping with clear error messages when tracestate is absent or identifiers are missing. The guardrails section provides explicit feedback loops and halt conditions. | 3 / 3 |
Progressive Disclosure | The skill references `reference.md` for parsing rules and `examples.md` for structured reports, which is good progressive disclosure structure. However, no bundle files were provided, so we cannot verify these references resolve to real content. The conditional loading of examples.md ('only when the user wants a structured report') is a nice touch, but the main body is fairly long and some detail (like the full return schema in step 5) could potentially be offloaded. | 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.
- Commit
a4497e7
- 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.