This skill should be used when the user asks to "find a dashboard", "search dashboards", "does a dashboard exist for X", "find widgets that query Y", "which dashboards use this field", "find a dashboard about errors", "look up dashboards by description", "search for existing monitoring dashboards", "find widgets that reference a field", or wants to discover existing Coralogix dashboards or widgets using natural-language or field-based search.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 description excels at trigger term coverage and completeness, providing an extensive list of natural-language phrases that would help Claude select this skill accurately. However, it is somewhat weak on specificity of capabilities — it focuses almost entirely on when to use the skill rather than describing what concrete actions or outputs it provides beyond 'search/find/discover'. The description also reads more as a trigger list than a balanced capability description.
Suggestions
Add concrete capability details beyond searching, such as 'Returns matching dashboard names, URLs, and widget configurations' or 'Searches by dashboard title, description, or queried fields' to improve specificity.
Restructure to lead with a concise capability statement (e.g., 'Searches and discovers existing Coralogix dashboards and widgets by name, description, or referenced fields') before the trigger phrases, for better readability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Coralogix dashboards/widgets) and some actions (find, search, discover), but doesn't list concrete specific capabilities beyond searching — e.g., it doesn't mention what it returns, whether it can filter by type, or what operations it performs on results. | 2 / 3 |
Completeness | The description clearly answers both 'what' (discover existing Coralogix dashboards or widgets using natural-language or field-based search) and 'when' (explicitly lists numerous trigger phrases and scenarios). The entire description is essentially a 'Use when...' clause with extensive trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'find a dashboard', 'search dashboards', 'does a dashboard exist', 'find widgets that query Y', 'which dashboards use this field', 'look up dashboards by description', 'search for existing monitoring dashboards', 'find widgets that reference a field'. These are highly natural phrases users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it targets a specific product (Coralogix), specific resource types (dashboards and widgets), and a specific action (search/discovery). Unlikely to conflict with other skills unless there are multiple Coralogix dashboard skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%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-crafted skill that efficiently teaches dashboard search with concrete, executable examples and clear organization. The command reference tables and examples are particularly strong. The main gap is the lack of validation/verification steps in the clone workflow and no explicit error-handling guidance when searches return empty or unexpected results.
Suggestions
Add a validation step after `cx dashboards create --from-file dashboard.json` (e.g., verify the new dashboard exists with `cx dashboards get <new-id>`) to close the feedback loop in the clone workflow.
Add brief guidance on what to do when search returns no results or irrelevant results (e.g., try alternative phrasings, broaden the search, fall back to `cx dashboards catalog`).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Coralogix is, what dashboards are, or how CLI tools work in general. Every section delivers new, specific information. The tables are compact and informative. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready CLI commands with realistic arguments. The examples cover multiple use cases (service search, field search, topic search, inspect-and-clone workflow) with concrete field paths and descriptions. | 3 / 3 |
Workflow Clarity | The 'inspect and clone' workflow shows a clear sequence, and the 'search before creating' principle establishes a workflow pattern. However, there are no explicit validation checkpoints — e.g., no guidance on what to do if search returns no results, or how to verify a cloned dashboard was created correctly before relying on it. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections (commands table, when-to-use table, examples, principles) and appropriately references related skills (cx-dashboards, cx-telemetry-querying) for deeper topics. For a skill of this scope and size, the organization is excellent with no need for additional files. | 3 / 3 |
Total | 11 / 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.
34d6303
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.