CtrlK
BlogDocsLog inGet started
Tessl Logo

cx-search-dashboard

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.

74

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-crafted, command-first skill body: executable examples, an explicit search-first principle, and tight organization with no dead weight beyond one redundant table. Its only minor issues are the overlapping 'When to Use Each Command' table and an example that reaches into the sibling skill's create command.

Suggestions

Merge the 'When to Use Each Command' table into the 'CLI Commands' table (e.g. a 'Use when' column) to remove the duplication.

Drop or hand off the 'cx dashboards create --from-file' clone example to the cx-dashboards skill, keeping this skill purely about discovery and inspection.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: no explanations of what Coralogix or dashboards are, and genuinely non-obvious guidance ("the results are ranked by similarity, not exact match; try several phrasings"). However, the "When to Use Each Command" table largely restates the "CLI Commands" table, which is minor redundancy — anchor 4 (efficient, minor instances that could be trimmed) rather than 5 (every token earns its place).

4 / 5

Actionability

Every command is fully executable with flags shown and realistic arguments in the examples ("cx dashboards search \"payment service error rate\"", "cx dashboards query-search --field '$d.http.status_code'", the get-and-clone sequence). Copy-paste ready commands covering the common cases match anchor 5.

5 / 5

Workflow Clarity

This is a simple, single-purpose read-only skill and the core action is unambiguous: "Search before creating — always run cx dashboards search before building a new dashboard". The search → get → inspect/clone flow is demonstrated end-to-end in the examples, and no validation checkpoints are needed for non-destructive search operations, so the simple-skill exception applies (anchor 5).

5 / 5

Progressive Disclosure

There are no bundle files, none are needed at this size (~70 lines), and the body is cleanly organized into CLI Commands, When to Use, Examples, Key Principles, and Related Skills sections with no content that should be split out to separate files. Per the under-50-lines exception for compact skills, well-organized sections alone merit anchor 5.

5 / 5

Total

19

/

20

Passed

Description

90%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit, natural trigger-phrase list and a clearly defined niche. The only weakness is that the capability statement is compressed into one clause, so the breadth of what the skill can do (catalog, get, inspect) is understated relative to what the body actually teaches.

Suggestions

Fold one or two more concrete capabilities into the 'what' clause, e.g. "...discover existing Coralogix dashboards or widgets via natural-language or field-based search, inspect their full definitions, and reuse found query patterns".

Trim the most redundant trigger phrasings (e.g. "find a dashboard about errors" and "find widgets that reference a field" near-duplicate others) to reduce padding without losing coverage.

DimensionReasoningScore

Specificity

The capability statement is a single clause — "wants to discover existing Coralogix dashboards or widgets using natural-language or field-based search" — naming the domain plus two search modes, but it does not enumerate other concrete capabilities the skill body covers (catalog listing, getting full dashboard JSON, inspecting found dashboards). This matches anchor 3 (domain and 1-2 concrete actions, not comprehensive) rather than 4, which expects several specific listed actions.

3 / 5

Completeness

Both "what" ("discover existing Coralogix dashboards or widgets using natural-language or field-based search") and "when" (the long explicit trigger-phrase list plus "or wants to discover...") are clearly and explicitly stated with concrete trigger phrases, matching anchor 5. Anchor 4 does not fit because the 'when' clause is already maximally explicit, not 'could be more specific'.

5 / 5

Trigger Term Quality

Ten quoted natural-language phrasings ("find a dashboard", "search dashboards", "does a dashboard exist for X", "find widgets that query Y", "which dashboards use this field", "look up dashboards by description", "search for existing monitoring dashboards") cover synonyms across find/search/look up and both dashboard- and widget-level intent. This is comprehensive natural-term coverage matching anchor 5.

5 / 5

Distinctiveness Conflict Risk

The niche is clear and consistently framed around search/discovery verbs (find, search, look up, discover), never creating or building, so it is well separated from the sibling cx-dashboards build skill. Distinct triggers with minimal conflict risk match anchor 5.

5 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
coralogix/cx-cli
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.