Build and deploy a Coralogix dashboard for a given service from its logs, spans, metrics, and service specs. Discovers telemetry via cx CLI commands, emits importable Coralogix JSON, verifies every PromQL and DataPrime query live through the `cx` CLI, and creates or updates dashboards via `cx dashboards create` and `cx dashboards replace`. Use whenever the user asks to create, build, generate, deploy, update, replace, or modify a Coralogix dashboard, monitoring dashboard, or observability dashboard for a service, app, or pipeline.
75
92%
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 (telemetry discovery, query verification, dashboard creation/update via cx CLI), includes comprehensive trigger terms covering multiple natural phrasings, and provides an explicit 'Use whenever...' clause. The description is distinctive enough to avoid conflicts with other monitoring or dashboard-related skills due to its Coralogix-specific terminology and tooling references.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: discovers telemetry via cx CLI, emits importable Coralogix JSON, verifies PromQL and DataPrime queries live, creates/updates dashboards via specific CLI commands (`cx dashboards create`, `cx dashboards replace`). | 3 / 3 |
Completeness | Clearly answers both 'what' (build/deploy Coralogix dashboards from logs/spans/metrics, discover telemetry, verify queries, emit JSON) and 'when' with an explicit 'Use whenever...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create', 'build', 'generate', 'deploy', 'update', 'replace', 'modify', 'Coralogix dashboard', 'monitoring dashboard', 'observability dashboard', 'service', 'app', 'pipeline'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically targets Coralogix dashboards using the `cx` CLI, mentions specific query languages (PromQL, DataPrime), and specific commands. Very unlikely to conflict with generic monitoring or dashboard skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, well-structured skill for a complex multi-phase workflow. Its greatest strengths are the explicit workflow sequencing with validation gates, highly actionable CLI commands and checklists, and clean progressive disclosure to reference files. The only notable weakness is moderate verbosity in places — some motivational explanations and minor redundancy in reference listings could be trimmed to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lengthy (~300 lines) but most content earns its place — phase descriptions, CLI commands, checklists, and output templates are all necessary for this complex workflow. However, some areas are slightly verbose: the Phase 1 discovery section over-explains what to look for, and the Phase 8 rationale paragraph ('Printing the ID alone forces the user...') explains motivation Claude doesn't need. The repeated reference tables at top and bottom are mildly redundant. | 2 / 3 |
Actionability | Highly actionable throughout: concrete CLI commands (`cx metrics search`, `cx dashboards create --from-file`, `cx dashboards replace`), specific JSON structure templates, exact field paths (`$d.message`, `$l.applicationname`), widget-type selection tables, and copy-paste-ready bash snippets for dashboard duplication and updates. The checklists in Phase 6 are precise and executable. | 3 / 3 |
Workflow Clarity | Exemplary 8-phase workflow with explicit sequencing constraints ('Don't jump to Phase 4 before the user approves Phase 3'), a progress checklist, validation gates (Phase 5 live-verification, Phase 6 structural self-check), clear error recovery paths ('If a query can't pass within retry budget, surface it to the user'), and explicit completion criteria (Phase 8 link sharing is mandatory). Feedback loops are well-defined for destructive/deployment operations. | 3 / 3 |
Progressive Disclosure | Clean progressive disclosure with a well-organized reference table at the top pointing to 8 specific reference files (one level deep), each clearly labeled by task. The main SKILL.md serves as the orchestration overview while delegating detailed syntax, templates, and procedures to dedicated reference files. Navigation is clear and references are consistently signaled throughout the document. | 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.