kopai/root-cause-analysis
Analyze telemetry data for root cause analysis using Kopai CLI. Use when debugging errors, investigating latency issues, tracing request flows across services, or correlating logs with traces. Also use when users report production issues like "why is my API slow", "getting 500 errors", "service is down", "requests are timing out", or any symptom that needs telemetry-based investigation — even if they don't mention traces or observability explicitly.
100
100%
Does it follow best practices?
Impact
Pending
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 communicates what the skill does (telemetry-based root cause analysis via Kopai CLI), when to use it (with explicit trigger scenarios), and includes natural user language that would realistically trigger selection. It uses proper third-person voice throughout and provides both technical and colloquial trigger terms, making it robust for skill selection across diverse user queries.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'root cause analysis', 'debugging errors', 'investigating latency issues', 'tracing request flows across services', 'correlating logs with traces'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (analyze telemetry data for root cause analysis using Kopai CLI) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios including both technical and natural-language user complaints). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user language including 'why is my API slow', 'getting 500 errors', 'service is down', 'requests are timing out', plus technical terms like 'telemetry', 'traces', 'latency', 'logs'. The note about triggering even without explicit observability mentions is particularly strong. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific tool name 'Kopai CLI', the telemetry/observability domain, and the focus on production debugging with traces and logs. Unlikely to conflict with general debugging or logging skills due to the specific scope. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%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 guides Claude through production debugging using Kopai CLI. It provides concrete, executable commands in a clear workflow sequence with appropriate fallback guidance, while keeping the content lean and well-organized with proper progressive disclosure to reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what traces, logs, or metrics are—it assumes Claude knows. Every section serves a purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable CLI commands with specific flags (--status-code ERROR, --json, --severity-min 17), a concrete example workflow with real commands, and practical tips like using jq for filtering. Commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | The RCA workflow is clearly sequenced (find → get context → correlate → check metrics → present findings) with explicit fallback guidance (e.g., 'If empty: broaden time range, check service name'). Step 5 includes what to present (evidence, impact, fix). The workflow has implicit validation through correlation steps. | 3 / 3 |
Progressive Disclosure | Clean overview with well-signaled one-level-deep references: rules are in `rules/<rule-name>.md`, filter details in `references/` directory, and setup in a separate otel-instrumentation skill. The main file stays concise while pointing to detailed materials. | 3 / 3 |
Total | 12 / 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.
Reviewed
Table of Contents