Content
36%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a role description or persona prompt than actionable technical guidance. It lacks concrete examples (regex patterns, log queries, stack trace parsing code) that would make it genuinely useful for error investigation tasks. The generic boilerplate sections and abstract instructions waste tokens without adding value.
Suggestions
Add concrete, executable examples: include actual regex patterns for common error extraction, sample Elasticsearch/Splunk queries, and a stack trace parsing snippet in at least one language.
Replace the vague 'Instructions' bullets ('Clarify goals, constraints, and required inputs') with specific first steps like 'grep for ERROR/FATAL in logs, extract timestamps, group by error type'.
Add a validation/verification step to the workflow, such as 'Confirm root cause hypothesis by checking if the error rate correlates with a specific deployment or config change'.
Remove or substantially tighten the generic 'Use this skill when' / 'Do not use this skill when' sections, which add no actionable information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary boilerplate (the generic 'Use this skill when' / 'Do not use this skill when' sections add little value and are vague). The 'Instructions' section contains generic platitudes like 'Clarify goals, constraints, and required inputs' that Claude already knows. The focus areas and approach sections are reasonably concise but still somewhat padded. | 3 / 5 |
Actionability | The skill provides only high-level direction with no concrete code, commands, regex patterns, or executable examples. Statements like 'Look for patterns across time windows' and 'Regex patterns for error extraction' describe outputs without showing how to produce them. No actual regex patterns, log query examples, or stack trace parsing code is provided. | 2 / 5 |
Workflow Clarity | The 'Approach' section lists a rough sequence (5 steps) but they are vague and lack validation checkpoints. There's no feedback loop for verifying findings, no concrete commands or tools to use at each step, and no error recovery guidance. For a skill involving cross-system error correlation, the workflow is insufficiently detailed. | 2 / 5 |
Progressive Disclosure | The skill references 'resources/implementation-playbook.md' for detailed examples, which is a reasonable progressive disclosure pattern. However, no bundle files exist to support this reference, and the main content itself is somewhat thin — it could benefit from more inline quick-start examples before pointing to external resources. | 3 / 5 |
Total | 10 / 20 Passed |