check-duplicates
Check for duplicate or similar cases. Use before deep analysis to avoid investigating the same incident twice. Takes a CASE_ID and returns list of similar cases.
87
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%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 a well-crafted skill description that clearly communicates its purpose, input/output, and when to use it. The 'Use before deep analysis' clause provides excellent timing guidance. Minor improvement could come from adding more natural trigger terms users might say when looking for duplicates.
Suggestions
Add common user phrases like 'dupe check', 'already reported', 'existing case', or 'seen this before' to improve trigger term coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: 'Check for duplicate or similar cases', 'Takes a CASE_ID', 'returns list of similar cases'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Check for duplicate or similar cases', 'Takes a CASE_ID and returns list of similar cases') and when ('Use before deep analysis to avoid investigating the same incident twice'). | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'duplicate', 'similar cases', 'CASE_ID', and 'incident', but missing common variations users might say like 'dupe check', 'existing cases', 'already reported', or 'case lookup'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on case deduplication with specific input/output (CASE_ID → similar cases list). Unlikely to conflict with general search or analysis skills due to the specific 'duplicate/similar cases' focus. | 3 / 3 |
Total | 11 / 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 well-structured, concise skill that clearly defines its purpose and workflow. The main weakness is the actionability of the code example, which uses an ambiguous syntax that isn't directly executable. The decision logic for handling duplicates is clear and the overall organization is excellent for a focused utility skill.
Suggestions
Make the function call in Step 1 executable by specifying the language/format (e.g., proper Python syntax or MCP tool call format)
Add a concrete example showing how to extract SIMILAR_CASE_IDS from the response structure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient with no unnecessary explanations. Every section serves a purpose - inputs are listed concisely, workflow is minimal, and outputs are tabular. No padding or concepts Claude already knows. | 3 / 3 |
Actionability | Provides a concrete function call with parameters, but the code block lacks proper syntax (not valid Python or any specific language). Step 2 'Extract the list of similar case IDs' is vague without showing how to actually parse the response. | 2 / 3 |
Workflow Clarity | Clear two-step workflow with explicit decision tree for handling results. The usage pattern provides a logical sequence with branching logic for duplicates found vs not found, and includes specific closure instructions. | 3 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is well-organized with clear sections (Inputs, Workflow, Outputs, Usage Pattern, When Duplicates Are Found). No external references needed for this scope. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- dandye/ai-runbooks
- Commit
4d132c7
- 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.