web-search
DuckDuckGo를 사용한 웹 검색. 텍스트, 뉴스, 이미지 검색을 지원. 빌트인 WebSearch가 제한적이거나, 뉴스/이미지 검색, 지역/기간 필터가 필요할 때 사용. "검색해줘", "찾아줘", "search", "뉴스 검색", "이미지 검색" 등의 요청 시 활성화.
95
93%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 a well-crafted skill description that excels across all dimensions. It clearly specifies the tool (DuckDuckGo), lists concrete capabilities (text/news/image search, filters), explains when to use it over alternatives (built-in WebSearch limitations), and provides excellent bilingual trigger terms. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: web search using DuckDuckGo, text search, news search, and image search. Also mentions specific features like region/period filters. | 3 / 3 |
Completeness | Clearly answers both what (DuckDuckGo web search with text/news/image support) and when (when built-in WebSearch is limited, when news/image search or filters are needed, with explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in both Korean and English: '검색해줘', '찾아줘', 'search', '뉴스 검색', '이미지 검색'. These are exactly what users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishes itself from built-in WebSearch by specifying when to use it instead (limitations of built-in, need for news/image/filters). The DuckDuckGo specificity and feature set create a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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 with excellent conciseness and actionability. The parameter table, multiple executable examples, and search operator reference provide comprehensive guidance. The main weakness is the workflow section which could benefit from validation steps for handling edge cases like empty results or rate limiting during execution.
Suggestions
Add a validation step in the workflow to check for empty results or errors before presenting to user (e.g., 'If results array is empty, try broader search terms or different region')
Include example JSON output structure so Claude knows what to expect and can validate the response format
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient. No unnecessary explanations of what DuckDuckGo is or how search engines work. Every section provides actionable information without padding. | 3 / 3 |
Actionability | Provides fully executable bash commands with clear parameter tables. Examples are copy-paste ready with realistic use cases including file output redirection. | 3 / 3 |
Workflow Clarity | Three-step workflow is clear but lacks validation checkpoints. No guidance on verifying search results, handling empty results, or confirming successful execution before proceeding. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from when to use, to core workflow, to parameters, to examples. Appropriate length for a single-file skill with no need for external references. | 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.
- Repository
- bear2u/my-skills
- Commit
1be5394
- 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.