duckduckgo-search
Performs web searches using DuckDuckGo to retrieve real-time information from the internet. Use when the user needs to search for current events, documentation, tutorials, or any information that requires web search capabilities.
72
Quality
66%
Does it follow best practices?
Impact
75%
3.57xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/10e9928a/duckduckgo-search/SKILL.mdQuality
Discovery
89%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-structured skill description that clearly communicates both purpose and trigger conditions. It uses proper third-person voice and includes an explicit 'Use when...' clause with relevant trigger terms. The main weakness is that the capabilities could be more specific about the types of searches or outputs supported.
Suggestions
Add more specific concrete actions like 'find documentation, lookup current news, research topics, verify facts' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web searches via DuckDuckGo) and the general action (retrieve real-time information), but doesn't list multiple specific concrete actions like 'search news articles, find documentation, lookup tutorials, verify facts'. | 2 / 3 |
Completeness | Clearly answers both what ('Performs web searches using DuckDuckGo to retrieve real-time information') and when ('Use when the user needs to search for current events, documentation, tutorials, or any information that requires web search capabilities'). | 3 / 3 |
Trigger Term Quality | Includes good natural keywords users would say: 'search', 'current events', 'documentation', 'tutorials', 'web search', 'information'. These are terms users naturally use when needing search capabilities. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with distinct triggers - specifically mentions DuckDuckGo and web search, which creates a unique identity. Unlikely to conflict with document processing or other skills due to explicit 'web search' and 'internet' terminology. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent actionable code examples that are immediately executable, but is severely bloated with unnecessary content. It explains basic concepts Claude already knows, includes excessive emoji decoration, and dumps everything into one massive file instead of using progressive disclosure. The core value (API usage patterns) is buried in verbose explanations.
Suggestions
Reduce to ~50 lines: Quick start with one text search example, then brief sections showing only the method signatures for news/images/videos with parameter differences
Move parameter reference tables (region codes, timelimit values) to a separate REFERENCE.md file
Remove explanatory text about what DuckDuckGo is, privacy features, and installation troubleshooting - Claude knows these concepts
Integrate error handling into the main examples rather than as a separate section, showing the try/except pattern once in the quick start
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations Claude doesn't need (what DuckDuckGo is, privacy features, emoji decorations). The skill is ~400 lines when it could be ~50 lines covering the essential API patterns. | 1 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples for all search types. Each code block is complete and runnable with proper imports and context managers. | 3 / 3 |
Workflow Clarity | For a simple API wrapper skill, the individual operations are clear, but the error handling section is separate from the main examples rather than integrated. The batch search example includes rate limiting which is good, but validation is minimal. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including parameter tables, troubleshooting, and integration examples that could be split into separate reference documents. | 1 / 3 |
Total | 7 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
45f9fac
- 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.