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
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 solid skill description that clearly communicates its purpose and when to use it. It has an explicit 'Use when' clause with good trigger terms and is distinctly identifiable as a web search skill. The main weakness is that the specificity of capabilities could be improved by listing more concrete actions beyond just 'retrieve real-time information.'
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Performs web searches using DuckDuckGo to retrieve real-time information, find documentation links, look up recent news, and answer factual questions about current topics.'
| 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 beyond searching—e.g., no mention of summarizing results, extracting links, filtering by date, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (performs web searches using DuckDuckGo to retrieve real-time information) and 'when' (explicit 'Use when' clause covering current events, documentation, tutorials, or any information requiring web search). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'web search', 'search', 'current events', 'documentation', 'tutorials', 'DuckDuckGo', and 'internet'. These cover a good range of how users would phrase search-related requests. | 3 / 3 |
Distinctiveness Conflict Risk | The mention of DuckDuckGo and web search creates a clear, distinct niche. It's unlikely to conflict with other skills since web searching via a specific engine is a well-defined capability. | 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 is highly actionable with complete, executable code examples for every feature, but it is severely bloated. It reads more like comprehensive library documentation than a focused skill file - Claude doesn't need emoji-decorated feature lists, installation troubleshooting, or 7 fully expanded search type examples to use the duckduckgo-search library. The content should be dramatically condensed with advanced usage split into referenced files.
Suggestions
Reduce the main skill to a quick-start section with one text search example, a brief parameter reference, and error handling pattern - move all other search types to a separate SEARCH_TYPES.md reference file.
Remove the feature list, installation troubleshooting FAQ, and explanatory text like '最常用的搜索方式，返回网页结果' - Claude already understands these concepts.
Split utility scripts (batch search, save-to-JSON) and integration examples into a separate EXAMPLES.md file referenced from the main skill.
Add a validation step in the batch search workflow to check for empty results and implement retry logic, rather than just sleeping between requests.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose - lists 7 search types with full code examples when Claude already knows how to use Python libraries. The feature list with emojis, parameter reference tables, FAQ section, and installation troubleshooting are all unnecessary padding. The entire skill could be condensed to ~30 lines covering the API surface and key parameters. | 1 / 3 |
Actionability | All code examples are fully executable, copy-paste ready Python commands. Parameters are clearly documented with valid values, and every search type includes a complete working example with proper imports and context managers. | 3 / 3 |
Workflow Clarity | The batch search example includes a rate-limiting delay (time.sleep), and error handling is covered, but there's no validation/verification step for batch operations (e.g., checking if results are empty or retrying on failure). The integration workflow with browser-use is loosely sequenced without explicit checkpoints. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with everything inline - 7 search types, utility scripts, parameter tables, error handling, proxy config, FAQ, and integration examples all in one file. Much of this content (parameter reference, utility scripts, integration guides) should be split into separate referenced files. | 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.