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 ./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 both what the skill does and when to use it, with an explicit 'Use when' clause and good trigger terms. Its main weakness is that the capability description is somewhat general—it could benefit from listing more specific actions beyond just 'performs web searches' to better differentiate the range of search-related tasks it handles.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Performs web searches using DuckDuckGo to retrieve real-time information, fetch URLs, and summarize search results.'
| 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 extracting snippets, returning URLs, summarizing results, 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 'information'. These cover common variations of how users request search functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to web searching via DuckDuckGo with distinct triggers like 'web search', 'real-time information', and 'current events'. Unlikely to conflict with other skills since web search is a well-defined niche. | 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 highly actionable, executable code examples covering the full DuckDuckGo search API surface, which is its main strength. However, it is severely over-engineered for a SKILL.md - it reads more like comprehensive library documentation than a concise skill instruction. The content should be dramatically condensed to core patterns with advanced features split into referenced files.
Suggestions
Reduce the main SKILL.md to ~50-80 lines covering only text search (the primary use case) with a quick-start example, error handling pattern, and rate limiting note. Move other search types (news, images, videos, maps, suggestions, answers) to a separate SEARCH_TYPES.md reference file.
Move the parameter reference tables (region codes, timelimit, safesearch) and utility scripts (batch search, save to JSON) into a separate REFERENCE.md file, linked from the main skill.
Remove the feature bullet list with emojis, installation troubleshooting, and explanatory text like '最常用的搜索方式，返回网页结果' - Claude already knows what text search is and can figure out installation issues.
Add a brief validation step for batch operations, e.g., checking result count and handling empty results before proceeding to the next query.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose - includes 7 different search types with full code examples, feature bullet points with emojis, parameter reference tables, FAQ sections, and integration examples. Much of this is API documentation that Claude could infer from the library. The skill is ~300+ lines when ~50 would suffice for the core patterns. | 1 / 3 |
Actionability | All code examples are fully executable, copy-paste ready Python snippets with concrete parameters, output formatting, and real usage patterns. Error handling, proxy configuration, and batch search examples are all complete and runnable. | 3 / 3 |
Workflow Clarity | Individual search operations are clear, and the batch search includes a rate-limiting delay. However, there's no explicit validation workflow - for batch operations, there's no feedback loop for handling partial failures or verifying results before proceeding. The integration section with browser-use hints at a multi-step workflow but doesn't fully sequence it with validation. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with everything inline - 7 search types, utility scripts, parameter tables, FAQ, integration examples all in one file. The parameter reference tables, utility scripts, and advanced search types should be split into separate referenced files to keep the main skill lean. | 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
- openclaw/skills
- Commit
fca9ef2
- 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.