search
Search the web using Tavily's LLM-optimized search API. Returns relevant results with content snippets, scores, and metadata. Use when you need to find web content on any topic without writing code.
81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
75%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 description that clearly communicates both purpose and usage triggers. Its main weakness is limited trigger term coverage - users might say 'look something up' or 'research this topic' and not match. The specificity could be improved by listing more concrete use cases beyond generic 'search'.
Suggestions
Add more natural trigger terms users would say, such as 'look up', 'research', 'search online', 'find information about'
Consider listing specific use cases like 'find current news', 'research topics', 'get recent information' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web search via Tavily API) and describes what it returns (results with content snippets, scores, metadata), but doesn't list multiple concrete actions beyond 'search' - it's a single capability described with some detail. | 2 / 3 |
Completeness | Clearly answers both what ('Search the web using Tavily's LLM-optimized search API. Returns relevant results with content snippets, scores, and metadata') and when ('Use when you need to find web content on any topic without writing code') with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes 'search the web', 'web content', and 'find' which are natural terms, but misses common variations like 'look up', 'google', 'research', 'search online', or 'browse'. The term 'Tavily' is technical and not user-facing. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche: web search via a specific API (Tavily), with the distinguishing factor of 'without writing code'. This differentiates it from code-based web scraping or other search tools. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent concrete examples and clear authentication guidance. The main weakness is verbosity - the extensive API reference and repeated curl examples inflate the token count when Claude could infer most of this from a few examples. The content would benefit from moving the full API reference to a separate file.
Suggestions
Move the detailed API Reference table and multiple curl examples to a separate REFERENCE.md file, keeping only 1-2 examples in the main skill
Consolidate the 'Basic Search' and 'Advanced Search' curl examples into a single example with inline comments showing optional parameters
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy - the curl examples repeat similar patterns multiple times, and the API reference table could be more compact. The OAuth explanation is appropriately brief. | 2 / 3 |
Actionability | Excellent actionability with fully executable bash/curl commands, complete JSON examples, and copy-paste ready code. Every example is concrete and immediately usable. | 3 / 3 |
Workflow Clarity | For a single-task skill (web search), the workflow is clear and unambiguous. Authentication steps are sequenced, and the quick start provides a clear path from basic to advanced usage. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but the API reference and multiple curl examples could be split into a separate reference file. The skill is somewhat monolithic at ~150 lines when the core usage could be much shorter. | 2 / 3 |
Total | 10 / 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.
- 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.