tavily-best-practices
Build production-ready Tavily integrations with best practices for web search, content extraction, crawling, and research in agentic workflows, RAG systems, and autonomous agents
52
60%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./content/tavily/skills/tavily-best-practices/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies the Tavily domain and lists relevant capability areas but reads more like a marketing tagline than a precise skill description. It lacks an explicit 'Use when...' clause, which is critical for skill selection, and the listed capabilities are category-level rather than concrete actions. The Tavily brand name provides some distinctiveness, but the surrounding terms are broad enough to cause overlap.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Tavily API integration, setting up Tavily search, or building search-augmented agents with Tavily.'
Replace broad category terms with concrete actions, e.g., 'Configure Tavily API keys, execute search queries, parse and rank search results, set up site crawling, and extract structured content from URLs.'
Include common user-facing trigger variations such as 'Tavily API', 'Tavily search tool', 'web search integration', and 'search-augmented generation' to improve matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Tavily) and lists several actions (web search, content extraction, crawling, research), but these read more like category labels than concrete specific actions. It lacks detail like 'configure API keys', 'parse search results', or 'set up crawl pipelines'. | 2 / 3 |
Completeness | It describes what the skill does (build Tavily integrations for various purposes) but completely lacks an explicit 'Use when...' clause or any trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also somewhat vague, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes 'Tavily', 'web search', 'content extraction', 'crawling', 'RAG', and 'agentic workflows' which are relevant keywords. However, it misses common user phrasings like 'search the web', 'Tavily API', 'search tool', or 'web scraping' and leans toward technical jargon ('agentic workflows', 'autonomous agents'). | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Tavily' specifically is distinctive and narrows the scope. However, terms like 'web search', 'content extraction', 'RAG systems', and 'agentic workflows' are broad enough to overlap with general web search skills, RAG pipeline skills, or agent-building skills. | 2 / 3 |
Total | 7 / 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-structured skill that efficiently covers the Tavily API surface area with executable examples and clear progressive disclosure to detailed references. The main weakness is the lack of error handling patterns and validation checkpoints, particularly for operations like crawl() and extract() that can fail or return unexpected results. The decision table for method selection is a particularly effective design choice.
Suggestions
Add error handling examples or validation checkpoints for extract/crawl operations (e.g., checking response status, handling rate limits, validating returned content)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what a search API is or how Python packages work. Every section provides direct, actionable content without padding. The table for method selection is an efficient way to convey decision logic. | 3 / 3 |
Actionability | Every method includes executable, copy-paste-ready Python code examples with real parameters. Key parameters are listed concisely for each method, and the client initialization shows multiple patterns including async. The research() example even includes the polling pattern. | 3 / 3 |
Workflow Clarity | The method selection table provides clear guidance on choosing the right approach, and the research() example shows a polling workflow. However, there are no validation checkpoints, error handling patterns, or feedback loops for operations like crawling or extraction that could fail or return partial results. | 2 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and quick reference in the main file, with clearly signaled one-level-deep references to detailed guides for each method. The 'Detailed Guides' section provides a well-organized navigation index with brief descriptions of what each reference contains. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- andrewyng/context-hub
- Commit
04c149c
- 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.