research
Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports.
85
77%
Does it follow best practices?
Impact
100%
6.25xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/tavily/research/SKILL.mdQuality
Discovery
67%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 description has good structure with an explicit 'Use when' clause that clearly communicates when to select this skill. However, it lacks concrete action verbs describing what the skill actually does (searches, synthesizes, cites) and could benefit from more natural trigger terms users would say. The distinctiveness is moderate—it could conflict with general research or report-writing skills.
Suggestions
Add specific action verbs: 'Searches multiple web sources, synthesizes findings, and generates explicit citations' instead of the abstract 'Comprehensive research grounded in web data'.
Expand trigger terms to include natural user phrases like 'look up', 'find information about', 'search for', 'fact-check', or 'verify'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (research, web data) and mentions some use cases (comparisons, current events, market analysis, detailed reports), but doesn't list concrete actions like 'searches multiple sources', 'extracts data', or 'generates citations'. | 2 / 3 |
Completeness | Clearly answers both what ('Comprehensive research grounded in web data with explicit citations') and when ('Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms users might say ('research', 'comparisons', 'current events', 'market analysis', 'reports', 'citations'), but missing common variations like 'look up', 'find information', 'search', 'sources', 'references', or 'fact-check'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on 'web data', 'citations', and 'multi-source synthesis' provides some distinction, but 'research' and 'reports' are generic enough to potentially overlap with other research or writing skills. | 2 / 3 |
Total | 9 / 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-crafted skill that efficiently teaches how to use the research script. It excels at actionability with concrete, executable examples and maintains excellent token efficiency. The main gap is the lack of error handling guidance for a network-dependent operation that can take up to 2 minutes.
Suggestions
Add a brief troubleshooting section covering common failure modes: OAuth timeout, API rate limits, or empty results
Consider adding guidance on what to do if research results are insufficient (e.g., refine query, try different model)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient. No unnecessary explanations of what research is or how APIs work. Every section serves a purpose with minimal padding. | 3 / 3 |
Actionability | Provides fully executable bash commands with concrete examples covering multiple use cases. Parameter table is clear and copy-paste ready. | 3 / 3 |
Workflow Clarity | For a simple single-action skill, the workflow is clear. However, there's no guidance on what to do if authentication fails, research times out, or results are unsatisfactory—missing validation/error recovery for a network-dependent operation. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (Authentication, Quick Start, Parameters, Model Selection, Examples). Appropriate length for a single-file skill with no need for external references. | 3 / 3 |
Total | 11 / 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.
- Repository
- tavily-ai/skills
- Commit
1e2a6a0
- 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.